refactor: refactor source.py

docs/how-to/document_search/search_documents.md

@@ -6,6 +6,7 @@
 3. Do the search
 
 This guide will walk you through all those steps and explain the details. Let's start with a minimalistic example to get the main idea:
+
 ```python
 import asyncio
 from pathlib import Path
@@ -16,6 +17,7 @@ from ragbits.document_search import DocumentSearch
 from ragbits.document_search.documents.document import DocumentMeta
 from ragbits.document_search.documents.sources import GCSSource
 
+
 async def main() -> None:
     # Load documents (there are multiple possible sources)
     documents = [
@@ -47,11 +49,13 @@ if __name__ == "__main__":
 Before doing any search we need to have some documents that will build our knowledge base. Ragbits offers a handy class `Document` that stores all the information needed for document loading.
 Objects of this class are usually instantiated using `DocumentMeta` helper class that supports loading files from your local storage, GCS or HuggingFace.
 You can easily add support for your custom sources by extending the `Source` class and implementing the abstract methods:
+
 ```python
 from pathlib import Path
 
 from ragbits.document_search.documents.sources import Source
 
+
 class CustomSource(Source):
     @property
     def id(self) -> str:

examples/document-search/multimodal.py

@@ -49,7 +49,7 @@
 
 def jpg_example(file_name: str) -> DocumentMeta:
     """
-    Create a document from a JPG file in the images directory.
+    Create a document from a JPG file in the image's directory.
     """
     return DocumentMeta(document_type=DocumentType.JPG, source=LocalFileSource(path=IMAGES_PATH / file_name))
 

examples/evaluation/document-search/advanced/config/pipeline/source/hf.yaml

@@ -1,4 +1,4 @@
-type: ragbits.document_search.documents.sources:HuggingFaceSource
+type: ragbits.document_search.documents.sources.hf:HuggingFaceSource
 config:
   path: "micpst/hf-docs"
   split: "train[:5]"

packages/ragbits-document-search/src/ragbits/document_search/_main.py

@@ -16,8 +16,8 @@
 from ragbits.core.vector_stores.base import VectorStoreOptions
 from ragbits.document_search.documents.document import Document, DocumentMeta
 from ragbits.document_search.documents.element import Element, ImageElement
-from ragbits.document_search.documents.source_resolver import SourceResolver
 from ragbits.document_search.documents.sources import Source
+from ragbits.document_search.documents.sources.base import SourceResolver
 from ragbits.document_search.ingestion.document_processor import DocumentProcessorRouter
 from ragbits.document_search.ingestion.processor_strategies import (
     ProcessingExecutionStrategy,

packages/ragbits-document-search/src/ragbits/document_search/documents/document.py

@@ -5,7 +5,8 @@
 
 from pydantic import BaseModel
 
-from ragbits.document_search.documents.sources import LocalFileSource, Source, SourceDiscriminator
+from ragbits.document_search.documents.sources import LocalFileSource, Source
+from ragbits.document_search.documents.sources.base import SourceDiscriminator
 
 
 class DocumentType(str, Enum):