LangChain

Another year, another leap in LLM app development! 🪄 Our new 2024 LangChain State of AI report uncovers key trends in how developers are building LLM apps. In 2024, we’ve seen a shift from retrieval workflows to multi-step, agentic applications. 🤖 Open-source models are also gaining traction as devs seek more customizable infrastructure. Here's where the AI ecosystem is headed, based on data from LangSmith.👇 Read the full report: https://lnkd.in/g5yd92QW

`langchain-box v0.3.1` has just been released. Python users can now use: 🗂️ BoxBlobLoader: Effortlessly load files via IDs, folders, search, or metadata queries. 🧩 Add custom extra_fields to metadata for more flexibility in workflows. Learn more from Box: https://lnkd.in/eGwyfTqR

🔥 Learn how Decagon built their AI Agent Engine 🔥 Join us for an evening meetup on February 4th in San Francisco hosted at Pear VC, featuring a fireside chat with Harrison Chase (CEO of LangChain) and Bihan Jiang (Product Lead at Decagon). Bihan and Harrison will take you behind the scenes of Decagon's comprehensive system for the deploying production-ready AI agents. Trusted by industry leaders like Duolingo, Notion, Rippling, and Eventbrite, Decagon's customer support agent handles end-to-end customer interactions. Enjoy snacks, drinks, and insightful discussions! Spots are limited, so RSVP now ➡️ https://lu.ma/w7y0bqwr

📩Email assistant agent Today we're releasing an open source email assistant agent that we've been using internally for the past six months We're also releasing a free to use hosted version This is the first agent in a new UX paradigm we're calling "ambient agents" 🤖What are ambient agents? While the dominant UX for LLM applications so far is chat, we imagine this changing "Ambient agents" are agents that are always on, listening to an event feed, and responding to or flagging those events as necessary Will let us scale ourselves far more than chat 📩Open source email assistant agent An email assistant is a great example of this - so we built and open sourced it! It checks emails and triages them. It can either ignore, notify, or respond. The human is very much in the loop - approving all outgoing emails Read more about ambient agents here: https://lnkd.in/gcqP8qMR See the open source email assistant here: https://lnkd.in/gDy9USvA Use the hosted email assistant for free: https://www.agentinbox.ai/

🗣️📄 DocTalk: Voice Chat with PDFs Experience natural conversations with your PDF documents through voice. Powered by RAG and real-time AI processing, DocTalk lets you interact with documents using Push-to-Talk or Open Mic. Learn more: https://lnkd.in/dE_2Hm3q

Adding Chat-LangChain To Slack Chat-LangChain is an AI assistant for answering questions about LangChain/Graph documentation. We recently created a free-to-use Chat-LangChain deployment and connected it to Slack as an app. This allows anyone to onboard Chat-LangChain to their Slack workspace and freely use it for QA. This video walks through the process: 1/ set up a Slack app 2/ use @modal_labs to route / format Slack events 3/ send responses from Chat-LangChain to Slack The processed reviewed is general and can also be extended to any LangGraph deployment. Video - https://lnkd.in/g7eyga8b Repo - https://lnkd.in/gVUNHzm3 LangChain Academy module to more context on LangGraph Deployments - https://lnkd.in/gjGAjHAx

Acxiom, a global leader in customer intelligence, is using generative AI to redefine audience segmentation for marketing & advertising. Using LangSmith, the Acxiom team has: 🔹 Scaled dynamic audience segmentation with robust LLM observability. 🔹 Streamlined debugging for more refined marketing campaigns. 🔹Enabled scalable, cost-efficient growth for their hybrid AI stack. 👉 Dive into the full story: https://lnkd.in/g9ndfpgV S/o to Varadarajan Srinivasan, Alex McAnulty, and Vicky Becart for bringing this story to life!

🤖📰 Intelligent News Agent Meet your AI-powered news assistant fighting information overload. Built with LangGraph, it processes multiple sources to deliver comprehensive news summaries that matter to you. Learn more: https://lnkd.in/gH8naHYc

🤖✈️ AI Travel Agent Tutorial Build an AI travel agent using LangChain's Plan and Execute architecture. This tutorial shows how to create intelligent agents that plan trips while managing essential travel tools and services. 🎥 Learn more: https://lnkd.in/gW22Qa4S

🤖📚 ContentMind AI Transform websites into LLM-ready research material with this intelligent agent. Built with LangGraph and LangSmith, it powers automated documentation indexing while seamlessly connecting to X and Slack through Arcade integration. Learn more: https://lnkd.in/g82ueuUB