From 5e5448f12527ed4b164b797b5250759fe4e0b603 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 11:54:23 -0800
Subject: [PATCH 01/11] v1

---
 .../celery/tasks/shared/RetryDocumentIndex.py |  32 ++-
 .../background/celery/tasks/shared/tasks.py   |  17 +-
 .../background/celery/tasks/vespa/tasks.py    |   9 +-
 backend/onyx/document_index/interfaces.py     |  17 +-
 backend/onyx/document_index/vespa/index.py    | 272 +++++++++---------
 .../scripts/force_delete_connector_by_id.py   |  15 +-
 backend/scripts/orphan_doc_cleanup_script.py  |  10 +-
 7 files changed, 212 insertions(+), 160 deletions(-)

diff --git a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
index 62a34196f60..7ed448d1b1d 100644
--- a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
+++ b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
@@ -28,13 +28,37 @@ def __init__(self, index: DocumentIndex):
         wait=wait_random_exponential(multiplier=1, max=MAX_WAIT),
         stop=stop_after_delay(STOP_AFTER),
     )
-    def delete_single(self, doc_id: str) -> int:
-        return self.index.delete_single(doc_id)
+    def delete_single(
+        self,
+        doc_id: str,
+        large_chunks_enabled: bool,
+        tenant_id: str | None,
+        chunk_count: int | None,
+    ) -> int:
+        return self.index.delete_single(
+            doc_id,
+            large_chunks_enabled=large_chunks_enabled,
+            tenant_id=tenant_id,
+            chunk_count=chunk_count,
+        )
 
     @retry(
         retry=retry_if_exception_type(httpx.ReadTimeout),
         wait=wait_random_exponential(multiplier=1, max=MAX_WAIT),
         stop=stop_after_delay(STOP_AFTER),
     )
-    def update_single(self, doc_id: str, fields: VespaDocumentFields) -> int:
-        return self.index.update_single(doc_id, fields)
+    def update_single(
+        self,
+        doc_id: str,
+        large_chunks_enabled: bool,
+        tenant_id: str | None,
+        chunk_count: int | None,
+        fields: VespaDocumentFields,
+    ) -> int:
+        return self.index.update_single(
+            doc_id,
+            large_chunks_enabled=large_chunks_enabled,
+            tenant_id=tenant_id,
+            chunk_count=chunk_count,
+            fields=fields,
+        )
diff --git a/backend/onyx/background/celery/tasks/shared/tasks.py b/backend/onyx/background/celery/tasks/shared/tasks.py
index 03a7ab83701..e30c3375697 100644
--- a/backend/onyx/background/celery/tasks/shared/tasks.py
+++ b/backend/onyx/background/celery/tasks/shared/tasks.py
@@ -80,7 +80,13 @@ def document_by_cc_pair_cleanup_task(
                 # delete it from vespa and the db
                 action = "delete"
 
-                chunks_affected = retry_index.delete_single(document_id)
+                # TODO: fix the large chunks enabled
+                chunks_affected = retry_index.delete_single(
+                    document_id,
+                    large_chunks_enabled=False,
+                    tenant_id=tenant_id,
+                    chunk_count=None,
+                )
                 delete_documents_complete__no_commit(
                     db_session=db_session,
                     document_ids=[document_id],
@@ -110,7 +116,14 @@ def document_by_cc_pair_cleanup_task(
                 )
 
                 # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
-                chunks_affected = retry_index.update_single(document_id, fields=fields)
+                # TODO: fix the large chunks enabled
+                chunks_affected = retry_index.update_single(
+                    document_id,
+                    large_chunks_enabled=False,
+                    tenant_id=tenant_id,
+                    chunk_count=doc.chunk_count,
+                    fields=fields,
+                )
 
                 # there are still other cc_pair references to the doc, so just resync to Vespa
                 delete_document_by_connector_credential_pair__no_commit(
diff --git a/backend/onyx/background/celery/tasks/vespa/tasks.py b/backend/onyx/background/celery/tasks/vespa/tasks.py
index c00bac354f3..591d55ec91b 100644
--- a/backend/onyx/background/celery/tasks/vespa/tasks.py
+++ b/backend/onyx/background/celery/tasks/vespa/tasks.py
@@ -992,7 +992,14 @@ def vespa_metadata_sync_task(
             )
 
             # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
-            chunks_affected = retry_index.update_single(document_id, fields)
+            # TODO: fix hte large chunks enabled
+            chunks_affected = retry_index.update_single(
+                document_id,
+                large_chunks_enabled=False,
+                tenant_id=tenant_id,
+                chunk_count=doc.chunk_count,
+                fields=fields,
+            )
 
             # update db last. Worst case = we crash right before this and
             # the sync might repeat again later
diff --git a/backend/onyx/document_index/interfaces.py b/backend/onyx/document_index/interfaces.py
index c97c87fd07e..d54f317247e 100644
--- a/backend/onyx/document_index/interfaces.py
+++ b/backend/onyx/document_index/interfaces.py
@@ -218,7 +218,13 @@ class Deletable(abc.ABC):
     """
 
     @abc.abstractmethod
-    def delete_single(self, doc_id: str) -> int:
+    def delete_single(
+        self,
+        doc_id: str,
+        large_chunks_enabled: bool,
+        tenant_id: str | None,
+        chunk_count: int | None,
+    ) -> int:
         """
         Given a single document id, hard delete it from the document index
 
@@ -239,7 +245,14 @@ class Updatable(abc.ABC):
     """
 
     @abc.abstractmethod
-    def update_single(self, doc_id: str, fields: VespaDocumentFields) -> int:
+    def update_single(
+        self,
+        doc_id: str,
+        large_chunks_enabled: bool,
+        chunk_count: int | None,
+        tenant_id: str | None,
+        fields: VespaDocumentFields,
+    ) -> int:
         """
         Updates all chunks for a document with the specified fields.
         None values mean that the field does not need an update.
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 80e5504fa8e..54cd608f6ef 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -13,11 +13,11 @@
 from typing import BinaryIO
 from typing import cast
 from typing import List
+from uuid import UUID
 
 import httpx  # type: ignore
 import requests  # type: ignore
 
-from onyx.configs.app_configs import DOCUMENT_INDEX_NAME
 from onyx.configs.chat_configs import DOC_TIME_DECAY
 from onyx.configs.chat_configs import NUM_RETURNED_HITS
 from onyx.configs.chat_configs import TITLE_CONTENT_RATIO
@@ -336,37 +336,21 @@ def index(
             # know precisely which chunks to delete. This information exists for
             # documents that have `chunk_count` in the database, but not for
             # `old_version` documents.
+            enriched_doc_infos: list[EnrichedDocumentIndexingInfo] = [
+                VespaIndex.enrich_basic_chunk_info(
+                    index_name=self.index_name,
+                    http_client=http_client,
+                    document_id=doc_id,
+                    previous_chunk_count=doc_id_to_previous_chunk_cnt.get(doc_id),
+                    new_chunk_count=doc_id_to_new_chunk_cnt.get(doc_id, 0),
+                )
+                for doc_id in doc_id_to_new_chunk_cnt.keys()
+            ]
 
-            enriched_doc_infos: list[EnrichedDocumentIndexingInfo] = []
-            for document_id, doc_count in doc_id_to_previous_chunk_cnt.items():
-                last_indexed_chunk = doc_id_to_previous_chunk_cnt.get(document_id, None)
-                # If the document has no `chunk_count` in the database, we know that it
-                # has the old chunk ID system and we must check for the final chunk index
-                is_old_version = False
-                if last_indexed_chunk is None:
-                    is_old_version = True
-                    minimal_doc_info = MinimalDocumentIndexingInfo(
-                        doc_id=document_id,
-                        chunk_start_index=doc_id_to_new_chunk_cnt.get(document_id, 0),
-                    )
-                    last_indexed_chunk = check_for_final_chunk_existence(
-                        minimal_doc_info=minimal_doc_info,
-                        start_index=doc_id_to_new_chunk_cnt[document_id],
-                        index_name=self.index_name,
-                        http_client=http_client,
-                    )
-
+            for cleaned_doc_info in enriched_doc_infos:
                 # If the document has previously indexed chunks, we know it previously existed
-                if doc_count or last_indexed_chunk:
-                    existing_docs.add(document_id)
-
-                enriched_doc_info = EnrichedDocumentIndexingInfo(
-                    doc_id=document_id,
-                    chunk_start_index=doc_id_to_new_chunk_cnt.get(document_id, 0),
-                    chunk_end_index=last_indexed_chunk,
-                    old_version=is_old_version,
-                )
-                enriched_doc_infos.append(enriched_doc_info)
+                if cleaned_doc_info.chunk_end_index:
+                    existing_docs.add(cleaned_doc_info.doc_id)
 
             # Now, for each doc, we know exactly where to start and end our deletion
             # So let's generate the chunk IDs for each chunk to delete
@@ -537,19 +521,12 @@ def update(self, update_requests: list[UpdateRequest]) -> None:
             time.monotonic() - update_start,
         )
 
-    def update_single(self, doc_id: str, fields: VespaDocumentFields) -> int:
-        """Note: if the document id does not exist, the update will be a no-op and the
-        function will complete with no errors or exceptions.
-        Handle other exceptions if you wish to implement retry behavior
-        """
-
-        total_chunks_updated = 0
-
-        # Handle Vespa character limitations
-        # Mutating update_request but it's not used later anyway
-        normalized_doc_id = replace_invalid_doc_id_characters(doc_id)
+    def update_single_chunk(
+        self, doc_chunk_id: UUID, index_name: str, fields: VespaDocumentFields
+    ) -> None:
+        """Update a single chunk in Vespa using its chunk ID."""
 
-        # Build the _VespaUpdateRequest objects
+        # Build the update request
         update_dict: dict[str, dict] = {"fields": {}}
         if fields.boost is not None:
             update_dict["fields"][BOOST] = {"assign": fields.boost}
@@ -566,7 +543,39 @@ def update_single(self, doc_id: str, fields: VespaDocumentFields) -> int:
 
         if not update_dict["fields"]:
             logger.error("Update request received but nothing to update")
-            return 0
+            return
+
+        with get_vespa_http_client(http2=False) as http_client:
+            vespa_url = (
+                f"{DOCUMENT_ID_ENDPOINT.format(index_name=index_name)}/{doc_chunk_id}"
+            )
+
+            try:
+                logger.debug(f'update_single PUT on URL "{vespa_url}"')
+                resp = http_client.put(
+                    vespa_url,
+                    headers={"Content-Type": "application/json"},
+                    json=update_dict,
+                )
+                resp.raise_for_status()
+
+            except httpx.HTTPStatusError as e:
+                logger.error(f"Failed to update chunk, details: {e.response.text}")
+                raise
+
+    def update_single(
+        self,
+        doc_id: str,
+        large_chunks_enabled: bool,
+        chunk_count: int | None,
+        tenant_id: str | None,
+        fields: VespaDocumentFields,
+    ) -> int:
+        """Note: if the document id does not exist, the update will be a no-op and the
+        function will complete with no errors or exceptions.
+        Handle other exceptions if you wish to implement retry behavior
+        """
+        doc_chunk_count = 0
 
         index_names = [self.index_name]
         if self.secondary_index_name:
@@ -574,66 +583,38 @@ def update_single(self, doc_id: str, fields: VespaDocumentFields) -> int:
 
         with get_vespa_http_client(http2=False) as http_client:
             for index_name in index_names:
-                params = httpx.QueryParams(
-                    {
-                        "selection": f"{index_name}.document_id=='{normalized_doc_id}'",
-                        "cluster": DOCUMENT_INDEX_NAME,
-                    }
+                enriched_doc_infos = VespaIndex.enrich_basic_chunk_info(
+                    index_name=index_name,
+                    http_client=http_client,
+                    document_id=doc_id,
+                    previous_chunk_count=chunk_count,
+                    new_chunk_count=0,
                 )
-
-                while True:
-                    try:
-                        vespa_url = (
-                            f"{DOCUMENT_ID_ENDPOINT.format(index_name=self.index_name)}"
-                        )
-                        logger.debug(f'update_single PUT on URL "{vespa_url}"')
-                        resp = http_client.put(
-                            vespa_url,
-                            params=params,
-                            headers={"Content-Type": "application/json"},
-                            json=update_dict,
-                        )
-
-                        resp.raise_for_status()
-                    except httpx.HTTPStatusError as e:
-                        logger.error(
-                            f"Failed to update chunks, details: {e.response.text}"
-                        )
-                        raise
-
-                    resp_data = resp.json()
-
-                    if "documentCount" in resp_data:
-                        chunks_updated = resp_data["documentCount"]
-                        total_chunks_updated += chunks_updated
-
-                    # Check for continuation token to handle pagination
-                    if "continuation" not in resp_data:
-                        break  # Exit loop if no continuation token
-
-                    if not resp_data["continuation"]:
-                        break  # Exit loop if continuation token is empty
-
-                    params = params.set("continuation", resp_data["continuation"])
-
-                logger.debug(
-                    f"VespaIndex.update_single: "
-                    f"index={index_name} "
-                    f"doc={normalized_doc_id} "
-                    f"chunks_updated={total_chunks_updated}"
+                doc_chunk_ids = assemble_document_chunk_info(
+                    enriched_document_info_list=[enriched_doc_infos],
+                    tenant_id=tenant_id,
+                    large_chunks_enabled=large_chunks_enabled,
                 )
+                doc_chunk_count += len(doc_chunk_ids)
 
-        return total_chunks_updated
+                for doc_chunk_id in doc_chunk_ids:
+                    self.update_single_chunk(
+                        doc_chunk_id=doc_chunk_id, index_name=index_name, fields=fields
+                    )
+        return doc_chunk_count
 
-    def delete_single(self, doc_id: str) -> int:
+    def delete_single(
+        self,
+        doc_id: str,
+        large_chunks_enabled: bool,
+        tenant_id: str | None,
+        chunk_count: int | None,
+    ) -> int:
         """Possibly faster overall than the delete method due to using a single
         delete call with a selection query."""
 
         total_chunks_deleted = 0
 
-        # Vespa deletion is poorly documented ... luckily we found this
-        # https://docs.vespa.ai/en/operations/batch-delete.html#example
-
         doc_id = replace_invalid_doc_id_characters(doc_id)
 
         # NOTE: using `httpx` here since `requests` doesn't support HTTP2. This is beneficial for
@@ -642,53 +623,34 @@ def delete_single(self, doc_id: str) -> int:
         if self.secondary_index_name:
             index_names.append(self.secondary_index_name)
 
-        with get_vespa_http_client(http2=False) as http_client:
+        with get_vespa_http_client(
+            http2=False
+        ) as http_client, concurrent.futures.ThreadPoolExecutor(
+            max_workers=NUM_THREADS
+        ) as executor:
             for index_name in index_names:
-                params = httpx.QueryParams(
-                    {
-                        "selection": f"{index_name}.document_id=='{doc_id}'",
-                        "cluster": DOCUMENT_INDEX_NAME,
-                    }
+                enriched_doc_infos = VespaIndex.enrich_basic_chunk_info(
+                    index_name=index_name,
+                    http_client=http_client,
+                    document_id=doc_id,
+                    previous_chunk_count=chunk_count,
+                    new_chunk_count=0,
                 )
-
-                while True:
-                    try:
-                        vespa_url = (
-                            f"{DOCUMENT_ID_ENDPOINT.format(index_name=index_name)}"
-                        )
-                        logger.debug(f'delete_single DELETE on URL "{vespa_url}"')
-                        resp = http_client.delete(
-                            vespa_url,
-                            params=params,
-                        )
-                        resp.raise_for_status()
-                    except httpx.HTTPStatusError as e:
-                        logger.error(
-                            f"Failed to delete chunk, details: {e.response.text}"
-                        )
-                        raise
-
-                    resp_data = resp.json()
-
-                    if "documentCount" in resp_data:
-                        chunks_deleted = resp_data["documentCount"]
-                        total_chunks_deleted += chunks_deleted
-
-                    # Check for continuation token to handle pagination
-                    if "continuation" not in resp_data:
-                        break  # Exit loop if no continuation token
-
-                    if not resp_data["continuation"]:
-                        break  # Exit loop if continuation token is empty
-
-                    params = params.set("continuation", resp_data["continuation"])
-
-                logger.debug(
-                    f"VespaIndex.delete_single: "
-                    f"index={index_name} "
-                    f"doc={doc_id} "
-                    f"chunks_deleted={total_chunks_deleted}"
+                chunks_to_delete = assemble_document_chunk_info(
+                    enriched_document_info_list=[enriched_doc_infos],
+                    tenant_id=tenant_id,
+                    large_chunks_enabled=large_chunks_enabled,
                 )
+                for doc_chunk_ids_batch in batch_generator(
+                    chunks_to_delete, BATCH_SIZE
+                ):
+                    total_chunks_deleted += len(doc_chunk_ids_batch)
+                    delete_vespa_chunks(
+                        doc_chunk_ids=doc_chunk_ids_batch,
+                        index_name=index_name,
+                        http_client=http_client,
+                        executor=executor,
+                    )
 
         return total_chunks_deleted
 
@@ -787,6 +749,40 @@ def admin_retrieval(
 
         return query_vespa(params)
 
