Was awesome to see this in python, glad it made its way to js! https://t.co/qGwE4ChYgC
— Harrison Chase (@hwchase17) 3 juillet 2023
Was awesome to see this in python, glad it made its way to js!
@hwchase17
-
Python AI Feature Successfully Ported to JavaScript
By
–
-
LangChain QA Documentation SQL Implementation Experience
By
–
anyone tried this out with a langchain (qa over docs, sql) yet?
-
Streamlit Invests in LLM and LangChain Integration Tools
By
–
Streamlit was built for this LLM era
— Harrison Chase (@hwchase17) 29 juin 2023
The @streamlit team has been putting out AWESOME content for the past few weeks, really investing in LLMs & LangChain integrations… a perfect combo https://t.co/VGR5jAKEwoStreamlit was built for this LLM era The @streamlit team has been putting out AWESOME content for the past few weeks, really investing in LLMs & LangChain integrations… a perfect combo
-
LangChain Launches New Integrations Hub for AI Tools
By
–
A lot of the power of @langchain is the sheer number of connections and optionality it provides Our new integrations hub should make it easier to explore and discover all that is out there Big s/o to @mollycantillon for helping build this!
-
MultiQueryRetriever: Advanced Retrieval Beyond Semantic Similarity
By
–
In search of retrieval better than simple semantic similarity search… Excited to share MultiQueryRetriever, inspired by @RickLamers
! -
Chains vs Agents Webinar with AGI House Hackathon Winners
By
–
Going live for "Chains vs Agents" webinar in ~1 hour! @swyx and I will also be joined by members of the winning team from the Agents AGI House hackathon this past weekend! They built a project called AgentEval they'll talk about
-
PremAI LangChain Challenge: Submit Your AI Projects Now
By
–
Excited to help judge this! Submit your projects to https://
github.com/premAI-io/chal
lenge-with-langchain
… -
LangChain PR improves open source model experimentation
By
–
PR for this here: https://
github.com/hwchase17/lang
chain/commit/e9877ea8b1d301efafb7d2fda5f9105b005774b8
… Shout out to Yuze Ma for highlighting this limitation at a hackathon this weekend! Hopefully this should make it easier to experiment with open source models -
Open Source Models Now Support Custom Tokenizer Fallbacks
By
–
Of course, when using an open source model (Vicuna, Dolly) that model name is not in the tiktoken wrapper Previously, this would raise an error We've now updated this to: (1) fallback to a default tokenizer, (2) allow users to specify model name to use for tiktoken
-
LangChain API Base Configuration and Token Management
By
–
It's always been possible to change the API base in the LangChain model wrappers However, the model wrappers do a lot of handy things like token management, which rely on tokenizers that by default we look up in tiktoken We look this up based on model name