Better documentation for understanding how custom agents work @samcwl added some much needed comments in both the documentation and the below notebook on the expected LLM output to get it to work with custom agents https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/custom_agent.html
…
@langchain
-
Improved Documentation for Custom LangChain Agents
By
–
-
AI21Labs Experimental Models Now Available for Integration
By
–
Also, highlighting one of the earlier points, its now possible to use some of the @AI21Labs experimental models! “`llm = AI21(maxTokens=10, model="j1-grande-instruct")“` Looking forward to playing around with this
-
v0.0.65 Release: Documentation Fixes and AI Model Support
By
–
v0.0.65 Doc Fixes – Francis, Chetanya Rastogi
Prompt improvements – @fpingham @brunotorious Support for @AI21Labs experimental models – xettrisomeman
Fix default @CohereAI embedding model – Sasmitha Manathunga Some doc improvements, listed -
FAISS Vectorstore Saving and Loading Guide
By
–
Instructions for saving and loading FAISS vectorstore You just want to create your vectorstore once, and then pass it around. We added some easy documentation on how to do so. https://
langchain.readthedocs.io/en/latest/modu
les/utils/combine_docs_examples/vectorstores.html#saving-and-loading
… -
Chat-LangChain: Extensible AI Documentation Tool for Websites
By
–
got it – https://
github.com/hwchase17/chat
-langchain
… should be pretty extendable to arbitrary websites (is currently langchain documentation, but you can swap out the URL). going to add more instructions for this today! -
Standard Interfaces for LLM and Embeddings Providers
By
–
pretty easy to swap this out! we have standard interfaces for most llm/embeddings providers
-
LangChain Chat Projects and Open Source AI Applications
By
–
Other links GitHub Repo: https://
github.com/hwchase17/chat
-langchain
… @huggingface Space: https://
huggingface.co/spaces/hwchase
17/chat-langchain
… Related projects that are also great: GitHub support bot from @floydophone
: https://
dagster.io/blog/chatgpt-l
angchain
…
Converse with PDFs from @deskriders_twt: https://
github.com/namuan/dr-doc-
search
… -
Lucid Web Browser Partnership for AI-Powered Question Answering
By
–
Big shout out to @chillzaza_ for partnering with us on this! This was based on a lot of his work with Lucid – a web browser that can do this type of question answering for the whole web
— LangChain (@LangChain) 17 janvier 2023
Also shout out to @sjwhitmore for the original idea ~3 months agohttps://t.co/rBrVXP3iM2Big shout out to @chillzaza_ for partnering with us on this! This was based on a lot of his work with Lucid – a web browser that can do this type of question answering for the whole web Also shout out to @sjwhitmore for the original idea ~3 months ago
-
ClerkieAI Advanced Question Answer Bot Now Live
By
–
If you like this and want a more advanced version of this for your codebase, you should check out @ClerkieAI Their question answer bot is live on our Discord:
-
Improving Chatbot UX: Follow-ups, Prompt Engineering, Data Prep
By
–
1. We make it an actual chatbot, where you can ask followup questions (important UX decision!) 2. @chillzaza_ has a lot of insights on prompt engineering (citing sources, writing markdown, speed) 3. Some notes on importance of data preparation