+    @classmethod
+    def enrich_basic_chunk_info(
+        cls,
+        index_name: str,
+        http_client: httpx.Client,
+        document_id: str,
+        previous_chunk_count: int | None = None,
+        new_chunk_count: int = 0,
+    ) -> EnrichedDocumentIndexingInfo:
+        last_indexed_chunk = previous_chunk_count
+
+        # If the document has no `chunk_count` in the database, we know that it
+        # has the old chunk ID system and we must check for the final chunk index
+        is_old_version = False
+        if last_indexed_chunk is None:
+            is_old_version = True
+            minimal_doc_info = MinimalDocumentIndexingInfo(
+                doc_id=document_id, chunk_start_index=new_chunk_count
+            )
+            last_indexed_chunk = check_for_final_chunk_existence(
+                minimal_doc_info=minimal_doc_info,
+                start_index=new_chunk_count,
+                index_name=index_name,
+                http_client=http_client,
+            )
+
+        enriched_doc_info = EnrichedDocumentIndexingInfo(
+            doc_id=document_id,
+            chunk_start_index=new_chunk_count,
+            chunk_end_index=last_indexed_chunk,
+            old_version=is_old_version,
+        )
+        return enriched_doc_info
+
     @classmethod
     def delete_entries_by_tenant_id(cls, tenant_id: str, index_name: str) -> None:
         """
diff --git a/backend/scripts/force_delete_connector_by_id.py b/backend/scripts/force_delete_connector_by_id.py
index bc994238870..3f0bf01ad61 100755
--- a/backend/scripts/force_delete_connector_by_id.py
+++ b/backend/scripts/force_delete_connector_by_id.py
@@ -38,7 +38,6 @@
 from onyx.document_index.factory import get_default_document_index
 from onyx.file_store.file_store import get_default_file_store
 from onyx.document_index.document_index_utils import get_both_index_names
-from onyx.db.document import delete_documents_complete__no_commit
 
 # pylint: enable=E402
 # flake8: noqa: E402
@@ -71,14 +70,14 @@ def _unsafe_deletion(
         if not documents:
             break
 
-        document_ids = [document.id for document in documents]
-        for doc_id in document_ids:
-            document_index.delete_single(doc_id)
+        # document_ids = [document.id for document in documents]
+        # for doc_id in document_ids:
+        #     document_index.delete_single(doc_id)
 
-        delete_documents_complete__no_commit(
-            db_session=db_session,
-            document_ids=document_ids,
-        )
+        # delete_documents_complete__no_commit(
+        #     db_session=db_session,
+        #     document_ids=document_ids,
+        # )
 
         num_docs_deleted += len(documents)
 
diff --git a/backend/scripts/orphan_doc_cleanup_script.py b/backend/scripts/orphan_doc_cleanup_script.py
index ea776e770eb..6d404f7f52e 100644
--- a/backend/scripts/orphan_doc_cleanup_script.py
+++ b/backend/scripts/orphan_doc_cleanup_script.py
@@ -83,11 +83,11 @@ def process_doc(doc_id: str) -> str | None:
 
                     try:
                         print(f"Deleting document {doc_id} in Vespa")
-                        chunks_deleted = vespa_index.delete_single(doc_id)
-                        if chunks_deleted > 0:
-                            print(
-                                f"Deleted {chunks_deleted} chunks for document {doc_id}"
-                            )
+                        # chunks_deleted = vespa_index.delete_single(doc_id)
+                        # if chunks_deleted > 0:
+                        #     print(
+                        #         f"Deleted {chunks_deleted} chunks for document {doc_id}"
+                        #     )
                         return doc_id
                     except Exception as e:
                         print(

From c35ccd2cf16439380995197628db1cd61ea9f389 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 12:43:31 -0800
Subject: [PATCH 02/11] update indexing logic

---
 .../celery/tasks/shared/RetryDocumentIndex.py |  3 -
 .../background/celery/tasks/shared/tasks.py   |  1 -
 backend/onyx/document_index/interfaces.py     |  8 +-
 backend/onyx/document_index/vespa/index.py    | 87 +++++++++++--------
 .../document_index/vespa/indexing_utils.py    | 53 ++++++++++-
 backend/onyx/indexing/indexing_pipeline.py    | 36 ++------
 backend/onyx/indexing/models.py               |  5 ++
 7 files changed, 117 insertions(+), 76 deletions(-)

diff --git a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
index 7ed448d1b1d..1f0cd000402 100644
--- a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
+++ b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
@@ -31,13 +31,11 @@ def __init__(self, index: DocumentIndex):
     def delete_single(
         self,
         doc_id: str,
-        large_chunks_enabled: bool,
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
         return self.index.delete_single(
             doc_id,
-            large_chunks_enabled=large_chunks_enabled,
             tenant_id=tenant_id,
             chunk_count=chunk_count,
         )
@@ -57,7 +55,6 @@ def update_single(
     ) -> int:
         return self.index.update_single(
             doc_id,
-            large_chunks_enabled=large_chunks_enabled,
             tenant_id=tenant_id,
             chunk_count=chunk_count,
             fields=fields,
diff --git a/backend/onyx/background/celery/tasks/shared/tasks.py b/backend/onyx/background/celery/tasks/shared/tasks.py
index e30c3375697..e1e901475cd 100644
--- a/backend/onyx/background/celery/tasks/shared/tasks.py
+++ b/backend/onyx/background/celery/tasks/shared/tasks.py
@@ -83,7 +83,6 @@ def document_by_cc_pair_cleanup_task(
                 # TODO: fix the large chunks enabled
                 chunks_affected = retry_index.delete_single(
                     document_id,
-                    large_chunks_enabled=False,
                     tenant_id=tenant_id,
                     chunk_count=None,
                 )
diff --git a/backend/onyx/document_index/interfaces.py b/backend/onyx/document_index/interfaces.py
index d54f317247e..85bfb7ae3d6 100644
--- a/backend/onyx/document_index/interfaces.py
+++ b/backend/onyx/document_index/interfaces.py
@@ -109,7 +109,7 @@ class UpdateRequest:
     Does not update any of the None fields
     """
 
-    document_ids: list[str]
+    minimal_document_indexing_info: list[MinimalDocumentIndexingInfo]
     # all other fields except these 4 will always be left alone by the update request
     access: DocumentAccess | None = None
     document_sets: set[str] | None = None
@@ -221,7 +221,6 @@ class Deletable(abc.ABC):
     def delete_single(
         self,
         doc_id: str,
-        large_chunks_enabled: bool,
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
@@ -248,7 +247,6 @@ class Updatable(abc.ABC):
     def update_single(
         self,
         doc_id: str,
-        large_chunks_enabled: bool,
         chunk_count: int | None,
         tenant_id: str | None,
         fields: VespaDocumentFields,
@@ -270,7 +268,9 @@ def update_single(
         raise NotImplementedError
 
     @abc.abstractmethod
-    def update(self, update_requests: list[UpdateRequest]) -> None:
+    def update(
+        self, update_requests: list[UpdateRequest], tenant_id: str | None
+    ) -> None:
         """
         Updates some set of chunks. The document and fields to update are specified in the update
         requests. Each update request in the list applies its changes to a list of document ids.
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 54cd608f6ef..2519c3e6f4c 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -25,6 +25,7 @@
 from onyx.configs.constants import KV_REINDEX_KEY
 from onyx.context.search.models import IndexFilters
 from onyx.context.search.models import InferenceChunkUncleaned
+from onyx.db.engine import get_session_with_tenant
 from onyx.document_index.document_index_utils import assemble_document_chunk_info
 from onyx.document_index.interfaces import DocumentIndex
 from onyx.document_index.interfaces import DocumentInsertionRecord
@@ -35,15 +36,15 @@
 from onyx.document_index.interfaces import VespaChunkRequest
 from onyx.document_index.interfaces import VespaDocumentFields
 from onyx.document_index.vespa.chunk_retrieval import batch_search_api_retrieval
-from onyx.document_index.vespa.chunk_retrieval import (
-    get_all_vespa_ids_for_document_id,
-)
 from onyx.document_index.vespa.chunk_retrieval import (
     parallel_visit_api_retrieval,
 )
 from onyx.document_index.vespa.chunk_retrieval import query_vespa
 from onyx.document_index.vespa.deletion import delete_vespa_chunks
 from onyx.document_index.vespa.indexing_utils import batch_index_vespa_chunks
+from onyx.document_index.vespa.indexing_utils import (
+    check_enable_large_chunks_and_multipass,
+)
 from onyx.document_index.vespa.indexing_utils import check_for_final_chunk_existence
 from onyx.document_index.vespa.indexing_utils import clean_chunk_id_copy
 from onyx.document_index.vespa.shared_utils.utils import get_vespa_http_client
@@ -431,21 +432,21 @@ def _update_chunk(
                         failure_msg = f"Failed to update document: {future_to_document_id[future]}"
                         raise requests.HTTPError(failure_msg) from e
 
-    def update(self, update_requests: list[UpdateRequest]) -> None:
+    def update(
+        self, update_requests: list[UpdateRequest], tenant_id: str | None
+    ) -> None:
         logger.debug(f"Updating {len(update_requests)} documents in Vespa")
 
         # Handle Vespa character limitations
         # Mutating update_requests but it's not used later anyway
         for update_request in update_requests:
-            update_request.document_ids = [
-                replace_invalid_doc_id_characters(doc_id)
-                for doc_id in update_request.document_ids
-            ]
+            for doc_info in update_request.minimal_document_indexing_info:
+                doc_info.doc_id = replace_invalid_doc_id_characters(doc_info.doc_id)
 
         update_start = time.monotonic()
 
         processed_updates_requests: list[_VespaUpdateRequest] = []
-        all_doc_chunk_ids: dict[str, list[str]] = {}
+        all_doc_chunk_ids: dict[str, list[UUID]] = {}
 
         # Fetch all chunks for each document ahead of time
         index_names = [self.index_name]
@@ -453,30 +454,24 @@ def update(self, update_requests: list[UpdateRequest]) -> None:
             index_names.append(self.secondary_index_name)
 
         chunk_id_start_time = time.monotonic()
-        with concurrent.futures.ThreadPoolExecutor(max_workers=NUM_THREADS) as executor:
-            future_to_doc_chunk_ids = {
-                executor.submit(
-                    get_all_vespa_ids_for_document_id,
-                    document_id=document_id,
-                    index_name=index_name,
-                    filters=None,
-                    get_large_chunks=True,
-                ): (document_id, index_name)
-                for index_name in index_names
-                for update_request in update_requests
-                for document_id in update_request.document_ids
-            }
-            for future in concurrent.futures.as_completed(future_to_doc_chunk_ids):
-                document_id, index_name = future_to_doc_chunk_ids[future]
-                try:
-                    doc_chunk_ids = future.result()
-                    if document_id not in all_doc_chunk_ids:
-                        all_doc_chunk_ids[document_id] = []
-                    all_doc_chunk_ids[document_id].extend(doc_chunk_ids)
-                except Exception as e:
-                    logger.error(
-                        f"Error retrieving chunk IDs for document {document_id} in index {index_name}: {e}"
-                    )
+        with get_vespa_http_client() as http_client:
+            for update_request in update_requests:
+                for doc_info in update_request.minimal_document_indexing_info:
+                    for index_name in index_names:
+                        doc_chunk_info = self.enrich_basic_chunk_info(
+                            index_name=index_name,
+                            http_client=http_client,
+                            document_id=doc_info.doc_id,
+                            previous_chunk_count=doc_info.chunk_start_index,
+                            new_chunk_count=0,
+                        )
+                        doc_chunk_ids = assemble_document_chunk_info(
+                            enriched_document_info_list=[doc_chunk_info],
+                            tenant_id=tenant_id,
+                            large_chunks_enabled=False,
+                        )
+                        all_doc_chunk_ids[doc_info.doc_id] = doc_chunk_ids
+
         logger.debug(
             f"Took {time.monotonic() - chunk_id_start_time:.2f} seconds to fetch all Vespa chunk IDs"
         )
@@ -505,11 +500,11 @@ def update(self, update_requests: list[UpdateRequest]) -> None:
                 logger.error("Update request received but nothing to update")
                 continue
 
-            for document_id in update_request.document_ids:
-                for doc_chunk_id in all_doc_chunk_ids[document_id]:
+            for doc_info in update_request.minimal_document_indexing_info:
+                for doc_chunk_id in all_doc_chunk_ids[doc_info.doc_id]:
                     processed_updates_requests.append(
                         _VespaUpdateRequest(
-                            document_id=document_id,
+                            document_id=doc_info.doc_id,
                             url=f"{DOCUMENT_ID_ENDPOINT.format(index_name=self.index_name)}/{doc_chunk_id}",
                             update_request=update_dict,
                         )
@@ -566,7 +561,6 @@ def update_single_chunk(
     def update_single(
         self,
         doc_id: str,
-        large_chunks_enabled: bool,
         chunk_count: int | None,
         tenant_id: str | None,
         fields: VespaDocumentFields,
@@ -583,6 +577,15 @@ def update_single(
 
         with get_vespa_http_client(http2=False) as http_client:
             for index_name in index_names:
+                large_chunks_enabled = False
+
+                with get_session_with_tenant(tenant_id=tenant_id) as db_session:
+                    multipass_config = check_enable_large_chunks_and_multipass(
+                        db_session=db_session,
+                        primary_index=index_name == self.index_name,
+                    )
+                    large_chunks_enabled = multipass_config.enable_large_chunks
+
                 enriched_doc_infos = VespaIndex.enrich_basic_chunk_info(
                     index_name=index_name,
                     http_client=http_client,
@@ -601,12 +604,12 @@ def update_single(
                     self.update_single_chunk(
                         doc_chunk_id=doc_chunk_id, index_name=index_name, fields=fields
                     )
+
         return doc_chunk_count
 
     def delete_single(
         self,
         doc_id: str,
-        large_chunks_enabled: bool,
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
@@ -629,6 +632,14 @@ def delete_single(
             max_workers=NUM_THREADS
         ) as executor:
             for index_name in index_names:
+                large_chunks_enabled = False
+                with get_session_with_tenant(tenant_id=tenant_id) as db_session:
+                    multipass_config = check_enable_large_chunks_and_multipass(
+                        db_session=db_session,
+                        primary_index=index_name == self.index_name,
+                    )
+                    large_chunks_enabled = multipass_config.enable_large_chunks
+
                 enriched_doc_infos = VespaIndex.enrich_basic_chunk_info(
                     index_name=index_name,
                     http_client=http_client,
diff --git a/backend/onyx/document_index/vespa/indexing_utils.py b/backend/onyx/document_index/vespa/indexing_utils.py
index 6781cae1d93..a8d35e996db 100644
--- a/backend/onyx/document_index/vespa/indexing_utils.py
+++ b/backend/onyx/document_index/vespa/indexing_utils.py
@@ -7,10 +7,15 @@
 
