Merge branch 'infiniflow:main' into main

api/utils/file_utils.py

@@ -146,7 +146,7 @@ def rewrite_yaml_conf(conf_path, config):
 
 
 def rewrite_json_file(filepath, json_data):
-    with open(filepath, "w") as f:
+    with open(filepath, "w", encoding='utf-8') as f:
         json.dump(json_data, f, indent=4, separators=(",", ": "))
     f.close()
 

deepdoc/parser/resume/entities/schools.py

@@ -11,7 +11,10 @@
 #  limitations under the License.
 #
 
-import os, json,re,copy
+import os
+import json
+import re
+import copy
 import pandas as pd
 current_file_path = os.path.dirname(os.path.abspath(__file__))
 TBL = pd.read_csv(os.path.join(current_file_path, "res/schools.csv"), sep="\t", header=0).fillna("")
@@ -23,7 +26,7 @@
 def loadRank(fnm):
     global TBL
     TBL["rank"] = 1000000
-    with open(fnm, "r",encoding='UTF-8') as f:
+    with open(fnm, "r", encoding='utf-8') as f:
         while True:
             l = f.readline()
             if not l:break
@@ -32,7 +35,7 @@ def loadRank(fnm):
                 nm,rk = l[0].strip(),int(l[1])
                 #assert len(TBL[((TBL.name_cn == nm) | (TBL.name_en == nm))]),f"<{nm}>"
                 TBL.loc[((TBL.name_cn == nm) | (TBL.name_en == nm)), "rank"] = rk
-            except Exception as e:
+            except Exception:
                 pass
 
 

deepdoc/vision/t_ocr.py

@@ -41,7 +41,7 @@ def main(args):
             "score": 1} for b, t in bxs if b[0][0] <= b[1][0] and b[0][1] <= b[-1][1]]
         img = draw_box(images[i], bxs, ["ocr"], 1.)
         img.save(outputs[i], quality=95)
-        with open(outputs[i] + ".txt", "w+") as f:
+        with open(outputs[i] + ".txt", "w+", encoding='utf-8') as f:
             f.write("\n".join([o["text"] for o in bxs]))
 
 

deepdoc/vision/t_recognizer.py

@@ -50,7 +50,7 @@ def main(args):
         if args.mode.lower() == "tsr":
             #lyt = [t for t in lyt if t["type"] == "table column"]
             html = get_table_html(images[i], lyt, ocr)
-            with open(outputs[i] + ".html", "w+") as f:
+            with open(outputs[i] + ".html", "w+", encoding='utf-8') as f:
                 f.write(html)
             lyt = [{
                 "type": t["label"],

docker/README.md

@@ -14,7 +14,7 @@
 - **docker-compose.yml**  
   Sets up environment for RAGFlow and its dependencies.
 - **docker-compose-base.yml**  
-  Sets up environment for RAGFlow's dependencies: Elasticsearch, MySQL, MinIO, and Redis.
+  Sets up environment for RAGFlow's dependencies: Elasticsearch/[Infinity](https://github.com/infiniflow/infinity), MySQL, MinIO, and Redis.
 
 ## 🐬 Docker environment variables
 

docs/configurations.md

@@ -32,7 +32,7 @@ docker compose -f docker/docker-compose.yml up -d
 - **docker-compose.yml**  
   Sets up environment for RAGFlow and its dependencies.
 - **docker-compose-base.yml**  
-  Sets up environment for RAGFlow's dependencies: Elasticsearch, MySQL, MinIO, and Redis.
+  Sets up environment for RAGFlow's dependencies: Elasticsearch/[Infinity](https://github.com/infiniflow/infinity), MySQL, MinIO, and Redis.
 
 ## Docker environment variables
 

docs/guides/_category_.json

@@ -1,6 +1,6 @@
 {
   "label": "Guides",
-  "position": 2,
+  "position": 3,
   "link": {
     "type": "generated-index",
     "description": "Guides for RAGFlow users and developers."

docs/references/_category_.json

@@ -1,6 +1,6 @@
 {
   "label": "References",
-  "position": 4,
+  "position": 6,
   "link": {
     "type": "generated-index",
     "description": "Miscellaneous References"

docs/references/http_api_reference.md

@@ -2120,7 +2120,7 @@ Failure:
 
 ---
 
-## Create session with an agent
+## Create session with agent
 
 **POST** `/api/v1/agents/{agent_id}/sessions`
 

docs/release_notes.md

@@ -13,7 +13,7 @@ Released on November 26, 2024.
 
