LangChain just announced a new Toolkit abstraction that allows developers to create agents designed for a particular use-case. We leveraged toolkits to build an agent capable of looking through an OpenAPI spec and making a correct API request based on the spec. Let's unpack this:
Co-Founder @LangChain
San Francisco, CA
Joined June 2011
- Excited to officially announce that I’ve teamed up with @hwchase17 to co-found @langchain and that we’ve raised a $10M seed round led by @benchmark. Working with Harrison, @milesgrimshaw and the rest of the the team/community has been a great privilege. Time to build! 🚀Really excited to publicly announce that: 1⃣ @ankush_gola11 and I have started a company around @langchain 2⃣We raised a seed round from @benchmark We wrote a bit about the journey so far, and where we want to take it: blog.langchain.dev/announcing-our…
- Thrilled to announce our Series B today which at a $1.25B valuation. Huge thank you to @tomloverro and the team at @IVP for leading this round, with participation from Alphabet’s @CapitalG and @SapphireVC and continued support from @sequoia, @benchmark and @AmplifyPartnersWe raised $125M to build the platform for agent engineering. Thank you to our investors (@IVP, @sequoia, @benchmark, @AmplifyPartners, @SapphireVC, @CapitalG, and more) for their belief in us, and to our customers like @Replit, @clay, @TrustVanta, @Cloudflare, @Rippling, @Cisco,
00:00 - We're excited about the Poe API and have released a repository with some basic examples on how you can use @langchain and @FastAPI to build Poe handlers. Check it out here: github.com/langchain-ai/l…Today we are officially launching the Poe API to all developers. Details in thread below!
- This is going to be really useful for running agents more efficiently, allowing you to run multiple tools in a single agent step. With the async API, these tools runs concurrently🤖Multi-Action Agent Asking an agent to take only one action at a time is so March of 2023 With a small little update to the AgentExecutor, it's now possible to have an agent output MULTIPLE agent actions to take Documentation: python.langchain.com/en/latest/modu…
- We've put together a repo that showcases how to use @langchain with @supabase to create a full-stack AI application. S/o @nfcampos for kicking this off and expect this template to evolve over time⭐️LangChain x Supabase⭐️ We put together a template repo for how to build a full stack application with LangChain and Supabase Repo: github.com/langchain-ai/l… For more details (and more ways to use Supabase within LangChain) see 👇 blog.langchain.dev/langchain-x-su…
- Some of you might have remembered a tweet I put out a couple months ago about an OpenAPI agent that iteratively looks through a large spec to figure out how to make a request. This new OpenAPI Planner/Executor agent is *way* betterNew version 🦜🔗 v0.0.132 with a focus on interacting with APIs (using OpenAPI specs) ⚕️OpenAPIEndpointChain - a chain that wraps a specific endpoint to provide a "Natural Language API" 📒OpenAPI Planner/Executor Agent - good for interacting with large specs 🧵
- Really excited to announce our partnership with Microsoft, a big step in advancing production-grade LLM applications for enterprises on Azure!LangChain 🤝🏾 Microsoft Today, we’re thrilled to announce our collaboration with @microsoft @azure. Our joint customers will enjoy deeper product integrations that live up to our commitment to AI with the enterprise assurances the Azure ecosystem provides. more on the blog and
- LangSmith processes nearly 1 billion events and 10s of TB of data every day! In order to help users sift through all of the data they're sending us, we launched Insights Agent! This agent automatically processes your traces in the background and gives you insights into how users🔎🤖LangSmith Insights Agent Really excited to launch our first in-product agent This agent lives inside LangSmith and combs through traces, giving you insights into: 🧑🤝🧑how users are using your agent ⁉️how your agent may be messing up 🛃{your custom insight here} The problem
00:00 - 🦜🛠️Super excited to launch LangSmith today in closed beta! Developers need more tooling to move their LLM Applications from prototype to production. LangSmith is here to bridge that gap.🦜🛠️ Introducing LangSmith 🦜🔗 A unified platform to help developers debug, test, evaluate, and monitor their LLM applications. Integrates seamlessly with LangChain, but doesn't require it.
- Awesome to hear how much the Replit team relied on LangSmith leading up to the launch of Replit Agent! It’s been great working with the team, congrats to them on a huge launchReplying to @hwchase17The team spent more time in langsmith than their significant others the past few weeks :D
- If you're building serious products with LLMs, you need evals. LangSmith is the best way to incorporate evals into your application development lifecycle, regardless of whether or not you're using LangChain to build your apps. Watch @langchain's very own YouTube starLangSmith Evaluations With the rapid pace of AI, developers are often faced with a paradox of choice: how to choose the right prompt, how to trade-off LLM quality vs cost? Evaluations can accelerate development with structured process for making these decisions. But, we've
- Excited to join eng leaders at Pinterest, Retool, and Encamp next week! Tune in to the discussion on AI's role in engineering, leveraging LLMs, and much more. You can register here:
- Excited that @langchain is featured in the @Wing_VC Enterprise Tech 30 as #1 in the early stage category! enterprisetech30.com Really proud of the progress we've made in streamlining LLM application development, but the work has just begun. Come join our growing team!⭐ We're grateful for the recognition in Enterprise Tech 30 as the #1 ranked Early-Stage Startup! ⭐ We're on a mission to make it easy to build the LLM apps of tomorrow, today. We're actively hiring across multiple roles including Software Engineer (JS, Python, SDK, &