 import httpx
 from retry import retry
+from sqlalchemy.orm import Session
 
+from onyx.configs.app_configs import ENABLE_MULTIPASS_INDEXING
 from onyx.connectors.cross_connector_utils.miscellaneous_utils import (
     get_experts_stores_representations,
 )
+from onyx.db.models import SearchSettings
+from onyx.db.search_settings import get_current_search_settings
+from onyx.db.search_settings import get_secondary_search_settings
 from onyx.document_index.document_index_utils import get_uuid_from_chunk
 from onyx.document_index.document_index_utils import get_uuid_from_chunk_info_old
 from onyx.document_index.interfaces import MinimalDocumentIndexingInfo
@@ -45,6 +50,8 @@
 from onyx.document_index.vespa_constants import TITLE
 from onyx.document_index.vespa_constants import TITLE_EMBEDDING
 from onyx.indexing.models import DocMetadataAwareIndexChunk
+from onyx.indexing.models import EmbeddingProvider
+from onyx.indexing.models import MultipassConfig
 from onyx.utils.logger import setup_logger
 
 logger = setup_logger()
@@ -263,5 +270,49 @@ def check_for_final_chunk_existence(
         )
         if not _does_doc_chunk_exist(doc_chunk_id, index_name, http_client):
             return index
-
         index += 1
+
+
+def should_use_multipass(search_settings: SearchSettings | None) -> bool:
+    """
+    Determines whether multipass should be used based on the search settings
+    or the default config if settings are unavailable.
+    """
+    if search_settings is not None:
+        return search_settings.multipass_indexing
+    return ENABLE_MULTIPASS_INDEXING
+
+
+def can_use_large_chunks(multipass: bool, search_settings: SearchSettings) -> bool:
+    """
+    Given multipass usage and an embedder, decides whether large chunks are allowed
+    based on model/provider constraints.
+    """
+    # Only local models that support a larger context are from Nomic
+    # Cohere does not support larger contexts (they recommend not going above ~512 tokens)
+    return (
+        multipass
+        and search_settings.model_name.startswith("nomic-ai")
+        and search_settings.provider_type != EmbeddingProvider.COHERE
+    )
+
+
+def check_enable_large_chunks_and_multipass(
+    db_session: Session, primary_index: bool = True
+) -> MultipassConfig:
+    """
+    Determines whether to enable multipass and large chunks by examining
+    the current search settings and the embedder configuration.
+    """
+    search_settings = (
+        get_current_search_settings(db_session)
+        if primary_index
+        else get_secondary_search_settings(db_session)
+    )
+    multipass = should_use_multipass(search_settings)
+    if not search_settings:
+        return MultipassConfig(multipass_indexing=False, enable_large_chunks=False)
+    enable_large_chunks = can_use_large_chunks(multipass, search_settings)
+    return MultipassConfig(
+        multipass_indexing=multipass, enable_large_chunks=enable_large_chunks
+    )
diff --git a/backend/onyx/indexing/indexing_pipeline.py b/backend/onyx/indexing/indexing_pipeline.py
index 1a2e73b2ab1..1502ac6b3d3 100644
--- a/backend/onyx/indexing/indexing_pipeline.py
+++ b/backend/onyx/indexing/indexing_pipeline.py
@@ -11,7 +11,6 @@
 
 from onyx.access.access import get_access_for_documents
 from onyx.access.models import DocumentAccess
-from onyx.configs.app_configs import ENABLE_MULTIPASS_INDEXING
 from onyx.configs.app_configs import INDEXING_EXCEPTION_LIMIT
 from onyx.configs.app_configs import MAX_DOCUMENT_CHARS
 from onyx.configs.constants import DEFAULT_BOOST
@@ -31,12 +30,14 @@
 from onyx.db.document_set import fetch_document_sets_for_documents
 from onyx.db.index_attempt import create_index_attempt_error
 from onyx.db.models import Document as DBDocument
-from onyx.db.search_settings import get_current_search_settings
 from onyx.db.tag import create_or_add_document_tag
 from onyx.db.tag import create_or_add_document_tag_list
 from onyx.document_index.interfaces import DocumentIndex
 from onyx.document_index.interfaces import DocumentMetadata
 from onyx.document_index.interfaces import IndexBatchParams
+from onyx.document_index.vespa.indexing_utils import (
+    check_enable_large_chunks_and_multipass,
+)
 from onyx.indexing.chunker import Chunker
 from onyx.indexing.embedder import IndexingEmbedder
 from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
@@ -44,7 +45,6 @@
 from onyx.indexing.models import DocMetadataAwareIndexChunk
 from onyx.utils.logger import setup_logger
 from onyx.utils.timing import log_function_time
-from shared_configs.enums import EmbeddingProvider
 
 logger = setup_logger()
 
@@ -479,28 +479,6 @@ def index_doc_batch(
     return result
 
 
-def check_enable_large_chunks_and_multipass(
-    embedder: IndexingEmbedder, db_session: Session
-) -> tuple[bool, bool]:
-    search_settings = get_current_search_settings(db_session)
-    multipass = (
-        search_settings.multipass_indexing
-        if search_settings
-        else ENABLE_MULTIPASS_INDEXING
-    )
-
-    enable_large_chunks = (
-        multipass
-        and
-        # Only local models that supports larger context are from Nomic
-        (embedder.model_name.startswith("nomic-ai"))
-        and
-        # Cohere does not support larger context they recommend not going above 512 tokens
-        embedder.provider_type != EmbeddingProvider.COHERE
-    )
-    return multipass, enable_large_chunks
-
-
 def build_indexing_pipeline(
     *,
     embedder: IndexingEmbedder,
@@ -513,14 +491,14 @@ def build_indexing_pipeline(
     callback: IndexingHeartbeatInterface | None = None,
 ) -> IndexingPipelineProtocol:
     """Builds a pipeline which takes in a list (batch) of docs and indexes them."""
-    multipass, enable_large_chunks = check_enable_large_chunks_and_multipass(
-        embedder, db_session
+    multipass_config = check_enable_large_chunks_and_multipass(
+        db_session, primary_index=True
     )
 
     chunker = chunker or Chunker(
         tokenizer=embedder.embedding_model.tokenizer,
-        enable_multipass=multipass,
-        enable_large_chunks=enable_large_chunks,
+        enable_multipass=multipass_config.multipass_indexing,
+        enable_large_chunks=multipass_config.enable_large_chunks,
         # after every doc, update status in case there are a bunch of really long docs
         callback=callback,
     )
diff --git a/backend/onyx/indexing/models.py b/backend/onyx/indexing/models.py
index e536428282b..44a8419cb95 100644
--- a/backend/onyx/indexing/models.py
+++ b/backend/onyx/indexing/models.py
@@ -154,3 +154,8 @@ def from_db_model(cls, search_settings: "SearchSettings") -> "IndexingSetting":
             index_name=search_settings.index_name,
             multipass_indexing=search_settings.multipass_indexing,
         )
+
+
+class MultipassConfig(BaseModel):
+    multipass_indexing: bool
+    enable_large_chunks: bool

From d0629d9cded5d8d10516b7d7b27343fd059e0def Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 13:01:47 -0800
Subject: [PATCH 03/11] update updates

---
 .../onyx/background/celery/tasks/shared/RetryDocumentIndex.py   | 2 +-
 backend/onyx/background/celery/tasks/shared/tasks.py            | 1 -
 backend/onyx/background/celery/tasks/vespa/tasks.py             | 2 --
 backend/onyx/document_index/vespa/index.py                      | 1 +
 4 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
index 1f0cd000402..cf3afefeb95 100644
--- a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
+++ b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
@@ -48,11 +48,11 @@ def delete_single(
     def update_single(
         self,
         doc_id: str,
-        large_chunks_enabled: bool,
         tenant_id: str | None,
         chunk_count: int | None,
         fields: VespaDocumentFields,
     ) -> int:
+        print("Update single")
         return self.index.update_single(
             doc_id,
             tenant_id=tenant_id,
diff --git a/backend/onyx/background/celery/tasks/shared/tasks.py b/backend/onyx/background/celery/tasks/shared/tasks.py
index e1e901475cd..a7050b57498 100644
--- a/backend/onyx/background/celery/tasks/shared/tasks.py
+++ b/backend/onyx/background/celery/tasks/shared/tasks.py
@@ -118,7 +118,6 @@ def document_by_cc_pair_cleanup_task(
                 # TODO: fix the large chunks enabled
                 chunks_affected = retry_index.update_single(
                     document_id,
-                    large_chunks_enabled=False,
                     tenant_id=tenant_id,
                     chunk_count=doc.chunk_count,
                     fields=fields,
diff --git a/backend/onyx/background/celery/tasks/vespa/tasks.py b/backend/onyx/background/celery/tasks/vespa/tasks.py
index 591d55ec91b..8eabeb7d8a8 100644
--- a/backend/onyx/background/celery/tasks/vespa/tasks.py
+++ b/backend/onyx/background/celery/tasks/vespa/tasks.py
@@ -992,10 +992,8 @@ def vespa_metadata_sync_task(
             )
 
             # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
-            # TODO: fix hte large chunks enabled
             chunks_affected = retry_index.update_single(
                 document_id,
-                large_chunks_enabled=False,
                 tenant_id=tenant_id,
                 chunk_count=doc.chunk_count,
                 fields=fields,
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 2519c3e6f4c..681dee153e8 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -601,6 +601,7 @@ def update_single(
                 doc_chunk_count += len(doc_chunk_ids)
 
                 for doc_chunk_id in doc_chunk_ids:
+                    print("THIS ONE is being updated")
                     self.update_single_chunk(
                         doc_chunk_id=doc_chunk_id, index_name=index_name, fields=fields
                     )

From 87efb1db5eb8cd5074c2110f974e6bbe9f24617d Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 13:02:34 -0800
Subject: [PATCH 04/11] nit

---
 backend/onyx/document_index/vespa/index.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 681dee153e8..4dc42a9671c 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -578,7 +578,6 @@ def update_single(
         with get_vespa_http_client(http2=False) as http_client:
             for index_name in index_names:
                 large_chunks_enabled = False
-
                 with get_session_with_tenant(tenant_id=tenant_id) as db_session:
                     multipass_config = check_enable_large_chunks_and_multipass(
                         db_session=db_session,

From c2db6de8c3fb2e065cbbd19dcdf40820d6fddb24 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 13:09:09 -0800
Subject: [PATCH 05/11] clean up args

---
 .../celery/tasks/shared/RetryDocumentIndex.py |  3 ++-
 backend/onyx/document_index/interfaces.py     |  8 +++++---
 backend/onyx/document_index/vespa/index.py    | 11 +++++++++--
 .../scripts/force_delete_connector_by_id.py   | 19 ++++++++++++-------
 backend/scripts/orphan_doc_cleanup_script.py  | 17 ++++++++++++-----
 5 files changed, 40 insertions(+), 18 deletions(-)

diff --git a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
index cf3afefeb95..34a3e0a8864 100644
--- a/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
+++ b/backend/onyx/background/celery/tasks/shared/RetryDocumentIndex.py
@@ -31,6 +31,7 @@ def __init__(self, index: DocumentIndex):
     def delete_single(
         self,
         doc_id: str,
+        *,
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
@@ -48,11 +49,11 @@ def delete_single(
     def update_single(
         self,
         doc_id: str,
+        *,
         tenant_id: str | None,
         chunk_count: int | None,
         fields: VespaDocumentFields,
     ) -> int:
-        print("Update single")
         return self.index.update_single(
             doc_id,
             tenant_id=tenant_id,
diff --git a/backend/onyx/document_index/interfaces.py b/backend/onyx/document_index/interfaces.py
index 85bfb7ae3d6..08dbfdc9efb 100644
--- a/backend/onyx/document_index/interfaces.py
+++ b/backend/onyx/document_index/interfaces.py
@@ -136,7 +136,7 @@ def __init__(
         index_name: str,
         secondary_index_name: str | None,
         *args: Any,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> None:
         super().__init__(*args, **kwargs)
         self.index_name = index_name
@@ -221,6 +221,7 @@ class Deletable(abc.ABC):
     def delete_single(
         self,
         doc_id: str,
+        *,
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
@@ -247,8 +248,9 @@ class Updatable(abc.ABC):
     def update_single(
         self,
         doc_id: str,
-        chunk_count: int | None,
+        *,
         tenant_id: str | None,
+        chunk_count: int | None,
         fields: VespaDocumentFields,
     ) -> int:
         """
@@ -269,7 +271,7 @@ def update_single(
 
     @abc.abstractmethod
     def update(
-        self, update_requests: list[UpdateRequest], tenant_id: str | None
+        self, update_requests: list[UpdateRequest], *, tenant_id: str | None
     ) -> None:
         """
         Updates some set of chunks. The document and fields to update are specified in the update
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 4dc42a9671c..78cfea85656 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -433,7 +433,7 @@ def _update_chunk(
                         raise requests.HTTPError(failure_msg) from e
 
     def update(
-        self, update_requests: list[UpdateRequest], tenant_id: str | None
+        self, update_requests: list[UpdateRequest], *, tenant_id: str | None
     ) -> None:
         logger.debug(f"Updating {len(update_requests)} documents in Vespa")
 
@@ -561,6 +561,7 @@ def update_single_chunk(
     def update_single(
         self,
         doc_id: str,
+        *,
         chunk_count: int | None,
         tenant_id: str | None,
         fields: VespaDocumentFields,
@@ -610,6 +611,7 @@ def update_single(
     def delete_single(
         self,
         doc_id: str,
+        *,
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
@@ -795,7 +797,12 @@ def enrich_basic_chunk_info(
         return enriched_doc_info
 
     @classmethod
-    def delete_entries_by_tenant_id(cls, tenant_id: str, index_name: str) -> None:
+    def delete_entries_by_tenant_id(
+        cls,
+        *,
+        tenant_id: str,
+        index_name: str,
+    ) -> None:
         """
         Deletes all entries in the specified index with the given tenant_id.
 
diff --git a/backend/scripts/force_delete_connector_by_id.py b/backend/scripts/force_delete_connector_by_id.py
index 3f0bf01ad61..39b98b9bcb8 100755
--- a/backend/scripts/force_delete_connector_by_id.py
+++ b/backend/scripts/force_delete_connector_by_id.py
@@ -5,6 +5,7 @@
 from sqlalchemy import delete
 from sqlalchemy.orm import Session
 
+from onyx.db.document import delete_documents_complete__no_commit
 from onyx.db.enums import ConnectorCredentialPairStatus
 
 # Modify sys.path
@@ -70,14 +71,17 @@ def _unsafe_deletion(
         if not documents:
             break
 
-        # document_ids = [document.id for document in documents]
-        # for doc_id in document_ids:
-        #     document_index.delete_single(doc_id)
+        for document in documents:
+            document_index.delete_single(
+                doc_id=document.id,
+                tenant_id=None,
+                chunk_count=document.chunk_count,
+            )
 
-        # delete_documents_complete__no_commit(
-        #     db_session=db_session,
-        #     document_ids=document_ids,
-        # )
+        delete_documents_complete__no_commit(
+            db_session=db_session,
+            document_ids=[document.id for document in documents],
+        )
 
         num_docs_deleted += len(documents)
 
@@ -215,6 +219,7 @@ def _delete_connector(cc_pair_id: int, db_session: Session) -> None:
     parser.add_argument(
         "connector_id", type=int, help="The ID of the connector to delete"
     )
+
     args = parser.parse_args()
     with get_session_context_manager() as db_session:
         _delete_connector(args.connector_id, db_session)
diff --git a/backend/scripts/orphan_doc_cleanup_script.py b/backend/scripts/orphan_doc_cleanup_script.py
index 6d404f7f52e..baf52d93b05 100644
--- a/backend/scripts/orphan_doc_cleanup_script.py
+++ b/backend/scripts/orphan_doc_cleanup_script.py
@@ -15,6 +15,7 @@
 from onyx.db.document import delete_documents_complete__no_commit  # noqa: E402
 from onyx.db.search_settings import get_current_search_settings  # noqa: E402
 from onyx.document_index.vespa.index import VespaIndex  # noqa: E402
+from onyx.db.document import get_document  # noqa: E402
 
