LangChain’s Post

🤖 skyffel has been playing around with building AI agents in the data pipelining space over the last week and just got a first working prototype! We help you tackle data loading from HTTP APIs. ⚙️ The agent generates an Airbyte low-code (YAML) connector from documentation. All you have to do is to provide it with the goal of your integration and links to documentation. 🔨 Take it for a spin: https://lnkd.in/gmS8gpwx (original link in comments)

Check out Shankar J.'s post comparing GPT-4 Turbo with GPT-4o for Vision Agent as well as running AgentCoder!

Check out how our vision-agent seamlessly transforms video data into structured format! 🎥💻 #VisionAgent #DataTransformation

LANDING AI is doing an amazing job on creating vision agents to autonomosly accomplish computer vision tasks, and this is the most exciting demo I've seen so far. In this video, Shankar J. is using our vision-agent library to put together LLMs (including the newly released GPT-4o) and computer vision models to automatically detect children's distance to a pool in a video stream. Even more impressive: the library generates the Python code for you to integrate directly into your own software or data pipeline! I can't wait for the next steps!

👋 Hi everyone, For Data Jam episode 11, our topic will be "Flowise - Build LLM Apps Easily". "Flowise is an open source low-code tool for developers to build customized LLM orchestration flow & AI agents" Drag & drop UI to build your customized LLM flow - Website: https://flowiseai.com/ - Github: https://lnkd.in/dsph3WMU What is the event format❓️ Basically, we're going to be exploring and studying a specific topic and hopefully it will create a discussion around that topic. See you on our discord server. If you haven't join the server, check the invitation link on below. Discord link: https://lnkd.in/gca6s8ug For Data Jam event reminder, you can register through this link: https://lnkd.in/gWmbygs4 And we will invite you to our google calendar so you won't miss it! #DataJam - EP11 - Flowise - Build LLM Apps Easily #datascience #machinelearning #artificialintelligence

CAN BRYANT BUILD...an AI app in 1 hour or less? Follow along as he attempts to engineer an application from scratch that can change and morph itself based on prompts from users... (...including an extension to run raw SQL against his database 🙈) Watch the full episode 📺 https://lnkd.in/ePGsQ5SM

Inbox v1 is ready in Midday 🎉 Drag-and-drop files or use your unique email to reconcile everything, saving time and improving accuracy. * Email provided by Postmark 📥 * Uploaded to Supabase storage 🗄️ * Background job via Trigger.dev 🔄 * Vercel AI SDK 🤖 * OCR extraction 👀 An in-depth tech blog coming soon. Share your questions you may have

Today, with AnythingLLM Desktop you can run any open-source LLM and unlock local RAG and AI agents with no code. That's right, a fully running and local Perplexity-level LLM running on your desktop privately complete with web-browsing, scraping, chart generation, and memory management - without writing a line of code. AnythingLLM can work with most LLM platforms like Ollama and LMStudio - which don't even support tool-calling and make them agent-capable. And this is just the first iteration of AnythingLLM's built-in, private, and local agent capabilities. You can get the latest AnythingLLM Desktop version from https://lnkd.in/gf5wqfQY. Don't forget to star us on Github: https://lnkd.in/gvbJF4XC For a more in-depth dive into using AnythingLLM for fully local RAG and AI agents, I made a YouTube video showing just how easy it is. https://lnkd.in/gWSHRkaE

I don't know if you realize how AMAZING this repo is 🤩 Look at this real-world end-to-end LLM pipeline with Airflow 👇 Ask Astro is an LLM-powered chatbot answering Airflow/Astronomer questions. This chatbot runs in production, is publicly available, and OPEN-SOURCE! With this repo, you will discover: ➡️ How to implement LLM pipelines with Airflow ➡️ How to retrieve data from different sources (pipeline) ➡️ How to answer questions from a frontend (pipeline) ➡️ How to build a feedback loop to improve the model (pipeline) and more! It's a crazy amount of work accessible for free here 😍: github[.]com[/]astronomer[/]ask-astro (💡remove the brackets) What better way to learn than looking at the code of a real app? Enjoy ❤️ #dataengineering #airflow #llm #ai

Codestral Mamba by Mistral AI is incredibly fast for questions with a lot of codebase context. With 7B parameters and an Apache 2.0 license, it's a great choice for an entirely local AI code assistant. Try it out now in VS Code and JetBrains with Continue!