Philippe PRADOS
Philippe PRADOS
The constructor of `PostgresChatMessageHistory` accepts only sync or async connection, and not an Engine. First, the connection was open in get_session_history, and pending during the life cycle of `RunnableWithMessageHistory`. So,...
Langchain offers two Markdown splitter implementations: - MarkdownTextSplitter - MarkdownHeaderTextSplitter The `MarkdownHeaderTextSplitter` class is not langchain compliant, since it inherits from anyone. It is not possible to use in a...
The `MongoDBStore` can manage only documents. It's not possible to use MongoDB for an `CacheBackedEmbeddings`. With this new implementation, it's possible to use: ```python CacheBackedEmbeddings.from_bytes_store( underlying_embeddings=embeddings, document_embedding_cache=MongoDBByteStore( connection_string=db_uri, db_name=db_name, collection_name=collection_name,...
**Describe the bug** Try to parse a pdf with `OCR_AGENT=unstructured.partition.utils.ocr_models.google_vision_ocr.OCRAgentGoogleVision`. **To Reproduce** Provide a code snippet that reproduces the issue. ``` import os os.environ[ "OCR_AGENT"] = "unstructured.partition.utils.ocr_models.google_vision_ocr.OCRAgentGoogleVision" from unstructured.partition.pdf import...
### Bug export_to_markdown with ImageRefMode.EMBEDDED generate error. ... ### Steps to reproduce ``` converter = DocumentConverter() result = converter.convert(file_path) result.document.export_to_markdown( image_mode=ImageRefMode.EMBEDDED, ) ``` generate error: ``` ``` Where it's possible...
This is one part of a larger Pull Request (PR) that is too large to be submitted all at once. This specific part focuses on updating the PDFPlumber parser. For...
> This PR is a composition of many other PRs. Modifications will be published one after the other, to facilitate analysis and integration into langchain. # Refactoring all PDF loader...