LangChain

Discover how to build a simple VLM-based multimodal information retrieval system using NVIDIA NIM. Perfect for developers looking to prototype small-scale experimental pipelines without the complexity of enterprise-ready solutions. Learn how to: ? Integrate vision-language models for text, images, and tables ? Leverage NVIDIA NIM microservices for scalable deployment ? Utilize LangGraph and Llama models for optimized retrieval Check out the new blog and explore the GitHub repo ?? https://nvda.ws/3F0zqEh

?? How MUFG Bank boosted sales efficiency 10x with LangChain At MUFG Bank, Japan's largest bank, the FX & Derivative Sales team spent considerable time gathering & synthesizing data from 10-K reports, financial disclosures, and market data to create client presentations. By using LangChain, the AI/ML team automated data extraction and used few-shot prompting to generate customized presentations. The result? ???Presentation creation time reduced from hours to just 3-5 minutes ?? 10x more corporate clients received tailored financial recommendations Read more: https://lnkd.in/gwkWu5HY

?? Announcing LangGraph v0.3 with Prebuilt Agents! We're introducing LangGraph prebuilt and a collection of ready-to-use agent libraries built with LangGraph: - LangGraph Prebuilt: high-level APIs for tool-calling agents (part of LangGraph) - Trustcall for reliable structured extraction - LangGraph Supervisor for supervisor multi-agent architectures - LangMem for long-term memory - LangGraph Swarm for swarm multi-agent architectures We hope this will make it easy to get started with building agents and foster a large collection of prebuilt agents built by the community. Want to contribute your own agents? Check out instructions in the blog! Blog: https://lnkd.in/d3K7w-QQ

Keith Fearon and I will be speaking at LangChain's upcoming Interrupt conference on 5/14! 11x is doing over 100k agent executions per day in production right now. I think we're one of the most sophisticated teams in the world when it comes to AI agents. I'm excited to share some of the lessons we've learned. Our partnership w/ LangChain has been essential! #ai #agents #langchain #interrupt #sf #conference

?? Start Evaluating LLMs with OpenEvals ?? Evals are a vital part of bringing LLM apps to production. To make it easier to get started, today we're announcing a new OSS repo: OpenEvals! OpenEvals contains prebuilt evaluators that help you quickly add evals to your app, whether it's built with LangChain, LangGraph, or neither. They encapsulate what we've seen as emerging best practices in the industry. Try it out in Python or JS - we welcome any feedback or contributions! ?? Blog: https://lnkd.in/ePr8gG9f ?? OpenEvals repo: https://lnkd.in/eKXqjbqW ?? Video intro: https://lnkd.in/ex3J_Rfc

?? Custom Routes in LangGraph Platform! Extend your LangGraph deployment with custom HTTP endpoints for anything from simple health checks to complete UIs - all in one server.Build persistent, full-stack AI apps in python with a single backend. ??Tutorial:?https://lnkd.in/gSDfWzic?- learn to use Jeremy Howard's Fast HTML for a modern chat UI with built-in conversational memory ?? Docs:?https://lnkd.in/gaX-MZst ?? Template:?https://lnkd.in/gsbmtvhn

?? LangGraph Swarm - A lightweight library for building swarm-style multi-agent systems with LangGraph - Multi-agent collaboration - enable specialized agents to work together and hand off context to each other - Customizable handoff tools for communication between agents Watch the video: https://lnkd.in/gbgyCeEd Try it out with `pip install langgraph-swarm` Repo: https://lnkd.in/gXUyEP_6

?? LangGraph.js Supervisor A lightweight library for building hierarchical multi-agent systems with LangGraph - ?? Create a supervisor agent to orchestrate multiple specialized agents - ??? Tool-based handoffs for agent communication - ??? Built with LangGraph.js: comes with built-in streaming, memory and human-in-the-loop support Watch the video ?? https://lnkd.in/gUWZUmH4 Try it out with `npm install @langchain/langgraph-supervisor` Repo: https://lnkd.in/g8mid5yj

Outshift by Cisco is leveraging LangGraph to power a ReAct-based DevOps agent that performs tasks such as retrieving info from GitHub repos with RestAPIs. See how they: ?? Automated CI/CD & infra tasks with API-based DevOps actions. ?? Used ReAct for smarter API calls like GitHub repo insights. ?? Managed state for reliable execution and iterative reasoning. Read the blog: https://lnkd.in/gp_ch2DX

Tomorrow, Feb 25th at 8am PT/11am ET — join Jesse Hall (MongoDB) & Jacob Lee (LangChain) to explore LangGraph.js + MongoDB for AI agents. Learn to: ? Integrate LangGraph.js and MongoDB ? Build a controllable AI agent with LangGraph.js ? Persist conversation state ? Deploy & test AI agents in a web environment Register now ?? https://lnkd.in/ebhAh_3w