Profile avatar
langchain.bsky.social
⚡️Build context-aware, reasoning applications ⚡️
144 posts 1,530 followers 0 following
Regular Contributor
Active Commenter

Vibe Testing GPT4.5 OpenAI just released GPT4.5 w "higher emotional intelligence and creativity" than prior models. Here, we overview its capabilities and vibe test it on research / writing using our Open Deep Researcher. Video: youtu.be/Jo2-fZ2THzU

🌌 GPT-4.5 🤝 LangChain 🦜 OpenAI just launched GPT-4.5 (Orion), a new, powerful, general-purpose model! If you have access, you can drop it in day 0 in your Python and TypeScript langchain apps just by switching your model string! Docs in the thread 👇

🔗🛠️ MCP Adapters A lightweight wrapper that converts Model Context Protocol tools into LangChain-compatible tools, with multi-server support and React agent compatibility. Seamlessly integrates with LangChain Core and LangGraph. Check it out 👉 github.com/langchain-ai...

🛠️ Introducing Langchain MCP Adapters: LangGraph agents 🤝 Anthropic Model Context Protocol ⚡ Instantly connect LangGraph agents to hundreds of tools in the growing MCP ecosystem! Watch the video ➡️ youtu.be/OX89LkTvNKQ Try it out in Python with `pip install langchain-mcp-adapters`

🤖 Meet Ava: WhatsApp AI Agent An open-source agent powering WhatsApp conversations with text, voice & image capabilities. Built on LangGraph, it delivers advanced AI features through a state-aware, graph-based architecture. Build your own AI companion 👉 theneuralmaze.substack.com/p/meet-ava-t...

🤖💻 GPT Computer Assistant Framework Just released: An open-source framework for building AI agents that interact with computers like humans. GCA empowers developers to create intelligent automation using multiple LLMs, screen interaction, and voice capabilities.

🔍 Deep Research Agent Build an autonomous research agent that processes Wikipedia content using LangChain's RAG with Milvus vector storage. Features intelligent question analysis, content synthesis, and local deployment. Ready to build your own? Check it out 🚀 milvus.io/blog/i-built...

🌐🤖 Browser-Use An open-source tool that lets AI agents control web browsers through natural language, powering sophisticated browser automation. Key Features: - Natural language control - Cloud/self-hosted options Check it out! 🚀 github.com/browser-use/...

🌐SiteRAG - an open source Chrome extension for RAG SiteRAG allows you to quickly extract the page/website contents and include them in the model's context for question answering. It can index pages and persist them in a vector store, allowing for RAG over that site. 🧵

📚🤖 Advanced RAG + Agents Cookbook A comprehensive open-source guide delivering production-ready implementations of cutting-edge RAG techniques with AI agents. Built with LangChain and LangGraph, it features advanced implementations like Hybrid, Self, and ReAct RAG.

🧠 OpenAI o3-mini + LangChain 🦜 OpenAI just dropped a new model! o3-mini is a reasoning model with "intelligence comparable to o1" at a fraction of the latency and cost. Try it in your LangChainAI Python or JS/TS apps by just changing a string. Let us know what you think!

🐋 DeepSeek 🤝 LangChain 🦜 DeepSeek has taken the community by storm since open-sourcing R1, a powerful model that reasons like OpenAI's o1 while also exposing its thought process! LangChain offers many ways to use it in your projects alongside the faster deepseek-V3 in Python and JS:

📄🤖 PDF Q&A with Deepseek Create a production-ready AI chatbot that answers questions from PDFs using DeepSeek's LLM and LangChain's document processing. Features intelligent text processing, advanced reasoning, and an intuitive interface. www.youtube.com/watch?v=M6vZ...

⭐️Want an open source version of OpenAI's Operator? There's a great open source project called Browser Use that does similar things (and more) while being open source Allows you to plug in any model you want Love to see open source leading the way🚀 github.com/browser-use/...

Understanding + Using Reasoning Models Reasoning models (OpenAI -o series, deepseek_ai's R1) are improving very rapidly. Here is a short overview of this new scaling paradigm with some practical prompting tricks and a set of emerging use-cases. Video: youtu.be/f0RbwrBcFmc

A Fully Local "Deep Researcher" w/ Deepseek-R1 deepseek_ai-R1 is an open source, highly performant reasoning model. We used ollama+LangGraph to build and test a local research assistant w/ Deepseek-R1-14b. Video: youtu.be/sGUjmyfof4Q Repo: github.com/langchain-ai...

We’ve just launched updates to the LangSmith Playground! 🕹️ Here's what’s new 👇🧵 ✨ New Prompt Settings UI Manage all your prompt settings in one streamlined view. Stay organized while building and testing prompts.

🤖 🔄 Build Smarter AI Agents LangGraph introduces state-aware AI workflows for sophisticated reasoning and decision-making. This tutorial shows you how to create advanced AI applications with powerful cyclical processing capabilities. Learn more: datasciencedojo.com/blog/langgra...

📊🤖 AI Financial Analyst Agent Create an intelligent stock analysis system that uses LangGraph and GPT-4 to automate investment recommendations with real-time market data and LLM-powered insights. Learn more about building your own AI analyst: rsci.app.link/nOKueixlNOb?...

🤖 Build AI Agents with LangGraph A practical tutorial showing you how to create AI agents and chatbots using LangGraph. This guide walks you through state management and LLM integration with real code examples, powered by modern LLM providers. Learn more: levelup.gitconnected.com/learn-how-to...

📚🤖 King RAGent An open-source AI research assistant that uses LangChain's RAG components to synthesize information from PDFs and web searches, delivering confident and comprehensive answers to your queries. Learn more about this powerful research assistant: github.com/alonlavian/R...

📥 Agent Inbox UI Today, we're releasing the UI web app which powers our human-in-the-loop agent interactions. The Agent Inbox UI is a generic app which can connect to, and interact with any LangGraph app that uses interrupt events for human-in-the-loop workflows 🧵

Need to centrally manage your LLM interactions? Join the waitlist for LangChain Gateway and become an early partner for our unified interface that streamlines your LLM workflows. 🤝

📲 Open Source Social Media Agent For the past three weeks, we've been using an ambient agent to draft and schedule social media posts highlighting community content Think of it as an "AI Social media intern" Today we're releasing it as an open source repo 🧵