This is a perfect application of LLMs with long context windows The longer the context window, the less time you have spend beforehand clustering/preparing the data Sign up for the @AnthropicAI hackathon (we'll be there!) to try out things like this! https://
x.com/AnthropicAI/st
atus/1679494670047379456?s=20
…
@hwchase17
-
LLMs Long Context Windows Reduce Data Preparation Needs
By
–
-
Stacking Chains as Tools in AI Agents
By
–
A great overview of using an agent to interact with custom data! Step 1: Upload data to Metal
Step 2: Create a retrieval QA chain
Step 3: Use that chain as a **tool** in your final agent This idea of stacking chains as tools (or agents as tools) is super powerful! -
Analyzing Natural Language Interactions with LLMs
By
–
Analyzing natural language interactions with LLMs The new interface for apps is through natural language. This means there is a new category of user interactions to analyze And the best way to analyze natural language interactions is… with an LLM
-
Berkeley AI Hackathon Winners Build Character Creation Tools
By
–
Winners from Berkeley AI hackathon sharing what they built to help game developers create characters more easily https://
crowdcast.io/c/cb9x203fynvd -
Creating Characters with AI: Creative Webinar
By
–
Going live to talk about creating characters with AI! Should be one of the more fun and creative webinars: https://
crowdcast.io/c/cb9x203fynvd -
Automatic Metadata Extraction Using LLMs Now Available
By
–
Automatic Metadata Extraction @RLanceMartin has done a lot of work showing how having the correct metadata attached to documents can be valuable, but there's still the question: how do you get that metadata? Use an LLM to extract it of course! Now live in JS and Python
-
LangChain Integrates Context AI for Chat Analytics
By
–
Chat Application Analytics Introducing an integration with @getcontextai which allows you to receive user analytics with a one line plugin Blog: https://
blog.langchain.dev/langchain-x-co
ntext-building-better-chat-products-with-user-analytics/
… Integration: https://
integrations.langchain.com/callbacks?inte
gration_name=ContextCallbackHandler
… -
PandasAI: GenAI Library for Data Analysis with Claude
By
–
Pandas AI x @AnthropicAI @ai_pandas is an AWESOME library by @lele_venturi that adds GenAI capabilities to pandas DFs It's also fully compatible with @langchain LLMs… which means you can easily use things like @AnthropicAI
's claude-2! Repo: https://
github.com/gventuri/panda
s-ai
… -
LangChain PGEmbedding Integration Now Available
By
–
Integrations page for LangChain: https://
integrations.langchain.com/new?integratio
n_name=PGEmbedding
… HN discussion: https://
news.ycombinator.com/item?id=366955
42
… -
Neon Database Vector Analysis Compared to pg_vector
By
–
What I really like about the analysis the @neondatabase team did is that they did a pretty detailed comparison to `pg_vector`. s/o @raoufdevrel for this They both have their pros and cons! @andrewkane @kiwicopple would love your thoughts here as well