Return source documents – Francisco Ingham You can now return documents used to generate the final answer in the VectorDBQA chain. Useful for getting more clarity on what was used to construct the answer Docs: https://
langchain.readthedocs.io/en/latest/modu
les/chains/combine_docs_examples/vector_db_qa.html#return-source-documents
…
@langchain
-
Return Source Documents in VectorDBQA Chain
By
–
-
Pinecone Wrapper Updates: Namespace Support and Similarity Scores
By
–
Updates to @pinecone wrapper – @SmitShah_11 iocuydi @iamraymondyuan – Namespace support
– from_index classmethod (for existing indices)
– method to return similarity scores along with documents Hopefully making it easier to use Pinecone indices! -
LangChain VectorDBQA Chain Types Integration Methods
By
–
Chain types There are many methods for combining documents (stuff, map reduce, map rereank, refine) It is now SUPER easy to choose your favorite one to use in VectorDBQA chains! Docs for QA: https://
langchain.readthedocs.io/en/latest/modu
les/chains/combine_docs_examples/vector_db_qa.html#chain-type
… Docs for QA with sources: https://
langchain.readthedocs.io/en/latest/modu
les/chains/combine_docs_examples/vector_db_qa_with_sources.html
… -
LangChain v0.0.61 Release: Vector DB and WolframAlpha Improvements
By
–
v0.0.61 WolframAlpha improvements – @nickscamara_ Doc improvements – Marc Green Making it easier to work with Vector DBs Improve @pinecone wrapper – @SmitShah_11 iocuydi @iamraymondyuan Return source documents – Francisco Ingham
Chain types -
Multi-Agent Architecture: Combining DB and Search Tool Patterns
By
–
super interesting. do you imagine a common query pattern to need both the DB and search tool? or will most queries be one or the other? if separate, you could almost make an agent for each tool, and then use those agents as tools themselves in a meta-agent that wraps them
-
GPT-3 with Memory: ChatGPT Approximation Explained
By
–
Yes correct – it’s not chat gpt, but rather an approximation of chat gpt that is gpt3 + memory (to replicate the conversational aspect)
-
FAISS Wrapper Now Returns Similarity Scores in Semantic Search
By
–
Return scores during semantic search – h/t @krrish_dh In addition to getting back the top documents from a vectorstore, the FAISS wrapper now supports returning similarity scores for those documents as well Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/utils/combine_docs_examples/vectorstores.html#faiss-specific
… -
LangChain deployment templates documentation now available
By
–
Deployment templates In the documentation, there is now a section for templates for how to deploy your LangChain app! https://
langchain.readthedocs.io/en/latest/depl
oyments.html
… Very open to contributions here – if you have any suggestions let us know! -
LangChain Multiple Memory Support Feature Release
By
–
Multiple Memory support – @diwanksingh You can now easily create a new memory instance that is a combination of multiple other types of memory! You no longer have to pick just one Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/memory/examples/multiple_memory.html
… -
WolframAlpha Integration Tool for LangChain Framework
By
–
WolframAlpha integration – @nickscamara_ Support for using Wolfram Alpha as a tool Collab Notebook: https://
colab.research.google.com/drive/1AAyEdTz
-Z6ShKvewbt1ZHUICqak0MiwR
… Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/utils/examples/wolfram_alpha.html
… s/o to others @brucehammer for suggesting this a few weeks ago, and others in the discord for reviewing!