Excited to help judge this! Submit your projects to https://
github.com/premAI-io/chal
lenge-with-langchain
…
@hwchase17
-
PremAI LangChain Challenge: Submit Your AI Projects Now
By
–
-
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
-
Open Source Model APIs Now OpenAI-Compatible via LangChain
By
–
Many startups focused on serving open source models have exposed APIs that are interoperable with OpenAI This makes it easy for anyone to try them out by just changing the API base We added better support for this in @langchain in the most recent release (h/t Yuze Ma)
-
LangChat: Customizable LangChain Chatbot Wrapper Specification
By
–
Pretty good spec for langchain chatbot wrapper (langchat?) Let use easily customize LLM used, system message, that’s it Who’s gonna build?
-
Chatbot Configuration: Memory, LLM, and System Message Options
By
–
chatbots is a good one. what (if anything) would you want to configure in a chatbot? memory type? llm? system message?
-
Higher Level LangChain Wrappers for LLM-Powered Applications
By
–
I like this a lot – a higher level wrapper around langchain to make a specific use case (LLM-powered bots over a dataset) easier to create What other use cases deserve higher level wrappers around langchain?
-
OpenAI Function Caching Reduces Development Costs
By
–
As @mayowaoshin noted, using @OpenAI functions can be expensive By enabling caching, you can eliminate some costs as you develop Just in time for some weekend hacking