 BATCH_SIZE = 100
 
@@ -63,6 +64,10 @@ def main() -> None:
             with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
 
                 def process_doc(doc_id: str) -> str | None:
+                    document = get_document(doc_id, db_session)
+                    if not document:
+                        print(f"Document {doc_id} not found in Postgres")
+                        return None
                     # Check if document exists in Vespa first
                     try:
                         chunks = vespa_index.id_based_retrieval(
@@ -83,11 +88,13 @@ def process_doc(doc_id: str) -> str | None:
 
                     try:
                         print(f"Deleting document {doc_id} in Vespa")
-                        # chunks_deleted = vespa_index.delete_single(doc_id)
-                        # if chunks_deleted > 0:
-                        #     print(
-                        #         f"Deleted {chunks_deleted} chunks for document {doc_id}"
-                        #     )
+                        chunks_deleted = vespa_index.delete_single(
+                            doc_id, tenant_id=None, chunk_count=document.chunk_count
+                        )
+                        if chunks_deleted > 0:
+                            print(
+                                f"Deleted {chunks_deleted} chunks for document {doc_id}"
+                            )
                         return doc_id
                     except Exception as e:
                         print(

From e7173378f62854d909b07b8997999127ce07ca9f Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 16:32:12 -0800
Subject: [PATCH 06/11] update for clarity + best practices

---
 .../background/celery/tasks/shared/tasks.py   |  2 --
 .../document_index/document_index_utils.py    |  5 ++-
 backend/onyx/document_index/vespa/index.py    | 32 +++++++++----------
 .../document_index/vespa/indexing_utils.py    |  2 +-
 backend/onyx/indexing/indexing_pipeline.py    |  6 ++--
 5 files changed, 22 insertions(+), 25 deletions(-)

diff --git a/backend/onyx/background/celery/tasks/shared/tasks.py b/backend/onyx/background/celery/tasks/shared/tasks.py
index a7050b57498..16434a6b5f5 100644
--- a/backend/onyx/background/celery/tasks/shared/tasks.py
+++ b/backend/onyx/background/celery/tasks/shared/tasks.py
@@ -80,7 +80,6 @@ def document_by_cc_pair_cleanup_task(
                 # delete it from vespa and the db
                 action = "delete"
 
-                # TODO: fix the large chunks enabled
                 chunks_affected = retry_index.delete_single(
                     document_id,
                     tenant_id=tenant_id,
@@ -115,7 +114,6 @@ def document_by_cc_pair_cleanup_task(
                 )
 
                 # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
-                # TODO: fix the large chunks enabled
                 chunks_affected = retry_index.update_single(
                     document_id,
                     tenant_id=tenant_id,
diff --git a/backend/onyx/document_index/document_index_utils.py b/backend/onyx/document_index/document_index_utils.py
index 8976b556eb2..4770a8a2843 100644
--- a/backend/onyx/document_index/document_index_utils.py
+++ b/backend/onyx/document_index/document_index_utils.py
@@ -37,7 +37,10 @@ def translate_boost_count_to_multiplier(boost: int) -> float:
     return 2 / (1 + math.exp(-1 * boost / 3))
 
 
-def assemble_document_chunk_info(
+# Assembles a list of Vespa chunk IDs for a document
+# given the required context. This can be used to directly query
+# Vespa's Document API.
+def get_document_chunk_ids(
     enriched_document_info_list: list[EnrichedDocumentIndexingInfo],
     tenant_id: str | None,
     large_chunks_enabled: bool,
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 78cfea85656..d8d4b41e4a4 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -26,7 +26,7 @@
 from onyx.context.search.models import IndexFilters
 from onyx.context.search.models import InferenceChunkUncleaned
 from onyx.db.engine import get_session_with_tenant
-from onyx.document_index.document_index_utils import assemble_document_chunk_info
+from onyx.document_index.document_index_utils import get_document_chunk_ids
 from onyx.document_index.interfaces import DocumentIndex
 from onyx.document_index.interfaces import DocumentInsertionRecord
 from onyx.document_index.interfaces import EnrichedDocumentIndexingInfo
@@ -42,11 +42,11 @@
 from onyx.document_index.vespa.chunk_retrieval import query_vespa
 from onyx.document_index.vespa.deletion import delete_vespa_chunks
 from onyx.document_index.vespa.indexing_utils import batch_index_vespa_chunks
-from onyx.document_index.vespa.indexing_utils import (
-    check_enable_large_chunks_and_multipass,
-)
 from onyx.document_index.vespa.indexing_utils import check_for_final_chunk_existence
 from onyx.document_index.vespa.indexing_utils import clean_chunk_id_copy
+from onyx.document_index.vespa.indexing_utils import (
+    get_multipass_config,
+)
 from onyx.document_index.vespa.shared_utils.utils import get_vespa_http_client
 from onyx.document_index.vespa.shared_utils.utils import (
     replace_invalid_doc_id_characters,
@@ -355,7 +355,7 @@ def index(
 
             # Now, for each doc, we know exactly where to start and end our deletion
             # So let's generate the chunk IDs for each chunk to delete
-            chunks_to_delete = assemble_document_chunk_info(
+            chunks_to_delete = get_document_chunk_ids(
                 enriched_document_info_list=enriched_doc_infos,
                 tenant_id=tenant_id,
                 large_chunks_enabled=large_chunks_enabled,
@@ -458,14 +458,14 @@ def update(
             for update_request in update_requests:
                 for doc_info in update_request.minimal_document_indexing_info:
                     for index_name in index_names:
-                        doc_chunk_info = self.enrich_basic_chunk_info(
+                        doc_chunk_info = VespaIndex.enrich_basic_chunk_info(
                             index_name=index_name,
                             http_client=http_client,
                             document_id=doc_info.doc_id,
                             previous_chunk_count=doc_info.chunk_start_index,
                             new_chunk_count=0,
                         )
-                        doc_chunk_ids = assemble_document_chunk_info(
+                        doc_chunk_ids = get_document_chunk_ids(
                             enriched_document_info_list=[doc_chunk_info],
                             tenant_id=tenant_id,
                             large_chunks_enabled=False,
@@ -578,9 +578,8 @@ def update_single(
 
         with get_vespa_http_client(http2=False) as http_client:
             for index_name in index_names:
-                large_chunks_enabled = False
                 with get_session_with_tenant(tenant_id=tenant_id) as db_session:
-                    multipass_config = check_enable_large_chunks_and_multipass(
+                    multipass_config = get_multipass_config(
                         db_session=db_session,
                         primary_index=index_name == self.index_name,
                     )
@@ -593,7 +592,7 @@ def update_single(
                     previous_chunk_count=chunk_count,
                     new_chunk_count=0,
                 )
-                doc_chunk_ids = assemble_document_chunk_info(
+                doc_chunk_ids = get_document_chunk_ids(
                     enriched_document_info_list=[enriched_doc_infos],
                     tenant_id=tenant_id,
                     large_chunks_enabled=large_chunks_enabled,
@@ -601,7 +600,6 @@ def update_single(
                 doc_chunk_count += len(doc_chunk_ids)
 
                 for doc_chunk_id in doc_chunk_ids:
-                    print("THIS ONE is being updated")
                     self.update_single_chunk(
                         doc_chunk_id=doc_chunk_id, index_name=index_name, fields=fields
                     )
@@ -615,9 +613,6 @@ def delete_single(
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
-        """Possibly faster overall than the delete method due to using a single
-        delete call with a selection query."""
-
         total_chunks_deleted = 0
 
         doc_id = replace_invalid_doc_id_characters(doc_id)
@@ -634,9 +629,8 @@ def delete_single(
             max_workers=NUM_THREADS
         ) as executor:
             for index_name in index_names:
-                large_chunks_enabled = False
                 with get_session_with_tenant(tenant_id=tenant_id) as db_session:
-                    multipass_config = check_enable_large_chunks_and_multipass(
+                    multipass_config = get_multipass_config(
                         db_session=db_session,
                         primary_index=index_name == self.index_name,
                     )
@@ -649,7 +643,7 @@ def delete_single(
                     previous_chunk_count=chunk_count,
                     new_chunk_count=0,
                 )
-                chunks_to_delete = assemble_document_chunk_info(
+                chunks_to_delete = get_document_chunk_ids(
                     enriched_document_info_list=[enriched_doc_infos],
                     tenant_id=tenant_id,
                     large_chunks_enabled=large_chunks_enabled,
@@ -762,6 +756,10 @@ def admin_retrieval(
 
         return query_vespa(params)
 
+    # Retrieves chunk information for a document:
+    # - Determines the last indexed chunk
+    # - Identifies if the document uses the old or new chunk ID system
+    # This data is crucial for Vespa document updates without relying on the visit API.
     @classmethod
     def enrich_basic_chunk_info(
         cls,
diff --git a/backend/onyx/document_index/vespa/indexing_utils.py b/backend/onyx/document_index/vespa/indexing_utils.py
index a8d35e996db..857162382ef 100644
--- a/backend/onyx/document_index/vespa/indexing_utils.py
+++ b/backend/onyx/document_index/vespa/indexing_utils.py
@@ -297,7 +297,7 @@ def can_use_large_chunks(multipass: bool, search_settings: SearchSettings) -> bo
     )
 
 
-def check_enable_large_chunks_and_multipass(
+def get_multipass_config(
     db_session: Session, primary_index: bool = True
 ) -> MultipassConfig:
     """
diff --git a/backend/onyx/indexing/indexing_pipeline.py b/backend/onyx/indexing/indexing_pipeline.py
index 1502ac6b3d3..74c6c08fd8a 100644
--- a/backend/onyx/indexing/indexing_pipeline.py
+++ b/backend/onyx/indexing/indexing_pipeline.py
@@ -36,7 +36,7 @@
 from onyx.document_index.interfaces import DocumentMetadata
 from onyx.document_index.interfaces import IndexBatchParams
 from onyx.document_index.vespa.indexing_utils import (
-    check_enable_large_chunks_and_multipass,
+    get_multipass_config,
 )
 from onyx.indexing.chunker import Chunker
 from onyx.indexing.embedder import IndexingEmbedder
@@ -491,9 +491,7 @@ def build_indexing_pipeline(
     callback: IndexingHeartbeatInterface | None = None,
 ) -> IndexingPipelineProtocol:
     """Builds a pipeline which takes in a list (batch) of docs and indexes them."""
-    multipass_config = check_enable_large_chunks_and_multipass(
-        db_session, primary_index=True
-    )
+    multipass_config = get_multipass_config(db_session, primary_index=True)
 
     chunker = chunker or Chunker(
         tokenizer=embedder.embedding_model.tokenizer,

From 7b20e11300c1173d041bfd776cec93c63dd19a3c Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Tue, 7 Jan 2025 21:07:21 -0800
Subject: [PATCH 07/11] nit + logs

---
 .../background/celery/tasks/shared/tasks.py   |   5 +-
 .../background/celery/tasks/vespa/tasks.py    |   4 +
 backend/onyx/db/document.py                   |   8 +
 backend/onyx/document_index/vespa/index.py    |  94 +++++-
 backend/tests/__init__.py                     |   0
 backend/tests/integration/__init__.py         |   0
 .../common_utils/managers/document.py         |  11 +-
 .../connector/test_connector_deletion.py      | 318 +++++++++---------
 8 files changed, 265 insertions(+), 175 deletions(-)
 create mode 100644 backend/tests/__init__.py
 create mode 100644 backend/tests/integration/__init__.py

diff --git a/backend/onyx/background/celery/tasks/shared/tasks.py b/backend/onyx/background/celery/tasks/shared/tasks.py
index 16434a6b5f5..b078c282b58 100644
--- a/backend/onyx/background/celery/tasks/shared/tasks.py
+++ b/backend/onyx/background/celery/tasks/shared/tasks.py
@@ -12,6 +12,7 @@
 from onyx.configs.constants import OnyxCeleryTask
 from onyx.db.document import delete_document_by_connector_credential_pair__no_commit
 from onyx.db.document import delete_documents_complete__no_commit
+from onyx.db.document import fetch_chunk_count_for_document
 from onyx.db.document import get_document
 from onyx.db.document import get_document_connector_count
 from onyx.db.document import mark_document_as_modified
@@ -80,10 +81,12 @@ def document_by_cc_pair_cleanup_task(
                 # delete it from vespa and the db
                 action = "delete"
 
+                chunk_count = fetch_chunk_count_for_document(document_id, db_session)
+
                 chunks_affected = retry_index.delete_single(
                     document_id,
                     tenant_id=tenant_id,
-                    chunk_count=None,
+                    chunk_count=chunk_count,
                 )
                 delete_documents_complete__no_commit(
                     db_session=db_session,
diff --git a/backend/onyx/background/celery/tasks/vespa/tasks.py b/backend/onyx/background/celery/tasks/vespa/tasks.py
index 8eabeb7d8a8..f3c7b67818e 100644
--- a/backend/onyx/background/celery/tasks/vespa/tasks.py
+++ b/backend/onyx/background/celery/tasks/vespa/tasks.py
@@ -990,6 +990,10 @@ def vespa_metadata_sync_task(
                 boost=doc.boost,
                 hidden=doc.hidden,
             )
+            logger.info("\n\n\n\n\n\n\n\nuPDATING DOCUMENT")
+            logger.info(document_id)
+            logger.info(fields)
+            logger.info(doc_access)
 
             # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
             chunks_affected = retry_index.update_single(
diff --git a/backend/onyx/db/document.py b/backend/onyx/db/document.py
index 7f11b64d824..b12c852f493 100644
--- a/backend/onyx/db/document.py
+++ b/backend/onyx/db/document.py
@@ -702,3 +702,11 @@ def fetch_chunk_counts_for_documents(
     # otherwise cast to str if you need to be sure it's a string:
     return [(str(row[0]), row[1]) for row in results]
     # or row.id, row.chunk_count if they are named attributes in your ORM model
+
+
+def fetch_chunk_count_for_document(
+    document_id: str,
+    db_session: Session,
+) -> int | None:
+    stmt = select(DbDocument.chunk_count).where(DbDocument.id == document_id)
+    return db_session.execute(stmt).scalar_one_or_none()
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index d8d4b41e4a4..8d02ee0f04b 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -517,47 +517,100 @@ def update(
         )
 
     def update_single_chunk(
-        self, doc_chunk_id: UUID, index_name: str, fields: VespaDocumentFields
+        self,
+        doc_chunk_id: UUID,  # The chunk ID, presumably your docid in Vespa
+        index_name: str,  # The Vespa doc type name (must match schema)
+        fields: VespaDocumentFields,  # Your container of fields to update
+        doc_id: str,  # Possibly used for logging
     ) -> None:
-        """Update a single chunk in Vespa using its chunk ID."""
+        """
+        Update a single "chunk" (document) in Vespa using its chunk ID.
+        Requires that 'index_name' matches the document type in your Vespa schema.
+        """
 
-        # Build the update request
+        # 1) Build the partial-update JSON
         update_dict: dict[str, dict] = {"fields": {}}
+
         if fields.boost is not None:
             update_dict["fields"][BOOST] = {"assign": fields.boost}
+
         if fields.document_sets is not None:
+            # WeightedSet<string> needs a map { item: weight, ... }
             update_dict["fields"][DOCUMENT_SETS] = {
                 "assign": {document_set: 1 for document_set in fields.document_sets}
             }
+
         if fields.access is not None:
+            # Another WeightedSet<string>
             update_dict["fields"][ACCESS_CONTROL_LIST] = {
                 "assign": {acl_entry: 1 for acl_entry in fields.access.to_acl()}
             }
+
         if fields.hidden is not None:
             update_dict["fields"][HIDDEN] = {"assign": fields.hidden}
 
         if not update_dict["fields"]:
-            logger.error("Update request received but nothing to update")
+            logger.error("Update request received but nothing to update.")
             return
 
+        # 2) Construct the correct doc URL
+        #    Make sure DOCUMENT_ID_ENDPOINT includes something like:
+        #      http://<host>:<port>/document/v1/{namespace}/{doc_type}/docid
+        #    Also note the "?create=true" so that partial updates upsert.
+        vespa_url = f"{DOCUMENT_ID_ENDPOINT.format(index_name=index_name)}/{doc_chunk_id}?create=true"
+
+        logger.info("Vespa partial-update payload: %s", update_dict)
+        logger.info('Attempting PUT to URL: "%s"', vespa_url)
+
         with get_vespa_http_client(http2=False) as http_client:
-            vespa_url = (
-                f"{DOCUMENT_ID_ENDPOINT.format(index_name=index_name)}/{doc_chunk_id}"
-            )
+            # --- (Optional) Check the doc before updating ---
+            try:
+                before_resp = http_client.get(vespa_url)
+                before_resp.raise_for_status()
+                before_doc_json = before_resp.json()
+                # You might not want to log large fields like embeddings, etc.
+                # If so, pop them out before logging:
+                before_doc_json.pop("embeddings", None)
+                before_doc_json.pop("title_embedding", None)
+                logger.info("Document before update [%s]: %s", doc_id, before_doc_json)
+            except httpx.HTTPError:
+                logger.warning(
+                    "Document %s did not exist prior to update (this might be normal if it's new).",
+                    doc_chunk_id,
+                )
 
