LangChain Blog (Page 10)

How Mendable leverages LangSmith to debug Tools & Actions

Editor's Note: this blog is from Nicolas Camara, CTO @ Mendable. Mendable.ai is a platform helping enterprise teams answer technical questions with AI.

6 min read

LangGraph: Multi-Agent Workflows

Links * Python Examples * JS Examples * YouTube Last week we highlighted LangGraph - a new package (available in both Python and JS) to better enable creation

By LangChain 6 min read

LangGraph

TL;DR: LangGraph is module built on top of LangChain to better enable creation of cyclical graphs, often needed for agent runtimes. * Python Repo * Python

By LangChain 7 min read

Build and deploy a RAG app with Pinecone Serverless

Key Links * Repo: https://github.com/langchain-ai/pinecone-serverless * Video: https://youtu.be/EhlPDL4QrWY Context LLMs are unlocking a new era of generative AI applications, becoming

By LangChain 3 min read

Ally Financial Collaborates with LangChain to Deliver Critical Coding Module to Mask Personal Identifying Information in a Compliant and Safe Manner

Ally Financial, the largest digital-only bank in the US and a leading auto lender, has recently collaborated with LangChain to release the first initial coding

Case Studies 5 min read

LangChain v0.1.0

Today we’re excited to announce the release of langchain 0.1.0, our first stable version. It is fully backwards compatible, comes in both

By LangChain 10 min read

LangChain State of AI 2023

In 2023 we saw an explosion of interest in Generative AI upon the heels of ChatGPT. All companies - from startups to enterprises - were

7 min read

Benchmarking Agent Tool Use

Agents may be the “killer” LLM app, but building and evaluating agents is hard. Function calling is a key skill for effective tool use, but

12 min read

How Rubric Labs and Graphite leveraged LLMs to create personalized videos at scale

How Rubric Labs and Graphite generated personalized, unique GitHub Wrapped 2023 videos for each user.

6 min read

Benchmarking RAG on tables

Key links LangChain public benchmark evaluation notebooks: * Long context LLMs here * Chunk size tuning here * Multi vector with ensemble here Motivation Retrieval augmented generation (RAG)

5 min read

Towards LangChain 0.1: LangChain-Core and LangChain-Community

The goal of LangChain has always been to make it as easy as possible to develop context-aware reasoning applications with LLMs. LangChain started as a

14 min read

Multi-modal RAG on slide decks

Key Links * LangChain public benchmark evaluation notebooks * LangChain template for multi-modal RAG on presentations Motivation Retrieval augmented generation (RAG) is one of the most important

5 min read