LangChain Blog

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

Featured

[Week of 11/27] LangChain Release Notes

3 min read

OpenAI's Bet on a Cognitive Architecture

10 min read

Building LLM-Powered Web Apps with Client-Side Technology

By LangChain 5 min read

Fine-tuning ChatGPT: Surpassing GPT-4 Summarization Performance–A 63% Cost Reduction and 11x Speed Enhancement using Synthetic Data and LangSmith

5 min read

Transforming Mortgage Ops with LangChain & LangSmith

Editor's Note: This post was written by Sasha Aptlin at Aptford through LangChain's Partner Program. Meet Maya, a loan officer at InstaMortgage, whose professional life

4 min read

Extraction Benchmarking

Test confidence_level_similarity json_edit_distance json_schema off_topic_similarity programming_language_similarity question_category sentiment_similarity toxicity_similarity claude-2-xsd-to-xml-5689 0.97 0.

27 min read

[Week of 11/27] LangChain Release Notes

New to LangChain Templates 📁 LangChain Templates are the easiest way to get started building GenAI applications. We have dozens of examples that you can adopt

3 min read

Deconstructing RAG

Context In a recent overview on the state of large language models (LLMs), Karpathy described LLMs as the kernel process of a new kind of

7 min read

Adding Long Term Memory to OpenGPTs

Three weeks ago we launched OpenGPTs, an implementation of OpenAI GPTs and Assistant API but in an open source manner. OpenGPTs allows for implementation of

8 min read

OpenAI's Bet on a Cognitive Architecture

Three weeks ago OpenAI held a highly anticipated developer day. They released a myriad of new features. The two most interesting to me were the

10 min read

LLMs accelerate Adyen's support team through smart-ticket routing and support agent copilot

Challenge As global commerce accelerates, Adyen, a publicly-traded financial technology platform, is helping large companies like Meta, Uber, H&M, and Microsoft achieve their ambitions

Case Studies 2 min read

Sharing LangSmith Benchmarks

The single biggest pain point we hear from developers taking their apps into production is around testing and evaluation. This difficulty is felt more acutely

9 min read

Introducing Dream – an AI no-code tool to build fully functional web apps and components with natural language

I’m Calix, and I’m currently a sophomore at USC Iovine & Young Academy. For my hacker residency at LangChain, I continued working on my

6 min read

Introducing Tuna - A Tool for Rapidly Generating Synthetic Fine-Tuning Datasets

Editor's Note: This post was written by Andrew Kean Gao through LangChain's Student Hacker in Residence Program. Brief Overview Tuna is a no-code tool for

16 min read

Applying OpenAI's RAG Strategies

Context At their demo day, Open AI reported a series of RAG experiments for a customer that they worked with. While evaluation metics will depend

4 min read

"Research Assistant": Exploring UXs Besides Chat

TLDR: We’re excited to announce a new LangChain template for helping with research, heavily inspired by and in collaboration with the GPT Researcher team.

6 min read