+            # --- Perform the partial update ---
             try:
-                logger.debug(f'update_single PUT on URL "{vespa_url}"')
                 resp = http_client.put(
                     vespa_url,
                     headers={"Content-Type": "application/json"},
                     json=update_dict,
                 )
                 resp.raise_for_status()
-
             except httpx.HTTPStatusError as e:
-                logger.error(f"Failed to update chunk, details: {e.response.text}")
+                logger.error(
+                    "Failed to update doc chunk %s (doc_id=%s). Details: %s",
+                    doc_chunk_id,
+                    doc_id,
+                    e.response.text,
+                )
                 raise
 
+            # --- (Optional) Check the doc after updating ---
+            try:
+                after_resp = http_client.get(vespa_url)
+                after_resp.raise_for_status()
+                after_doc_json = after_resp.json()
+                after_doc_json.pop("embeddings", None)
+                after_doc_json.pop("title_embedding", None)
+                logger.info("Document after update [%s]: %s", doc_id, after_doc_json)
+            except httpx.HTTPError as e:
+                logger.warning(
+                    "Failed fetching document after update for %s: %s",
+                    doc_chunk_id,
+                    str(e),
+                )
+
     def update_single(
         self,
         doc_id: str,
@@ -570,6 +623,9 @@ def update_single(
         function will complete with no errors or exceptions.
         Handle other exceptions if you wish to implement retry behavior
         """
+        logger.info(f"RIGHT NOW UPDATING document {doc_id} with fields {fields}")
+        logger.info(fields.__dict__)
+
         doc_chunk_count = 0
 
         index_names = [self.index_name]
@@ -592,17 +648,28 @@ def update_single(
                     previous_chunk_count=chunk_count,
                     new_chunk_count=0,
                 )
+                logger.info("ENRICHED DOC INFO")
+                logger.info(enriched_doc_infos)
+
                 doc_chunk_ids = get_document_chunk_ids(
                     enriched_document_info_list=[enriched_doc_infos],
                     tenant_id=tenant_id,
                     large_chunks_enabled=large_chunks_enabled,
                 )
+
+                logger.info("UPDATING len(doc_chunk_ids)")
+
                 doc_chunk_count += len(doc_chunk_ids)
 
                 for doc_chunk_id in doc_chunk_ids:
+                    logger.info("UPDATING CHUNK")
                     self.update_single_chunk(
-                        doc_chunk_id=doc_chunk_id, index_name=index_name, fields=fields
+                        doc_chunk_id=doc_chunk_id,
+                        index_name=index_name,
+                        fields=fields,
+                        doc_id=doc_id,
                     )
+        logger.info(f"UPDATED A TOTAL OF {doc_chunk_count} CHUNKS for {doc_id}")
 
         return doc_chunk_count
 
@@ -613,6 +680,7 @@ def delete_single(
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
+        print("\n\n\n\n\n\n\n\nDELETE")
         total_chunks_deleted = 0
 
         doc_id = replace_invalid_doc_id_characters(doc_id)
@@ -643,6 +711,9 @@ def delete_single(
                     previous_chunk_count=chunk_count,
                     new_chunk_count=0,
                 )
+                print("the enriched doc info", enriched_doc_infos)
+                # for   doc_info in enriched_doc_infos:
+                #     print(doc_info.__dict__)
                 chunks_to_delete = get_document_chunk_ids(
                     enriched_document_info_list=[enriched_doc_infos],
                     tenant_id=tenant_id,
@@ -651,6 +722,7 @@ def delete_single(
                 for doc_chunk_ids_batch in batch_generator(
                     chunks_to_delete, BATCH_SIZE
                 ):
+                    print("DELETING CHUNK")
                     total_chunks_deleted += len(doc_chunk_ids_batch)
                     delete_vespa_chunks(
                         doc_chunk_ids=doc_chunk_ids_batch,
diff --git a/backend/tests/__init__.py b/backend/tests/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/backend/tests/integration/__init__.py b/backend/tests/integration/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/backend/tests/integration/common_utils/managers/document.py b/backend/tests/integration/common_utils/managers/document.py
index 939a420f014..58465be0149 100644
--- a/backend/tests/integration/common_utils/managers/document.py
+++ b/backend/tests/integration/common_utils/managers/document.py
@@ -21,8 +21,10 @@ def _verify_document_permissions(
     group_names: list[str] | None = None,
     doc_creating_user: DATestUser | None = None,
 ) -> None:
-    acl_keys = set(retrieved_doc["access_control_list"].keys())
+    acl_keys = set(retrieved_doc.get("access_control_list", {}).keys())
     print(f"ACL keys: {acl_keys}")
+    print(f"Full retrieved document: {retrieved_doc}")
+
     if cc_pair.access_type == AccessType.PUBLIC:
         if "PUBLIC" not in acl_keys:
             raise ValueError(
@@ -39,11 +41,14 @@ def _verify_document_permissions(
 
     if group_names is not None:
         expected_group_keys = {f"group:{group_name}" for group_name in group_names}
+        print(f"Expected group keys: {expected_group_keys}")
         found_group_keys = {key for key in acl_keys if key.startswith("group:")}
+        print(f"Found group keys: {found_group_keys}")
         if found_group_keys != expected_group_keys:
             raise ValueError(
-                f"Document {retrieved_doc['document_id']} has incorrect group ACL keys. Found: {found_group_keys}, \n"
-                f"Expected: {expected_group_keys}"
+                f"Document {retrieved_doc['document_id']} has incorrect group ACL keys. "
+                f"Expected: {expected_group_keys}  Found: {found_group_keys}\n"
+                f"All ACL keys: {acl_keys}"
             )
 
     if doc_set_names is not None:
diff --git a/backend/tests/integration/tests/connector/test_connector_deletion.py b/backend/tests/integration/tests/connector/test_connector_deletion.py
index 8878a502e2a..d2af7a31f56 100644
--- a/backend/tests/integration/tests/connector/test_connector_deletion.py
+++ b/backend/tests/integration/tests/connector/test_connector_deletion.py
@@ -5,8 +5,6 @@
     - updates the document sets and user groups to remove the connector
 - Ensure that deleting a connector that is part of an overlapping document set and/or user group works as expected
 """
-from uuid import uuid4
-
 from sqlalchemy.orm import Session
 
 from onyx.db.engine import get_sqlalchemy_engine
@@ -192,161 +190,161 @@ def test_connector_deletion(reset: None, vespa_client: vespa_fixture) -> None:
     )
 
 
-def test_connector_deletion_for_overlapping_connectors(
-    reset: None, vespa_client: vespa_fixture
-) -> None:
-    """Checks to make sure that connectors with overlapping documents work properly. Specifically, that the overlapping
-    document (1) still exists and (2) has the right document set / group post-deletion of one of the connectors.
-    """
-    # Creating an admin user (first user created is automatically an admin)
-    admin_user: DATestUser = UserManager.create(name="admin_user")
-    # create api key
-    api_key: DATestAPIKey = APIKeyManager.create(
-        user_performing_action=admin_user,
-    )
-
-    # create connectors
-    cc_pair_1 = CCPairManager.create_from_scratch(
-        source=DocumentSource.INGESTION_API,
-        user_performing_action=admin_user,
-    )
-    cc_pair_2 = CCPairManager.create_from_scratch(
-        source=DocumentSource.INGESTION_API,
-        user_performing_action=admin_user,
-    )
-
-    doc_ids = [str(uuid4())]
-    cc_pair_1.documents = DocumentManager.seed_dummy_docs(
-        cc_pair=cc_pair_1,
-        document_ids=doc_ids,
-        api_key=api_key,
-    )
-    cc_pair_2.documents = DocumentManager.seed_dummy_docs(
-        cc_pair=cc_pair_2,
-        document_ids=doc_ids,
-        api_key=api_key,
-    )
-
-    # verify vespa document exists and that it is not in any document sets or groups
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_1,
-        doc_set_names=[],
-        group_names=[],
-        doc_creating_user=admin_user,
-    )
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_2,
-        doc_set_names=[],
-        group_names=[],
-        doc_creating_user=admin_user,
-    )
-
-    # create document set
-    doc_set_1 = DocumentSetManager.create(
-        name="Test Document Set 1",
-        cc_pair_ids=[cc_pair_1.id],
-        user_performing_action=admin_user,
-    )
-    DocumentSetManager.wait_for_sync(
-        document_sets_to_check=[doc_set_1],
-        user_performing_action=admin_user,
-    )
-
-    print("Document set 1 created and synced")
-
-    # verify vespa document is in the document set
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_1,
-        doc_set_names=[doc_set_1.name],
-        doc_creating_user=admin_user,
-    )
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_2,
-        doc_creating_user=admin_user,
-    )
-
-    # create a user group and attach it to connector 1
-    user_group_1: DATestUserGroup = UserGroupManager.create(
-        name="Test User Group 1",
-        cc_pair_ids=[cc_pair_1.id],
-        user_performing_action=admin_user,
-    )
-    UserGroupManager.wait_for_sync(
-        user_groups_to_check=[user_group_1],
-        user_performing_action=admin_user,
-    )
-    cc_pair_1.groups = [user_group_1.id]
-
-    print("User group 1 created and synced")
-
-    # create a user group and attach it to connector 2
-    user_group_2: DATestUserGroup = UserGroupManager.create(
-        name="Test User Group 2",
-        cc_pair_ids=[cc_pair_2.id],
-        user_performing_action=admin_user,
-    )
-    UserGroupManager.wait_for_sync(
-        user_groups_to_check=[user_group_2],
-        user_performing_action=admin_user,
-    )
-    cc_pair_2.groups = [user_group_2.id]
-
-    print("User group 2 created and synced")
-
-    # verify vespa document is in the user group
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_1,
-        group_names=[user_group_1.name, user_group_2.name],
-        doc_creating_user=admin_user,
-    )
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_2,
-        group_names=[user_group_1.name, user_group_2.name],
-        doc_creating_user=admin_user,
-    )
-
-    # delete connector 1
-    CCPairManager.pause_cc_pair(
-        cc_pair=cc_pair_1,
-        user_performing_action=admin_user,
-    )
-    CCPairManager.delete(
-        cc_pair=cc_pair_1,
-        user_performing_action=admin_user,
-    )
-
-    # wait for deletion to finish
-    CCPairManager.wait_for_deletion_completion(
-        cc_pair_id=cc_pair_1.id, user_performing_action=admin_user
-    )
-
-    print("Connector 1 deleted")
-
-    # check that only connector 1 is deleted
-    # TODO: check for the CC pair rather than the connector once the refactor is done
-    CCPairManager.verify(
-        cc_pair=cc_pair_1,
-        verify_deleted=True,
-        user_performing_action=admin_user,
-    )
-    CCPairManager.verify(
-        cc_pair=cc_pair_2,
-        user_performing_action=admin_user,
-    )
-
-    # verify the document is not in any document sets
-    # verify the document is only in user group 2
-    DocumentManager.verify(
-        vespa_client=vespa_client,
-        cc_pair=cc_pair_2,
-        doc_set_names=[],
-        group_names=[user_group_2.name],
-        doc_creating_user=admin_user,
-        verify_deleted=False,
-    )
+# def test_connector_deletion_for_overlapping_connectors(
+#     reset: None, vespa_client: vespa_fixture
+# ) -> None:
+#     """Checks to make sure that connectors with overlapping documents work properly. Specifically, that the overlapping
+#     document (1) still exists and (2) has the right document set / group post-deletion of one of the connectors.
+#     """
+#     # Creating an admin user (first user created is automatically an admin)
+#     admin_user: DATestUser = UserManager.create(name="admin_user")
+#     # create api key
+#     api_key: DATestAPIKey = APIKeyManager.create(
+#         user_performing_action=admin_user,
+#     )
+
+#     # create connectors
+#     cc_pair_1 = CCPairManager.create_from_scratch(
+#         source=DocumentSource.INGESTION_API,
+#         user_performing_action=admin_user,
+#     )
+#     cc_pair_2 = CCPairManager.create_from_scratch(
+#         source=DocumentSource.INGESTION_API,
+#         user_performing_action=admin_user,
+#     )
+
+#     doc_ids = [str(uuid4())]
+#     cc_pair_1.documents = DocumentManager.seed_dummy_docs(
+#         cc_pair=cc_pair_1,
+#         document_ids=doc_ids,
+#         api_key=api_key,
+#     )
+#     cc_pair_2.documents = DocumentManager.seed_dummy_docs(
+#         cc_pair=cc_pair_2,
+#         document_ids=doc_ids,
+#         api_key=api_key,
+#     )
+
+#     # verify vespa document exists and that it is not in any document sets or groups
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_1,
+#         doc_set_names=[],
+#         group_names=[],
+#         doc_creating_user=admin_user,
+#     )
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_2,
+#         doc_set_names=[],
+#         group_names=[],
+#         doc_creating_user=admin_user,
+#     )
+
+#     # create document set
+#     doc_set_1 = DocumentSetManager.create(
+#         name="Test Document Set 1",
+#         cc_pair_ids=[cc_pair_1.id],
+#         user_performing_action=admin_user,
+#     )
+#     DocumentSetManager.wait_for_sync(
+#         document_sets_to_check=[doc_set_1],
+#         user_performing_action=admin_user,
+#     )
+
+#     print("Document set 1 created and synced")
+
+#     # verify vespa document is in the document set
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_1,
+#         doc_set_names=[doc_set_1.name],
+#         doc_creating_user=admin_user,
+#     )
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_2,
+#         doc_creating_user=admin_user,
+#     )
+
+#     # create a user group and attach it to connector 1
+#     user_group_1: DATestUserGroup = UserGroupManager.create(
+#         name="Test User Group 1",
+#         cc_pair_ids=[cc_pair_1.id],
+#         user_performing_action=admin_user,
+#     )
+#     UserGroupManager.wait_for_sync(
+#         user_groups_to_check=[user_group_1],
+#         user_performing_action=admin_user,
+#     )
+#     cc_pair_1.groups = [user_group_1.id]
+
+#     print("User group 1 created and synced")
+
+#     # create a user group and attach it to connector 2
+#     user_group_2: DATestUserGroup = UserGroupManager.create(
+#         name="Test User Group 2",
+#         cc_pair_ids=[cc_pair_2.id],
+#         user_performing_action=admin_user,
+#     )
+#     UserGroupManager.wait_for_sync(
+#         user_groups_to_check=[user_group_2],
+#         user_performing_action=admin_user,
+#     )
+#     cc_pair_2.groups = [user_group_2.id]
+
+#     print("User group 2 created and synced")
+
+#     # verify vespa document is in the user group
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_1,
+#         group_names=[user_group_1.name, user_group_2.name],
+#         doc_creating_user=admin_user,
+#     )
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_2,
+#         group_names=[user_group_1.name, user_group_2.name],
+#         doc_creating_user=admin_user,
+#     )
+
+#     # delete connector 1
+#     CCPairManager.pause_cc_pair(
+#         cc_pair=cc_pair_1,
+#         user_performing_action=admin_user,
+#     )
+#     CCPairManager.delete(
+#         cc_pair=cc_pair_1,
+#         user_performing_action=admin_user,
+#     )
+
+#     # wait for deletion to finish
+#     CCPairManager.wait_for_deletion_completion(
+#         cc_pair_id=cc_pair_1.id, user_performing_action=admin_user
+#     )
+
+#     print("Connector 1 deleted")
+
+#     # check that only connector 1 is deleted
+#     # TODO: check for the CC pair rather than the connector once the refactor is done
+#     CCPairManager.verify(
+#         cc_pair=cc_pair_1,
+#         verify_deleted=True,
+#         user_performing_action=admin_user,
+#     )
+#     CCPairManager.verify(
+#         cc_pair=cc_pair_2,
+#         user_performing_action=admin_user,
+#     )
+
+#     # verify the document is not in any document sets
+#     # verify the document is only in user group 2
+#     DocumentManager.verify(
+#         vespa_client=vespa_client,
+#         cc_pair=cc_pair_2,
+#         doc_set_names=[],
+#         group_names=[user_group_2.name],
+#         doc_creating_user=admin_user,
+#         verify_deleted=False,
+#     )