 ### New features
 
-- Supports [Infinity](https://github.com/infiniflow/infinity) or Elasticsearch (default) as document engine for vector storage and full-text indexing.
+- Supports [Infinity](https://github.com/infiniflow/infinity) or Elasticsearch (default) as document engine for vector storage and full-text indexing. [#2894](https://github.com/infiniflow/ragflow/pull/2894)
 - Enhances user experience by adding more variables to the Agent and implementing auto-saving.
 - Adds a three-step translation agent template, inspired by [Andrew Ng's translation agent](https://github.com/andrewyng/translation-agent).
 - Adds an SEO-optimized blog writing agent template.
@@ -22,16 +22,60 @@ Released on November 26, 2024.
 - Optimizes term weight calculations, reducing the retrieval time by 50%.
 - Improves task executor monitoring with additional performance indicators.
 - Replaces Redis with Valkey.
-- Adds three new UI languages (contributed by community): Indonesian, Spanish, and Vietnamese.
+- Adds three new UI languages (*contributed by the community*): Indonesian, Spanish, and Vietnamese.
+
+### Compatability changes
+
+As of this release, **service_config.yaml.template** replaces **service_config.yaml** for configuring backend services. Upon Docker container startup, the environment variables defined in this template file are automatically populated and a **service_config.yaml** is auto-generated from it. [#3341](https://github.com/infiniflow/ragflow/pull/3341)
+
+This approach eliminates the need to manually update **service_config.yaml** after making changes to **.env**, facilitating dynamic environment configurations.
+
+:::danger
+Ensure that you [upgrade both your code and Docker image to this release](https://ragflow.io/docs/dev/upgrade_ragflow#upgrade-ragflow-to-the-most-recent-officially-published-release) before trying this new approach.
+:::
 
 ### Related APIs
 
 #### HTTP APIs
 
-- [Create session with agent](https://ragflow.io/docs/dev/http_api_reference#create-session-with-an-agent)
+- [Create session with agent](https://ragflow.io/docs/dev/http_api_reference#create-session-with-agent)
 - [Converse with agent](https://ragflow.io/docs/dev/http_api_reference#converse-with-agent)
 
 #### Python APIs
 
 - [Create session with agent](https://ragflow.io/docs/dev/python_api_reference#create-session-with-agent)
-- [Converse with agent](https://ragflow.io/docs/dev/python_api_reference#create-session-with-agent)
+- [Converse with agent](https://ragflow.io/docs/dev/python_api_reference#create-session-with-agent)
+
+### Documentation
+
+#### Added documents
+
+- [Configurations](https://ragflow.io/docs/dev/configurations)
+- [Manage team members](https://ragflow.io/docs/dev/manage_team_members)
+- [Run health check on RAGFlow's dependencies](https://ragflow.io/docs/dev/run_health_check)
+
+## v0.13.0
+
+- Adds the team management functionality for all users.
+- Updates the Agent UI to improve usability.
+- Adds support for Markdown chunking in the **General** chunk method.
+- Introduces an **invoke** tool within the Agent UI.
+- Integrates support for Dify's knowledge base API.
+- Adds support for GLM4-9B and Yi-Lightning models.
+- Introduces HTTP and Python APIs for dataset management, file management within dataset, and chat assistant management.
+
+:::tip NOTE
+To download RAGFlow's Python SDK:
+
+```bash
+pip install ragflow-sdk==0.13.0
+```
+:::
+
+### Documentation
+
+#### Added documents
+
+- [Acquire a RAGFlow API key](https://ragflow.io/docs/dev/acquire_ragflow_api_key)
+- [HTTP API Reference](https://ragflow.io/docs/dev/http_api_reference)
+- [Python API Reference](https://ragflow.io/docs/dev/python_api_reference)

graphrag/search.py

@@ -59,8 +59,8 @@ def merge_into_first(sres, title="") -> dict[str, str]:
         q_vec = matchDense.embedding_data
         src = req.get("fields", ["docnm_kwd", "content_ltks", "kb_id", "img_id", "title_tks", "important_kwd",
                                  "doc_id", f"q_{len(q_vec)}_vec", "position_list", "name_kwd",
-                                 "q_1024_vec", "q_1536_vec", "available_int", "content_with_weight",
-                                 "weight_int", "weight_flt", "rank_int"
+                                 "available_int", "content_with_weight",
+                                 "weight_int", "weight_flt"
                                  ])
 
         fusionExpr = FusionExpr("weighted_sum", 32, {"weights": "0.5, 0.5"})