LLM apps involve complex decision flows that produce a ✨ton✨ of data. Understanding that data can be the key to transforming a prototype into a production-ready GenAI app. 🚀

And there's only one database you need to power that understanding - ClickHouse!

But don't take our

🚦🐘 Neon Postgres Vectorstore 🚦🐘

Neon - Serverless Postgres has awesome “serverless” Postgres scaling capabilities.

You can now use them in RAG pipelines in LangChain 🦜🔗 JS/TS as a vectorstore!

Install the latest community package to try it.

h/t Ishan Anand

js.langchain.com/docs/integrati…

⚡ LangSmith Evaluations: RAG Evaluation (Answer Correctness) ⚡

Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith.

This is the 12th video in our series, focusing on

Local RAG Explained with Unstructured and LangChain

Complete video: youtu.be/watch?v=7ru0oj…
Code: github.com/katanaml/sparr…

In this tutorial, I do a code walkthrough and demonstrate how to implement the RAG pipeline using Unstructured, LangChain, and Pydantic for processing

If the rise of LLMs caught you by surprise, here's your chance to get a preview of what's likely to be the next monumental jump in AI capabilities:

LLM-backed agents that use software tools

In this video, I'll walk you through the concepts and code of building an LLM-backed

Dialoqbase v1.8.0 has been released with huge improvements and features.

Here is an example using the llama3 model via .Fireworks AI API to chat on a GitHub repo.

Powered by LangChain

How we built it: WikiChat, a RAG chatbot based on trending Wikipedia entries.

Check out technical blog to see how we leveraged DataStax Astra DB, LangChain, and @Vercel.

#AIChatbot #RetrievalAugmentedGeneration #VectorDB dtsx.io/3HreGU6

Have you ever wanted to use a LangChain Agent, but powered by a model other than OpenAI?

That is now possible

The new Tool Calling Agent means you can power your agents using
- Anthropic
- Mistral AI
- Fireworks AI
- Vertex AI

with support for others like cohere

░D░A░T░A░F░L░Y░W░H░E░E░L

⚡️LangSmith Webhooks w/ Modal

LangSmith automations help you build a data flywheel by taking actions on data. By default you can move data to datasets or annotation queue

With Modal you can set up a webhook to perform arbitrary actions

docs.smith.langchain.com/monitoring/faq…

💪Empowering Development with FlowTestAI: Bridging APIs and LLMs for Enhanced Testing and Privacy

Interacting with APIs is a big use case for LLMs. Excited to highlight a fun blog from FlowTestAI showing how they built a prod platform for this

blog.langchain.dev/empowering-dev…

cool experimentations with generative ui

👨🏼‍🔬experimenting with ai rendered ui

🚀Easiest way to Build your OpenAI like chatGPT message website with Streamlit

Uses LangChain, OpenAI api, and streamlit to create a ChatGPT clone

Great place to get started if you're just exploring building with LLMs

youtube.com/watch?v=mGpXF0…

🦜⚒️LangSmith 101, Boost your Responsible AI with LangChain's Powerful framework

A good introductory video in LangSmith

Learn how to trace, log, test, and evaluate your applications!

youtube.com/watch?v=p03YrC…

✒️Build an AI-powered blogging platform (Next.js, Langchain & CopilotKit)

In this article, you will learn how to build an AI-powered blogging platform that can search the web and research any topic for a blog article

dev.to/copilotkit/how…

🦜 Build a serverless AI chat with RAG using LangChain.js

This shows how LangChain.js, Ollama with Mistral 7B model and Azure can be used together to build a serverless chatbot that can answer questions using a RAG pipeline

techcommunity.microsoft.com/t5/apps-on-azu…

✂️But, How is Chunking Done?

To create Better RAG applications, you need to know how to split or chunk the documents so you preserve the content while asking questions.

Data Science Basics shows how to do this with LangChain

youtube.com/watch?v=tMwdl9…

🦙How to chat with your PDFs using local Large Language Models [Ollama RAG]

Covers loading PDFs with Unstructured, splitting that text data with RecursiveCharacterTextSplitter, creating embeddings with Ollama

youtube.com/watch?v=ztBJqz…

😍 The recording from our Flow Engineering webinar with Harrison Chase and Itamar Friedman is up!

youtube.com/watch?v=eBjxz7…

'Flow Engineering' is a term that has been gaining in popularity recently. The first time it was mentioned as term was in CodiumAI paper on AlphaCodium, where they