From 231d03a4d6ff0d099404ea89732e94191eca9106 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Wed, 8 Jan 2025 12:25:19 -0800
Subject: [PATCH 08/11] fix

---
 backend/onyx/db/document.py                   | 15 +++--
 .../document_index/document_index_utils.py    |  7 ++-
 backend/onyx/document_index/vespa/index.py    | 63 +++----------------
 .../document_index/vespa/indexing_utils.py    |  2 +
 .../common_utils/managers/document.py         |  7 +++
 5 files changed, 28 insertions(+), 66 deletions(-)

diff --git a/backend/onyx/db/document.py b/backend/onyx/db/document.py
index b12c852f493..d9ff82d797a 100644
--- a/backend/onyx/db/document.py
+++ b/backend/onyx/db/document.py
@@ -685,23 +685,22 @@ def get_document_sources(
 def fetch_chunk_counts_for_documents(
     document_ids: list[str],
     db_session: Session,
-) -> list[tuple[str, int | None]]:
+) -> list[tuple[str, int]]:
     """
     Return a list of (document_id, chunk_count) tuples.
-    Note: chunk_count might be None if not set in DB,
-    so we declare it as Optional[int].
+    If a document_id is not found in the database, it will be returned with a chunk_count of 0.
     """
     stmt = select(DbDocument.id, DbDocument.chunk_count).where(
         DbDocument.id.in_(document_ids)
     )
 
-    # results is a list of 'Row' objects, each containing two columns
     results = db_session.execute(stmt).all()
 
-    # If DbDocument.id is guaranteed to be a string, you can just do row.id;
-    # otherwise cast to str if you need to be sure it's a string:
-    return [(str(row[0]), row[1]) for row in results]
-    # or row.id, row.chunk_count if they are named attributes in your ORM model
+    # Create a dictionary of document_id to chunk_count
+    chunk_counts = {str(row.id): row.chunk_count or 0 for row in results}
+
+    # Return a list of tuples, using 0 for documents not found in the database
+    return [(doc_id, chunk_counts.get(doc_id, 0)) for doc_id in document_ids]
 
 
 def fetch_chunk_count_for_document(
diff --git a/backend/onyx/document_index/document_index_utils.py b/backend/onyx/document_index/document_index_utils.py
index 4770a8a2843..831ffb6d403 100644
--- a/backend/onyx/document_index/document_index_utils.py
+++ b/backend/onyx/document_index/document_index_utils.py
@@ -8,7 +8,7 @@
 from onyx.db.search_settings import get_secondary_search_settings
 from onyx.document_index.interfaces import EnrichedDocumentIndexingInfo
 from onyx.indexing.models import DocMetadataAwareIndexChunk
-
+from shared_configs.configs import MULTI_TENANT
 
 DEFAULT_BATCH_SIZE = 30
 DEFAULT_INDEX_NAME = "danswer_chunk"
@@ -113,10 +113,11 @@ def get_uuid_from_chunk_info(
         "large_" + str(large_chunk_id) if large_chunk_id is not None else str(chunk_id)
     )
     unique_identifier_string = "_".join([doc_str, chunk_index])
-    if tenant_id:
+    if tenant_id and MULTI_TENANT:
         unique_identifier_string += "_" + tenant_id
 
-    return uuid.uuid5(uuid.NAMESPACE_X500, unique_identifier_string)
+    uuid_value = uuid.uuid5(uuid.NAMESPACE_X500, unique_identifier_string)
+    return uuid_value
 
 
 def get_uuid_from_chunk_info_old(
diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index 8d02ee0f04b..b69fa853d0c 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -337,12 +337,13 @@ def index(
             # know precisely which chunks to delete. This information exists for
             # documents that have `chunk_count` in the database, but not for
             # `old_version` documents.
+
             enriched_doc_infos: list[EnrichedDocumentIndexingInfo] = [
                 VespaIndex.enrich_basic_chunk_info(
                     index_name=self.index_name,
                     http_client=http_client,
                     document_id=doc_id,
-                    previous_chunk_count=doc_id_to_previous_chunk_cnt.get(doc_id),
+                    previous_chunk_count=doc_id_to_previous_chunk_cnt.get(doc_id, 0),
                     new_chunk_count=doc_id_to_new_chunk_cnt.get(doc_id, 0),
                 )
                 for doc_id in doc_id_to_new_chunk_cnt.keys()
@@ -518,10 +519,10 @@ def update(
 
     def update_single_chunk(
         self,
-        doc_chunk_id: UUID,  # The chunk ID, presumably your docid in Vespa
-        index_name: str,  # The Vespa doc type name (must match schema)
-        fields: VespaDocumentFields,  # Your container of fields to update
-        doc_id: str,  # Possibly used for logging
+        doc_chunk_id: UUID,
+        index_name: str,
+        fields: VespaDocumentFields,
+        doc_id: str,
     ) -> None:
         """
         Update a single "chunk" (document) in Vespa using its chunk ID.
@@ -559,27 +560,7 @@ def update_single_chunk(
         #    Also note the "?create=true" so that partial updates upsert.
         vespa_url = f"{DOCUMENT_ID_ENDPOINT.format(index_name=index_name)}/{doc_chunk_id}?create=true"
 
-        logger.info("Vespa partial-update payload: %s", update_dict)
-        logger.info('Attempting PUT to URL: "%s"', vespa_url)
-
         with get_vespa_http_client(http2=False) as http_client:
-            # --- (Optional) Check the doc before updating ---
-            try:
-                before_resp = http_client.get(vespa_url)
-                before_resp.raise_for_status()
-                before_doc_json = before_resp.json()
-                # You might not want to log large fields like embeddings, etc.
-                # If so, pop them out before logging:
-                before_doc_json.pop("embeddings", None)
-                before_doc_json.pop("title_embedding", None)
-                logger.info("Document before update [%s]: %s", doc_id, before_doc_json)
-            except httpx.HTTPError:
-                logger.warning(
-                    "Document %s did not exist prior to update (this might be normal if it's new).",
-                    doc_chunk_id,
-                )
-
-            # --- Perform the partial update ---
             try:
                 resp = http_client.put(
                     vespa_url,
@@ -588,29 +569,10 @@ def update_single_chunk(
                 )
                 resp.raise_for_status()
             except httpx.HTTPStatusError as e:
-                logger.error(
-                    "Failed to update doc chunk %s (doc_id=%s). Details: %s",
-                    doc_chunk_id,
-                    doc_id,
-                    e.response.text,
-                )
+                error_message = f"Failed to update doc chunk {doc_chunk_id} (doc_id={doc_id}). Details: {e.response.text}"
+                logger.error(error_message)
                 raise
 
-            # --- (Optional) Check the doc after updating ---
-            try:
-                after_resp = http_client.get(vespa_url)
-                after_resp.raise_for_status()
-                after_doc_json = after_resp.json()
-                after_doc_json.pop("embeddings", None)
-                after_doc_json.pop("title_embedding", None)
-                logger.info("Document after update [%s]: %s", doc_id, after_doc_json)
-            except httpx.HTTPError as e:
-                logger.warning(
-                    "Failed fetching document after update for %s: %s",
-                    doc_chunk_id,
-                    str(e),
-                )
-
     def update_single(
         self,
         doc_id: str,
@@ -623,8 +585,6 @@ def update_single(
         function will complete with no errors or exceptions.
         Handle other exceptions if you wish to implement retry behavior
         """
-        logger.info(f"RIGHT NOW UPDATING document {doc_id} with fields {fields}")
-        logger.info(fields.__dict__)
 
         doc_chunk_count = 0
 
@@ -640,7 +600,6 @@ def update_single(
                         primary_index=index_name == self.index_name,
                     )
                     large_chunks_enabled = multipass_config.enable_large_chunks
-
                 enriched_doc_infos = VespaIndex.enrich_basic_chunk_info(
                     index_name=index_name,
                     http_client=http_client,
@@ -648,8 +607,6 @@ def update_single(
                     previous_chunk_count=chunk_count,
                     new_chunk_count=0,
                 )
-                logger.info("ENRICHED DOC INFO")
-                logger.info(enriched_doc_infos)
 
                 doc_chunk_ids = get_document_chunk_ids(
                     enriched_document_info_list=[enriched_doc_infos],
@@ -711,9 +668,6 @@ def delete_single(
                     previous_chunk_count=chunk_count,
                     new_chunk_count=0,
                 )
-                print("the enriched doc info", enriched_doc_infos)
-                # for   doc_info in enriched_doc_infos:
-                #     print(doc_info.__dict__)
                 chunks_to_delete = get_document_chunk_ids(
                     enriched_document_info_list=[enriched_doc_infos],
                     tenant_id=tenant_id,
@@ -722,7 +676,6 @@ def delete_single(
                 for doc_chunk_ids_batch in batch_generator(
                     chunks_to_delete, BATCH_SIZE
                 ):
-                    print("DELETING CHUNK")
                     total_chunks_deleted += len(doc_chunk_ids_batch)
                     delete_vespa_chunks(
                         doc_chunk_ids=doc_chunk_ids_batch,
diff --git a/backend/onyx/document_index/vespa/indexing_utils.py b/backend/onyx/document_index/vespa/indexing_utils.py
index 857162382ef..ed802ada9ac 100644
--- a/backend/onyx/document_index/vespa/indexing_utils.py
+++ b/backend/onyx/document_index/vespa/indexing_utils.py
@@ -136,7 +136,9 @@ def _index_vespa_chunk(
     document = chunk.source_document
 
     # No minichunk documents in vespa, minichunk vectors are stored in the chunk itself
+
     vespa_chunk_id = str(get_uuid_from_chunk(chunk))
+
     embeddings = chunk.embeddings
 
     embeddings_name_vector_map = {"full_chunk": embeddings.full_embedding}
diff --git a/backend/tests/integration/common_utils/managers/document.py b/backend/tests/integration/common_utils/managers/document.py
index 58465be0149..1e6d5b6acd5 100644
--- a/backend/tests/integration/common_utils/managers/document.py
+++ b/backend/tests/integration/common_utils/managers/document.py
@@ -158,9 +158,16 @@ def verify(
     ) -> None:
         doc_ids = [document.id for document in cc_pair.documents]
         retrieved_docs_dict = vespa_client.get_documents_by_id(doc_ids)["documents"]
+        print(f"from the doc ids {doc_ids}")
+
+        print("--------------------------------")
+        for doc in retrieved_docs_dict:
+            print(f"document iD: {doc['fields']['document_id']} and {doc['id']}")
+
         retrieved_docs = {
             doc["fields"]["document_id"]: doc["fields"] for doc in retrieved_docs_dict
         }
+
         # Left this here for debugging purposes.
         # import json
         # for doc in retrieved_docs.values():

From 8ef4857e8a081889d501e8e75553a3263a62a722 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Wed, 8 Jan 2025 12:31:16 -0800
Subject: [PATCH 09/11] minor clean up

---
 .../background/celery/tasks/vespa/tasks.py    |   4 -
 backend/scripts/orphan_doc_cleanup_script.py  |   1 -
 backend/testing.txt                           | 140 ++++++++
 .../common_utils/managers/document.py         |   6 -
 .../connector/test_connector_deletion.py      | 318 +++++++++---------
 backend/vespa_update_logs.txt                 | 120 +++++++
 6 files changed, 420 insertions(+), 169 deletions(-)
 create mode 100644 backend/testing.txt
 create mode 100644 backend/vespa_update_logs.txt

diff --git a/backend/onyx/background/celery/tasks/vespa/tasks.py b/backend/onyx/background/celery/tasks/vespa/tasks.py
index f3c7b67818e..8eabeb7d8a8 100644
--- a/backend/onyx/background/celery/tasks/vespa/tasks.py
+++ b/backend/onyx/background/celery/tasks/vespa/tasks.py
@@ -990,10 +990,6 @@ def vespa_metadata_sync_task(
                 boost=doc.boost,
                 hidden=doc.hidden,
             )
-            logger.info("\n\n\n\n\n\n\n\nuPDATING DOCUMENT")
-            logger.info(document_id)
-            logger.info(fields)
-            logger.info(doc_access)
 
             # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
             chunks_affected = retry_index.update_single(
diff --git a/backend/scripts/orphan_doc_cleanup_script.py b/backend/scripts/orphan_doc_cleanup_script.py
index baf52d93b05..c138bdc64a6 100644
--- a/backend/scripts/orphan_doc_cleanup_script.py
+++ b/backend/scripts/orphan_doc_cleanup_script.py
@@ -66,7 +66,6 @@ def main() -> None:
                 def process_doc(doc_id: str) -> str | None:
                     document = get_document(doc_id, db_session)
                     if not document:
-                        print(f"Document {doc_id} not found in Postgres")
                         return None
                     # Check if document exists in Vespa first
                     try:
diff --git a/backend/testing.txt b/backend/testing.txt
new file mode 100644
index 00000000000..49406e070e9
--- /dev/null
+++ b/backend/testing.txt
@@ -0,0 +1,140 @@
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] doc_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] doc_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] doc_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] doc_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] doc_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] doc_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] doc_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
+[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
+[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
+[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
+[2025-01-08 12:25:51] doc_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
+[2025-01-08 12:25:51] doc_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] doc_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
+[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
+[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
+[2025-01-08 12:25:51] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
+[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
+[2025-01-08 12:25:51] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
+[2025-01-08 12:25:51] doc_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
+[2025-01-08 12:25:51] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] doc_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
+[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
+[2025-01-08 12:25:51] doc_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] doc_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] doc_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
+[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
+[2025-01-08 12:25:51] OLD? UPDATE SINGLE
+[2025-01-08 12:25:51] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
+[2025-01-08 12:25:51] doc_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
+[2025-01-08 12:25:51] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
+[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
+[2025-01-08 12:25:51] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
+[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
+[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
+[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
+[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
+[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] called in update_single
+[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
+[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
+[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] OLD? UPDATE SINGLE
+[2025-01-08 12:25:52] doc_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:52] OLD? UPDATE SINGLE
+[2025-01-08 12:25:52] OLD? UPDATE SINGLE
+[2025-01-08 12:25:52] doc_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:52] doc_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:52] OLD? UPDATE SINGLE
+[2025-01-08 12:25:52] doc_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
+[2025-01-08 12:25:52] called in update_single
+[2025-01-08 12:25:52] called in update_single
+[2025-01-08 12:25:52] called in update_single
+[2025-01-08 12:25:52] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
+[2025-01-08 12:25:52] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
+[2025-01-08 12:25:52] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
+[2025-01-08 12:25:52] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
+[2025-01-08 12:25:52] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
+[2025-01-08 12:25:52] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
+[2025-01-08 12:25:52] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] called in update_single
+[2025-01-08 12:25:52] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
+[2025-01-08 12:25:52] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
+[2025-01-08 12:25:52] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
+[2025-01-08 12:25:52] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
diff --git a/backend/tests/integration/common_utils/managers/document.py b/backend/tests/integration/common_utils/managers/document.py
index 1e6d5b6acd5..d1514126cc3 100644
--- a/backend/tests/integration/common_utils/managers/document.py
+++ b/backend/tests/integration/common_utils/managers/document.py
@@ -23,7 +23,6 @@ def _verify_document_permissions(
 ) -> None:
     acl_keys = set(retrieved_doc.get("access_control_list", {}).keys())
     print(f"ACL keys: {acl_keys}")
-    print(f"Full retrieved document: {retrieved_doc}")
 
     if cc_pair.access_type == AccessType.PUBLIC:
         if "PUBLIC" not in acl_keys:
@@ -158,11 +157,6 @@ def verify(
     ) -> None:
         doc_ids = [document.id for document in cc_pair.documents]
         retrieved_docs_dict = vespa_client.get_documents_by_id(doc_ids)["documents"]
-        print(f"from the doc ids {doc_ids}")
-
-        print("--------------------------------")
-        for doc in retrieved_docs_dict:
-            print(f"document iD: {doc['fields']['document_id']} and {doc['id']}")
 
         retrieved_docs = {
             doc["fields"]["document_id"]: doc["fields"] for doc in retrieved_docs_dict
diff --git a/backend/tests/integration/tests/connector/test_connector_deletion.py b/backend/tests/integration/tests/connector/test_connector_deletion.py
index d2af7a31f56..8878a502e2a 100644
--- a/backend/tests/integration/tests/connector/test_connector_deletion.py
+++ b/backend/tests/integration/tests/connector/test_connector_deletion.py
@@ -5,6 +5,8 @@
     - updates the document sets and user groups to remove the connector
 - Ensure that deleting a connector that is part of an overlapping document set and/or user group works as expected
 """
+from uuid import uuid4
+
 from sqlalchemy.orm import Session
 
 from onyx.db.engine import get_sqlalchemy_engine
@@ -190,161 +192,161 @@ def test_connector_deletion(reset: None, vespa_client: vespa_fixture) -> None:
     )
 
