pg_embedding @PostgreSQL is popular database choice. Excited to share a new extension from @neondatabase to help you use it for embeddings as well (with HNSW)! Blog:
@hwchase17
-
Integrations Page Gets Major Updates with New Categories
By
–
Some big improvements to the integrations page, including new categories (callbacks) and new pages (top/trending/new)
-
LangChain Updates Anthropic Client Wrapper for Latest Version
By
–
Updated Anthropic Client In the newest @langchain release (0.0.225) we've updated our @AnthropicAI wrapper to deal with their new 0.3.* client Should be seamless upgrade experience – just `pip install -U anthropic` and you'll be set! No more changes than that
-
Team feedback on complex AI logic chain implementation
By
–
Big shout to the team at @exemplaryai for feedback on this front! There's sneaky a lot of logic in this one chain, hopefully this clears some of it up. Anything else we can do to help here?
-
Token Max Parameter in ReduceDocumentChain and ConversationalRetrievalChain
By
–
Token Max parameter This impacts the ReduceDocumentChain, which can often be used to power the ConversationalRetrievalChain This parameter controls how large of chunks (in token length) to combine documents into before reducing Docs:
-
Enhanced Reference Documentation with Better Docstrings Examples
By
–
Improved Reference Docs We beefed up our reference documentation to include better docstrings and a more end-to-end example There's a lot of toggles to play with, hopefully this helps make it more clear what all the parameters are Docs:
-
ConversationalRetrievalChain Gets Quality of Life Improvements
By
–
ConversationalRetrievalChain Upgrades One of our more popular chains is the ConversationalRetrievalChain, which allows you to create a retrieval augmented generation chatbot We've introduced some small but impactful quality of life changes:
-
Building Slack Bots with LangChain and Jina AI
By
–
awesome stuff showing how to build slack bots using langchain and @JinaAI_ !
-
LangChain Airbyte Dagster Integration for Document Processing
By
–
LangChain x @AirbyteHQ x @dagster Load documents from one of @AirbyteHQ
's 300+ sources, split/embed/store it with @langchain
… all orchestrated by @dagster
! Excited to share this end to end guide -
Memory Implementation for Follow-up Questions in AI Systems
By
–
And finally, chat: we explain how to use memory to enable follow up questions, why that is necessary, and methods for doing so Big shout to to @RLanceMartin for helping prep all these materials!!!! Always fun to do these! What topic should we do next?