1/ Plan-and-execute Planner LLM generates a task list, each task is executed by a smaller LLM, and dynamic replanning (or response) is done using the final output. Based on the @yoheinakajima
's BabyAGI project and Lei Wang's "Plan and solve" paper Python:
@langchain
-
Plan-and-Execute: LLM Task Planning and Dynamic Replanning
By
–
-
Self-RAG: Self-Reflection for Reliable Retrieval-Augmented Generation
By
–
Self RAG Self-reflection is one of the most interesting ideas in RAG, giving an LLM the ability to self-correct problems in retrieval and / or generation. But, implementing this reliably can be tricky. We've found that graphs are a great way to reliably express logical flows,
-
RAGAS v0.1 Released for RAG Application Evaluation
By
–
Evaluate RAG applications with RAGAS v0.1 RAGAS is one of the most popular OSS ways to test RAG applications And they just released v0.1! If you've been meaning to improve your evaluation pipeline for RAG applications – never a better time to start! https://
github.com/explodinggradi
ents/ragas
… -
Deploying PDF RAG Chatbots to Production with LangServe
By
–
Unlock the Power of Lang Chain: Deploying to Production Made Easy In part 3 of his series, @austinbv shows how to deploy a PDF RAG chatbot to production using LangServe YouTube: https://
youtube.com/watch?v=CbBIwV
xjdP8
… -
Deploying LangChain Agents with LangServe API Endpoints
By
–
So you've built a LangChain chain or agent – what next? How do you deploy it?
— LangChain (@LangChain) 11 février 2024
This great blog by @GitMaxd walks through how to do this with LangServe
📃Your first A.I. API endpoint with 🦜LangServehttps://t.co/3NRJ6QRnMz pic.twitter.com/6O5w563n3nSo you've built a LangChain chain or agent – what next? How do you deploy it? This great blog by @GitMaxd walks through how to do this with LangServe Your first A.I. API endpoint with LangServe https://
medium.com/@gitmaxd/your-
first-a-i-api-endpoint-with-langserve-deeb65e750b1
… -
Building Multi-Agent Apps with LangGraph Gemini Pro Streamlit
By
–
LangGraph + Gemini Pro + Custom Tool + Streamlit = Multi-Agent Application Development Awesome tutorial (YouTube and blog) from Gao Dalie on how to build a multi-agent application with LangGraph and Gemini-Pro YouTube: https://
youtube.com/watch?v=FWBnNc
Zv3kw
… Blog: https://
levelup.gitconnected.com/langgraph-gemi
ni-pro-custom-tool-streamlit-multi-agent-application-development-79c1473086b8
… -
LangChain 101: Document Loading, Splitting and RAG with LCEL
By
–
LangChain 101: Talking to Documents: Load, Split, and simple RAG with LCEL Loading documents and splitting them are a key part of RAG In his most recent update to the "LangChain 101" series Ivan Reznikov covers this in detail https://
pub.towardsai.net/langchain-101-
part-3a-talking-to-documents-load-split-and-simple-rag-with-lcel-26b005ccb30a
… -
LangChain Updates: LangSmith Monitoring, RAG Improvements
By
–
LangChain Release Notes Week of 2/5 LangSmith: better monitoring, cost visibility, regression testing, and feedback rubrics for annotation queues A deep dive into OpenGPTs Cookbooks for better RAGs & a new YouTube series around RAG: RAG from Scratch!
-
CommandBar LangSmith Partnership Enhances Copilot Performance
By
–
Excited to share more about how @langchain partners with @CommandBar on their Copilot User Assistant! CommandBar decided to use LangSmith to give them visibility over their Copilot’s performance and ultimately deliver better experiences for their customers. While the team did
-
Build Gemini-Powered Search Agents with LangChain
By
–
Gemini + Google Search Agent Curious what you can build yourself in the @Google Gemini era? Spend a few minutes with LangChain founding engineer @eyfriis and quickly get up and running with a Gemini-powered agent that has access to Google Search to retrieve information!