 
-# def test_connector_deletion_for_overlapping_connectors(
-#     reset: None, vespa_client: vespa_fixture
-# ) -> None:
-#     """Checks to make sure that connectors with overlapping documents work properly. Specifically, that the overlapping
-#     document (1) still exists and (2) has the right document set / group post-deletion of one of the connectors.
-#     """
-#     # Creating an admin user (first user created is automatically an admin)
-#     admin_user: DATestUser = UserManager.create(name="admin_user")
-#     # create api key
-#     api_key: DATestAPIKey = APIKeyManager.create(
-#         user_performing_action=admin_user,
-#     )
-
-#     # create connectors
-#     cc_pair_1 = CCPairManager.create_from_scratch(
-#         source=DocumentSource.INGESTION_API,
-#         user_performing_action=admin_user,
-#     )
-#     cc_pair_2 = CCPairManager.create_from_scratch(
-#         source=DocumentSource.INGESTION_API,
-#         user_performing_action=admin_user,
-#     )
-
-#     doc_ids = [str(uuid4())]
-#     cc_pair_1.documents = DocumentManager.seed_dummy_docs(
-#         cc_pair=cc_pair_1,
-#         document_ids=doc_ids,
-#         api_key=api_key,
-#     )
-#     cc_pair_2.documents = DocumentManager.seed_dummy_docs(
-#         cc_pair=cc_pair_2,
-#         document_ids=doc_ids,
-#         api_key=api_key,
-#     )
-
-#     # verify vespa document exists and that it is not in any document sets or groups
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_1,
-#         doc_set_names=[],
-#         group_names=[],
-#         doc_creating_user=admin_user,
-#     )
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_2,
-#         doc_set_names=[],
-#         group_names=[],
-#         doc_creating_user=admin_user,
-#     )
-
-#     # create document set
-#     doc_set_1 = DocumentSetManager.create(
-#         name="Test Document Set 1",
-#         cc_pair_ids=[cc_pair_1.id],
-#         user_performing_action=admin_user,
-#     )
-#     DocumentSetManager.wait_for_sync(
-#         document_sets_to_check=[doc_set_1],
-#         user_performing_action=admin_user,
-#     )
-
-#     print("Document set 1 created and synced")
-
-#     # verify vespa document is in the document set
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_1,
-#         doc_set_names=[doc_set_1.name],
-#         doc_creating_user=admin_user,
-#     )
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_2,
-#         doc_creating_user=admin_user,
-#     )
-
-#     # create a user group and attach it to connector 1
-#     user_group_1: DATestUserGroup = UserGroupManager.create(
-#         name="Test User Group 1",
-#         cc_pair_ids=[cc_pair_1.id],
-#         user_performing_action=admin_user,
-#     )
-#     UserGroupManager.wait_for_sync(
-#         user_groups_to_check=[user_group_1],
-#         user_performing_action=admin_user,
-#     )
-#     cc_pair_1.groups = [user_group_1.id]
-
-#     print("User group 1 created and synced")
-
-#     # create a user group and attach it to connector 2
-#     user_group_2: DATestUserGroup = UserGroupManager.create(
-#         name="Test User Group 2",
-#         cc_pair_ids=[cc_pair_2.id],
-#         user_performing_action=admin_user,
-#     )
-#     UserGroupManager.wait_for_sync(
-#         user_groups_to_check=[user_group_2],
-#         user_performing_action=admin_user,
-#     )
-#     cc_pair_2.groups = [user_group_2.id]
-
-#     print("User group 2 created and synced")
-
-#     # verify vespa document is in the user group
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_1,
-#         group_names=[user_group_1.name, user_group_2.name],
-#         doc_creating_user=admin_user,
-#     )
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_2,
-#         group_names=[user_group_1.name, user_group_2.name],
-#         doc_creating_user=admin_user,
-#     )
-
-#     # delete connector 1
-#     CCPairManager.pause_cc_pair(
-#         cc_pair=cc_pair_1,
-#         user_performing_action=admin_user,
-#     )
-#     CCPairManager.delete(
-#         cc_pair=cc_pair_1,
-#         user_performing_action=admin_user,
-#     )
-
-#     # wait for deletion to finish
-#     CCPairManager.wait_for_deletion_completion(
-#         cc_pair_id=cc_pair_1.id, user_performing_action=admin_user
-#     )
-
-#     print("Connector 1 deleted")
-
-#     # check that only connector 1 is deleted
-#     # TODO: check for the CC pair rather than the connector once the refactor is done
-#     CCPairManager.verify(
-#         cc_pair=cc_pair_1,
-#         verify_deleted=True,
-#         user_performing_action=admin_user,
-#     )
-#     CCPairManager.verify(
-#         cc_pair=cc_pair_2,
-#         user_performing_action=admin_user,
-#     )
-
-#     # verify the document is not in any document sets
-#     # verify the document is only in user group 2
-#     DocumentManager.verify(
-#         vespa_client=vespa_client,
-#         cc_pair=cc_pair_2,
-#         doc_set_names=[],
-#         group_names=[user_group_2.name],
-#         doc_creating_user=admin_user,
-#         verify_deleted=False,
-#     )
+def test_connector_deletion_for_overlapping_connectors(
+    reset: None, vespa_client: vespa_fixture
+) -> None:
+    """Checks to make sure that connectors with overlapping documents work properly. Specifically, that the overlapping
+    document (1) still exists and (2) has the right document set / group post-deletion of one of the connectors.
+    """
+    # Creating an admin user (first user created is automatically an admin)
+    admin_user: DATestUser = UserManager.create(name="admin_user")
+    # create api key
+    api_key: DATestAPIKey = APIKeyManager.create(
+        user_performing_action=admin_user,
+    )
+
+    # create connectors
+    cc_pair_1 = CCPairManager.create_from_scratch(
+        source=DocumentSource.INGESTION_API,
+        user_performing_action=admin_user,
+    )
+    cc_pair_2 = CCPairManager.create_from_scratch(
+        source=DocumentSource.INGESTION_API,
+        user_performing_action=admin_user,
+    )
+
+    doc_ids = [str(uuid4())]
+    cc_pair_1.documents = DocumentManager.seed_dummy_docs(
+        cc_pair=cc_pair_1,
+        document_ids=doc_ids,
+        api_key=api_key,
+    )
+    cc_pair_2.documents = DocumentManager.seed_dummy_docs(
+        cc_pair=cc_pair_2,
+        document_ids=doc_ids,
+        api_key=api_key,
+    )
+
+    # verify vespa document exists and that it is not in any document sets or groups
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_1,
+        doc_set_names=[],
+        group_names=[],
+        doc_creating_user=admin_user,
+    )
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_2,
+        doc_set_names=[],
+        group_names=[],
+        doc_creating_user=admin_user,
+    )
+
+    # create document set
+    doc_set_1 = DocumentSetManager.create(
+        name="Test Document Set 1",
+        cc_pair_ids=[cc_pair_1.id],
+        user_performing_action=admin_user,
+    )
+    DocumentSetManager.wait_for_sync(
+        document_sets_to_check=[doc_set_1],
+        user_performing_action=admin_user,
+    )
+
+    print("Document set 1 created and synced")
+
+    # verify vespa document is in the document set
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_1,
+        doc_set_names=[doc_set_1.name],
+        doc_creating_user=admin_user,
+    )
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_2,
+        doc_creating_user=admin_user,
+    )
+
+    # create a user group and attach it to connector 1
+    user_group_1: DATestUserGroup = UserGroupManager.create(
+        name="Test User Group 1",
+        cc_pair_ids=[cc_pair_1.id],
+        user_performing_action=admin_user,
+    )
+    UserGroupManager.wait_for_sync(
+        user_groups_to_check=[user_group_1],
+        user_performing_action=admin_user,
+    )
+    cc_pair_1.groups = [user_group_1.id]
+
+    print("User group 1 created and synced")
+
+    # create a user group and attach it to connector 2
+    user_group_2: DATestUserGroup = UserGroupManager.create(
+        name="Test User Group 2",
+        cc_pair_ids=[cc_pair_2.id],
+        user_performing_action=admin_user,
+    )
+    UserGroupManager.wait_for_sync(
+        user_groups_to_check=[user_group_2],
+        user_performing_action=admin_user,
+    )
+    cc_pair_2.groups = [user_group_2.id]
+
+    print("User group 2 created and synced")
+
+    # verify vespa document is in the user group
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_1,
+        group_names=[user_group_1.name, user_group_2.name],
+        doc_creating_user=admin_user,
+    )
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_2,
+        group_names=[user_group_1.name, user_group_2.name],
+        doc_creating_user=admin_user,
+    )
+
+    # delete connector 1
+    CCPairManager.pause_cc_pair(
+        cc_pair=cc_pair_1,
+        user_performing_action=admin_user,
+    )
+    CCPairManager.delete(
+        cc_pair=cc_pair_1,
+        user_performing_action=admin_user,
+    )
+
+    # wait for deletion to finish
+    CCPairManager.wait_for_deletion_completion(
+        cc_pair_id=cc_pair_1.id, user_performing_action=admin_user
+    )
+
+    print("Connector 1 deleted")
+
+    # check that only connector 1 is deleted
+    # TODO: check for the CC pair rather than the connector once the refactor is done
+    CCPairManager.verify(
+        cc_pair=cc_pair_1,
+        verify_deleted=True,
+        user_performing_action=admin_user,
+    )
+    CCPairManager.verify(
+        cc_pair=cc_pair_2,
+        user_performing_action=admin_user,
+    )
+
+    # verify the document is not in any document sets
+    # verify the document is only in user group 2
+    DocumentManager.verify(
+        vespa_client=vespa_client,
+        cc_pair=cc_pair_2,
+        doc_set_names=[],
+        group_names=[user_group_2.name],
+        doc_creating_user=admin_user,
+        verify_deleted=False,
+    )
diff --git a/backend/vespa_update_logs.txt b/backend/vespa_update_logs.txt
new file mode 100644
index 00000000000..b4afa57c6e7
--- /dev/null
+++ b/backend/vespa_update_logs.txt
@@ -0,0 +1,120 @@
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-9666258c-a25a-4290-9050-951dd054f0b3', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac Chunk ID: c4e99738-6467-5a14-a151-d2d68173d286
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 Chunk ID: b518bd97-dda4-5241-8dcf-60164e0a6baa
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-49b93c6c-0625-474e-a29b-10533384c461', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 Chunk ID: ea672bb3-2d07-51c5-a39a-5f5bd7219fab
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa?create=true"
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286?create=true"
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-3340635d-6077-4feb-8553-0618c0a249c7', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 Chunk ID: d88662bf-f859-58cc-84b6-f04257838115
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-c0cda300-a641-449e-b53f-8572735899dc', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab?create=true"
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Document c4e99738-6467-5a14-a151-d2d68173d286 did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Document b518bd97-dda4-5241-8dcf-60164e0a6baa did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 Chunk ID: 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115?create=true"
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 Chunk ID: b15838ad-4607-5815-9079-6c37a6688836
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 Chunk ID: 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
+[2025-01-08 12:25:51] Document ea672bb3-2d07-51c5-a39a-5f5bd7219fab did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc Chunk ID: 91971d6a-e954-5c17-a3f4-88b9e7090adf
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836?create=true"
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf?create=true"
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e?create=true"
+[2025-01-08 12:25:51] Document d88662bf-f859-58cc-84b6-f04257838115 did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 Chunk ID: 1175290a-e73b-59ae-a00b-155603488490
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc?create=true"
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-3340635d-6077-4feb-8553-0618c0a249c7', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490?create=true"
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-49b93c6c-0625-474e-a29b-10533384c461', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Document 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Document b15838ad-4607-5815-9079-6c37a6688836 did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 Chunk ID: 9188e172-07ff-547f-8ecc-f8ce25c181b0
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac Chunk ID: c4e99738-6467-5a14-a151-d2d68173d286
+[2025-01-08 12:25:51] Document 91971d6a-e954-5c17-a3f4-88b9e7090adf did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 Chunk ID: 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 Chunk ID: ea672bb3-2d07-51c5-a39a-5f5bd7219fab
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc?create=true"
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0?create=true"
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286?create=true"
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab?create=true"
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 Chunk ID: d88662bf-f859-58cc-84b6-f04257838115
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 Chunk ID: 1175290a-e73b-59ae-a00b-155603488490
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] Document 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490?create=true"
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115?create=true"
+[2025-01-08 12:25:51] Document 1175290a-e73b-59ae-a00b-155603488490 did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-9666258c-a25a-4290-9050-951dd054f0b3', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:51] Document 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Document 9188e172-07ff-547f-8ecc-f8ce25c181b0 did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] CREATED Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 Chunk ID: b518bd97-dda4-5241-8dcf-60164e0a6baa
+[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa?create=true"
+[2025-01-08 12:25:51] Document 1175290a-e73b-59ae-a00b-155603488490 did not exist prior to update (this might be normal if it's new).
+[2025-01-08 12:25:51] Document before update [test-doc-9666258c-a25a-4290-9050-951dd054f0b3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b518bd97-dda4-5241-8dcf-60164e0a6baa', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document before update [test-doc-49b93c6c-0625-474e-a29b-10533384c461]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::d88662bf-f859-58cc-84b6-f04257838115', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document before update [test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document before update [test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::c4e99738-6467-5a14-a151-d2d68173d286', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-c0cda300-a641-449e-b53f-8572735899dc]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::91971d6a-e954-5c17-a3f4-88b9e7090adf', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-49b93c6c-0625-474e-a29b-10533384c461]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::d88662bf-f859-58cc-84b6-f04257838115', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::9188e172-07ff-547f-8ecc-f8ce25c181b0', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-9666258c-a25a-4290-9050-951dd054f0b3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b518bd97-dda4-5241-8dcf-60164e0a6baa', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b15838ad-4607-5815-9079-6c37a6688836', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::c4e99738-6467-5a14-a151-d2d68173d286', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::1175290a-e73b-59ae-a00b-155603488490', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:51] Document after update [test-doc-3340635d-6077-4feb-8553-0618c0a249c7]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::1175290a-e73b-59ae-a00b-155603488490', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-3340635d-6077-4feb-8553-0618c0a249c7]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::c4e99738-6467-5a14-a151-d2d68173d286', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-49b93c6c-0625-474e-a29b-10533384c461]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::d88662bf-f859-58cc-84b6-f04257838115', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-9666258c-a25a-4290-9050-951dd054f0b3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b518bd97-dda4-5241-8dcf-60164e0a6baa', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-c0cda300-a641-449e-b53f-8572735899dc', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:52] CREATED Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 Chunk ID: 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
+[2025-01-08 12:25:52] CREATED Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc Chunk ID: 91971d6a-e954-5c17-a3f4-88b9e7090adf
+[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:52] CREATED Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 Chunk ID: b15838ad-4607-5815-9079-6c37a6688836
+[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf?create=true"
+[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e?create=true"
+[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836?create=true"
+[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43', chunk_start_index=0, old_version=False, chunk_end_index=1)
+[2025-01-08 12:25:52] CREATED Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 Chunk ID: 9188e172-07ff-547f-8ecc-f8ce25c181b0
+[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
+[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0?create=true"
+[2025-01-08 12:25:52] Document before update [test-doc-c0cda300-a641-449e-b53f-8572735899dc]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::91971d6a-e954-5c17-a3f4-88b9e7090adf', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document before update [test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document before update [test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b15838ad-4607-5815-9079-6c37a6688836', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document before update [test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::9188e172-07ff-547f-8ecc-f8ce25c181b0', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b15838ad-4607-5815-9079-6c37a6688836', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::9188e172-07ff-547f-8ecc-f8ce25c181b0', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
+[2025-01-08 12:25:52] Document after update [test-doc-c0cda300-a641-449e-b53f-8572735899dc]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::91971d6a-e954-5c17-a3f4-88b9e7090adf', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}

From 86d9829c6fe9770c3c58e4d05264e3eef18acb02 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Wed, 8 Jan 2025 12:31:44 -0800
Subject: [PATCH 10/11] remove logs

---
 backend/testing.txt           | 140 ----------------------------------
 backend/vespa_update_logs.txt | 120 -----------------------------
 2 files changed, 260 deletions(-)
 delete mode 100644 backend/testing.txt
 delete mode 100644 backend/vespa_update_logs.txt

diff --git a/backend/testing.txt b/backend/testing.txt
deleted file mode 100644
index 49406e070e9..00000000000
--- a/backend/testing.txt
+++ /dev/null
@@ -1,140 +0,0 @@
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] doc_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] doc_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] doc_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] doc_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] doc_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] doc_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] doc_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
-[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
-[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
-[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
-[2025-01-08 12:25:51] doc_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
-[2025-01-08 12:25:51] doc_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] doc_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
-[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
-[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
-[2025-01-08 12:25:51] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
-[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
-[2025-01-08 12:25:51] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
-[2025-01-08 12:25:51] doc_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
-[2025-01-08 12:25:51] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] doc_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
-[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
-[2025-01-08 12:25:51] doc_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] doc_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] doc_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
-[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
-[2025-01-08 12:25:51] OLD? UPDATE SINGLE
-[2025-01-08 12:25:51] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
-[2025-01-08 12:25:51] doc_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:51] Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac and id is c4e99738-6467-5a14-a151-d2d68173d286
-[2025-01-08 12:25:51] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
-[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
-[2025-01-08 12:25:51] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 and id is ea672bb3-2d07-51c5-a39a-5f5bd7219fab
-[2025-01-08 12:25:51] Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 and id is 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
-[2025-01-08 12:25:51] document_id test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-3340635d-6077-4feb-8553-0618c0a249c7, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
-[2025-01-08 12:25:51] document_id test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 and id is d88662bf-f859-58cc-84b6-f04257838115
-[2025-01-08 12:25:51] Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 and id is 1175290a-e73b-59ae-a00b-155603488490
-[2025-01-08 12:25:51] document_id test-doc-49b93c6c-0625-474e-a29b-10533384c461, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] document_id test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] called in update_single
-[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
-[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:51] Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 and id is b518bd97-dda4-5241-8dcf-60164e0a6baa
-[2025-01-08 12:25:51] document_id test-doc-9666258c-a25a-4290-9050-951dd054f0b3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] OLD? UPDATE SINGLE
-[2025-01-08 12:25:52] doc_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:52] OLD? UPDATE SINGLE
-[2025-01-08 12:25:52] OLD? UPDATE SINGLE
-[2025-01-08 12:25:52] doc_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:52] doc_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:52] OLD? UPDATE SINGLE
-[2025-01-08 12:25:52] doc_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_count 1, tenant_id None, fields VespaDocumentFields(access=DocumentAccess(external_user_emails=set(), external_user_group_ids=set(), is_public=True, user_emails={'admin_user@test.com'}, user_groups={'test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52'}), document_sets=set(), boost=0, hidden=False)
-[2025-01-08 12:25:52] called in update_single
-[2025-01-08 12:25:52] called in update_single
-[2025-01-08 12:25:52] called in update_single
-[2025-01-08 12:25:52] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
-[2025-01-08 12:25:52] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
-[2025-01-08 12:25:52] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
-[2025-01-08 12:25:52] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc and id is 91971d6a-e954-5c17-a3f4-88b9e7090adf
-[2025-01-08 12:25:52] Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 and id is 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
-[2025-01-08 12:25:52] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] document_id test-doc-c0cda300-a641-449e-b53f-8572735899dc, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] document_id test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 and id is b15838ad-4607-5815-9079-6c37a6688836
-[2025-01-08 12:25:52] document_id test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] called in update_single
-[2025-01-08 12:25:52] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
-[2025-01-08 12:25:52] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
-[2025-01-08 12:25:52] Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 and id is 9188e172-07ff-547f-8ecc-f8ce25c181b0
-[2025-01-08 12:25:52] document_id test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43, chunk_id 0, tenant_id public, large_chunk_id None
diff --git a/backend/vespa_update_logs.txt b/backend/vespa_update_logs.txt
deleted file mode 100644
index b4afa57c6e7..00000000000
--- a/backend/vespa_update_logs.txt
+++ /dev/null
@@ -1,120 +0,0 @@
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-9666258c-a25a-4290-9050-951dd054f0b3', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac Chunk ID: c4e99738-6467-5a14-a151-d2d68173d286
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 Chunk ID: b518bd97-dda4-5241-8dcf-60164e0a6baa
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-49b93c6c-0625-474e-a29b-10533384c461', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 Chunk ID: ea672bb3-2d07-51c5-a39a-5f5bd7219fab
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa?create=true"
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286?create=true"
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-3340635d-6077-4feb-8553-0618c0a249c7', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 Chunk ID: d88662bf-f859-58cc-84b6-f04257838115
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-c0cda300-a641-449e-b53f-8572735899dc', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab?create=true"
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Document c4e99738-6467-5a14-a151-d2d68173d286 did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Document b518bd97-dda4-5241-8dcf-60164e0a6baa did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 Chunk ID: 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115?create=true"
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 Chunk ID: b15838ad-4607-5815-9079-6c37a6688836
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 Chunk ID: 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
-[2025-01-08 12:25:51] Document ea672bb3-2d07-51c5-a39a-5f5bd7219fab did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc Chunk ID: 91971d6a-e954-5c17-a3f4-88b9e7090adf
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836?create=true"
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf?create=true"
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e?create=true"
-[2025-01-08 12:25:51] Document d88662bf-f859-58cc-84b6-f04257838115 did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 Chunk ID: 1175290a-e73b-59ae-a00b-155603488490
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc?create=true"
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-3340635d-6077-4feb-8553-0618c0a249c7', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490?create=true"
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-49b93c6c-0625-474e-a29b-10533384c461', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Document 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Document b15838ad-4607-5815-9079-6c37a6688836 did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 Chunk ID: 9188e172-07ff-547f-8ecc-f8ce25c181b0
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac Chunk ID: c4e99738-6467-5a14-a151-d2d68173d286
-[2025-01-08 12:25:51] Document 91971d6a-e954-5c17-a3f4-88b9e7090adf did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-3340635d-6077-4feb-8553-0618c0a249c7 Chunk ID: 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9 Chunk ID: ea672bb3-2d07-51c5-a39a-5f5bd7219fab
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc?create=true"
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0?create=true"
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286?create=true"
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab?create=true"
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-49b93c6c-0625-474e-a29b-10533384c461 Chunk ID: d88662bf-f859-58cc-84b6-f04257838115
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547 Chunk ID: 1175290a-e73b-59ae-a00b-155603488490
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] Document 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490?create=true"
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115?create=true"
-[2025-01-08 12:25:51] Document 1175290a-e73b-59ae-a00b-155603488490 did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] EnrichedDocumentIndexingInfo(doc_id='test-doc-9666258c-a25a-4290-9050-951dd054f0b3', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:51] Document 3d01e4cc-0c5f-57ad-8139-fbc7edce37cc did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Document 9188e172-07ff-547f-8ecc-f8ce25c181b0 did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] CREATED Doc ID: test-doc-9666258c-a25a-4290-9050-951dd054f0b3 Chunk ID: b518bd97-dda4-5241-8dcf-60164e0a6baa
-[2025-01-08 12:25:51] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:51] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa?create=true"
-[2025-01-08 12:25:51] Document 1175290a-e73b-59ae-a00b-155603488490 did not exist prior to update (this might be normal if it's new).
-[2025-01-08 12:25:51] Document before update [test-doc-9666258c-a25a-4290-9050-951dd054f0b3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b518bd97-dda4-5241-8dcf-60164e0a6baa', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document before update [test-doc-49b93c6c-0625-474e-a29b-10533384c461]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::d88662bf-f859-58cc-84b6-f04257838115', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document before update [test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document before update [test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::c4e99738-6467-5a14-a151-d2d68173d286', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-c0cda300-a641-449e-b53f-8572735899dc]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::91971d6a-e954-5c17-a3f4-88b9e7090adf', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-49b93c6c-0625-474e-a29b-10533384c461]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::d88662bf-f859-58cc-84b6-f04257838115', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::9188e172-07ff-547f-8ecc-f8ce25c181b0', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-9666258c-a25a-4290-9050-951dd054f0b3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b518bd97-dda4-5241-8dcf-60164e0a6baa', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b15838ad-4607-5815-9079-6c37a6688836', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::c4e99738-6467-5a14-a151-d2d68173d286', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::1175290a-e73b-59ae-a00b-155603488490', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:51] Document after update [test-doc-3340635d-6077-4feb-8553-0618c0a249c7]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-48b1c08c-2625-4a79-b5a8-57f96648f547]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/1175290a-e73b-59ae-a00b-155603488490', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::1175290a-e73b-59ae-a00b-155603488490', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-3340635d-6077-4feb-8553-0618c0a249c7]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::3d01e4cc-0c5f-57ad-8139-fbc7edce37cc', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-010f8ddf-f065-421e-8b5f-dba2e51409ac]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/c4e99738-6467-5a14-a151-d2d68173d286', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::c4e99738-6467-5a14-a151-d2d68173d286', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-15d0dcd4-afd0-41c0-ac3a-f062d7d54ae9]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::ea672bb3-2d07-51c5-a39a-5f5bd7219fab', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-49b93c6c-0625-474e-a29b-10533384c461]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/d88662bf-f859-58cc-84b6-f04257838115', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::d88662bf-f859-58cc-84b6-f04257838115', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-9666258c-a25a-4290-9050-951dd054f0b3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b518bd97-dda4-5241-8dcf-60164e0a6baa', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b518bd97-dda4-5241-8dcf-60164e0a6baa', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-c0cda300-a641-449e-b53f-8572735899dc', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:52] CREATED Doc ID: test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248 Chunk ID: 619fc1a8-74e3-57fe-95dc-1ac48d9ead3e
-[2025-01-08 12:25:52] CREATED Doc ID: test-doc-c0cda300-a641-449e-b53f-8572735899dc Chunk ID: 91971d6a-e954-5c17-a3f4-88b9e7090adf
-[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:52] CREATED Doc ID: test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3 Chunk ID: b15838ad-4607-5815-9079-6c37a6688836
-[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf?create=true"
-[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e?create=true"
-[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836?create=true"
-[2025-01-08 12:25:52] EnrichedDocumentIndexingInfo(doc_id='test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43', chunk_start_index=0, old_version=False, chunk_end_index=1)
-[2025-01-08 12:25:52] CREATED Doc ID: test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43 Chunk ID: 9188e172-07ff-547f-8ecc-f8ce25c181b0
-[2025-01-08 12:25:52] Vespa partial-update payload: {'fields': {'boost': {'assign': 0}, 'document_sets': {'assign': {}}, 'access_control_list': {'assign': {'PUBLIC': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1, 'user_email:admin_user@test.com': 1}}, 'hidden': {'assign': False}}}
-[2025-01-08 12:25:52] Attempting PUT to URL: "http://localhost:8081/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0?create=true"
-[2025-01-08 12:25:52] Document before update [test-doc-c0cda300-a641-449e-b53f-8572735899dc]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::91971d6a-e954-5c17-a3f4-88b9e7090adf', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document before update [test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document before update [test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b15838ad-4607-5815-9079-6c37a6688836', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document before update [test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::9188e172-07ff-547f-8ecc-f8ce25c181b0', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-99aacccf-d43f-46f8-8fd3-979a4a58f248]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::619fc1a8-74e3-57fe-95dc-1ac48d9ead3e', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-aea1f8b8-f1a7-4071-a9c2-492a372512a3]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/b15838ad-4607-5815-9079-6c37a6688836', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::b15838ad-4607-5815-9079-6c37a6688836', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-e91efe25-09d0-4f1f-8adb-f62ae8bd1f43]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/9188e172-07ff-547f-8ecc-f8ce25c181b0', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::9188e172-07ff-547f-8ecc-f8ce25c181b0', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}
-[2025-01-08 12:25:52] Document after update [test-doc-c0cda300-a641-449e-b53f-8572735899dc]: {'pathId': '/document/v1/default/danswer_chunk_nomic_ai_nomic_embed_text_v1/docid/91971d6a-e954-5c17-a3f4-88b9e7090adf', 'id': 'id:default:danswer_chunk_nomic_ai_nomic_embed_text_v1::91971d6a-e954-5c17-a3f4-88b9e7090adf', 'fields': {'hidden': False, 'boost': 0.0, 'skip_title': False, 'access_control_list': {'PUBLIC': 1, 'user_email:admin_user@test.com': 1, 'group:test-user-group-c0453b8b-0090-4d0f-8672-e08091908c52': 1}, 'section_continuation': False}}

From 85fa3278771e43fdaf9b39aa1fa4783286ac7147 Mon Sep 17 00:00:00 2001
From: pablodanswer <pablo@danswer.ai>
Date: Wed, 8 Jan 2025 12:35:49 -0800
Subject: [PATCH 11/11] quick nit

---
 backend/onyx/document_index/vespa/index.py               | 9 +--------
 .../tests/integration/common_utils/managers/document.py  | 2 --
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/backend/onyx/document_index/vespa/index.py b/backend/onyx/document_index/vespa/index.py
index b69fa853d0c..ce2c580524f 100644
--- a/backend/onyx/document_index/vespa/index.py
+++ b/backend/onyx/document_index/vespa/index.py
@@ -526,10 +526,8 @@ def update_single_chunk(
     ) -> None:
         """
         Update a single "chunk" (document) in Vespa using its chunk ID.
-        Requires that 'index_name' matches the document type in your Vespa schema.
         """
 
-        # 1) Build the partial-update JSON
         update_dict: dict[str, dict] = {"fields": {}}
 
         if fields.boost is not None:
@@ -542,7 +540,7 @@ def update_single_chunk(
             }
 
         if fields.access is not None:
-            # Another WeightedSet<string>
+            # Similar to above
             update_dict["fields"][ACCESS_CONTROL_LIST] = {
                 "assign": {acl_entry: 1 for acl_entry in fields.access.to_acl()}
             }
@@ -554,10 +552,6 @@ def update_single_chunk(
             logger.error("Update request received but nothing to update.")
             return
 
-        # 2) Construct the correct doc URL
-        #    Make sure DOCUMENT_ID_ENDPOINT includes something like:
-        #      http://<host>:<port>/document/v1/{namespace}/{doc_type}/docid
-        #    Also note the "?create=true" so that partial updates upsert.
         vespa_url = f"{DOCUMENT_ID_ENDPOINT.format(index_name=index_name)}/{doc_chunk_id}?create=true"
 
         with get_vespa_http_client(http2=False) as http_client:
@@ -637,7 +631,6 @@ def delete_single(
         tenant_id: str | None,
         chunk_count: int | None,
     ) -> int:
-        print("\n\n\n\n\n\n\n\nDELETE")
         total_chunks_deleted = 0
 
         doc_id = replace_invalid_doc_id_characters(doc_id)
diff --git a/backend/tests/integration/common_utils/managers/document.py b/backend/tests/integration/common_utils/managers/document.py
index d1514126cc3..9ce3430fe62 100644
--- a/backend/tests/integration/common_utils/managers/document.py
+++ b/backend/tests/integration/common_utils/managers/document.py
@@ -40,9 +40,7 @@ def _verify_document_permissions(
 
     if group_names is not None:
         expected_group_keys = {f"group:{group_name}" for group_name in group_names}
-        print(f"Expected group keys: {expected_group_keys}")
         found_group_keys = {key for key in acl_keys if key.startswith("group:")}
-        print(f"Found group keys: {found_group_keys}")
         if found_group_keys != expected_group_keys:
             raise ValueError(
                 f"Document {retrieved_doc['document_id']} has incorrect group ACL keys. "