LangChain

GPTeam: A multi-agent simulation

Editor's Note: This is another edition in our series of guest posts highlighting novel applications of LangChain. After the Generative Agents paper was released, there was a flurry of open source projects rushing to incorporate some of the key ideas. GPTeam was one of the most impressive ones we saw,

Going Beyond Chatbots: How to Make GPT-4 Output Structured Data Using LangChain

By Jacob Lee Over the past few months, I had the opportunity to do some cool exploratory work for a client that integrated LLMs like GPT-4 and Claude into their internal workflow, rather than exposing them through a chat interface. The general idea was to take some input data, analyze

Auto-Evaluation of Anthropic 100k Context Window

Lance Martin Retrieval Architectures LLM question answering (Q+A) typically involves retrieval of documents relevant to the question followed by synthesis of the retrieved chunks into an answer by an LLM.  In practice, the retrieval step is necessary because the LLM context window is limited relative to the size of

Rebuff: Detecting Prompt Injection Attacks

[Editor's Note]: we're excited to highlight a guest blog by Willem Pienaar. As more and more LangChains make their way into production, we're getting an increased amount of questions about the security and privacy of these systems. We did a webinar on this topic a few weeks ago, and the

Plan-and-Execute Agents

TL;DR: We’re introducing a new type of agent executor, which we’re calling “Plan-and-Execute”. This is to contrast against the previous types of agent we supported, which we’re calling “Action” agents. Plan-and-Execute agents are heavily inspired by BabyAGI and the recent Plan-and-Solve paper. We think Plan-and-Execute is

Feature Stores and LLMs

Editor's note: big thank you to Willem Pienaar (Feast), Mike Del Balso (Tecton), and Simba Khadder (FeatureForm) for their comments and help on this post. LLMs represent a new paradigm of AI. There is a big open question of how many of the tools and services that were useful for

Structured Tools

TL;DR: we're introducing a new abstraction to allow for usage of more complex tools. While previous tools took in a single string input, new tools can take in an arbitrary number of inputs of arbitrary types. We are also introducing a new agent class that works well with these

Auto-Evaluator Opportunities

Editor's Note: this is a guest blog post by Lance Martin. TL;DR We recently open-sourced an auto-evaluator tool for grading LLM question-answer chains. We are now releasing an open source, free to use hosted app and API to expand usability. Below we discuss a few opportunities to further improve

Callbacks Improvements

TL;DR: We're announcing improvements to our callbacks system, which powers logging, tracing, streaming output, and some awesome third-party integrations. This will better support concurrent runs with independent callbacks, tracing of deeply nested trees of LangChain components, and callback handlers scoped to a single request (which is super useful for

Unleashing the power of AI Collaboration with Parallelized LLM Agent Actor Trees

Editor's note: the following is a guest blog post from Cyrus at Shaman AI. We use guest blog posts to highlight interesting and novel applciations, and this is certainly that. There's been a lot of talk about agents recently, but most have been discussions around a single agent. If multiple

Gradio & LLM Agents

Editor's note: this is a guest blog post from Freddy Boulton, a software engineer at Gradio. We're excited to share this post because it brings a large number of exciting new tools into the ecosystem. Agents are largely defined by the tools they have, so to be able to equip

RecAlign - The smart content filter for social media feed

[Editor's Note] This is a guest post by Tian Jin. We are highlighting this application as we think it is a novel use case. Specifically, we think recommendation systems are incredibly impactful in our everyday lives and there has not been a ton of discourse on how LLMs will impact

Improving Document Retrieval with Contextual Compression

Note: This post assumes some familiarity with LangChain and is moderately technical. 💡 TL;DR: We’ve introduced a new abstraction and a new document Retriever to facilitate the post-processing of retrieved documents. Specifically, the new abstraction makes it easy to take a set of retrieved documents and extract from them

Autonomous Agents & Agent Simulations

Over the past two weeks, there has been a massive increase in using LLMs in an agentic manner. Specifically, projects like AutoGPT, BabyAGI, CAMEL, and Generative Agents have popped up. The LangChain community has now implemented some parts of all of those projects in the LangChain framework. While researching and

AI-Powered Medical Knowledge: Revolutionizing Care for Rare Conditions

[Editor's Note]: This is a guest post by Jack Simon, who recently participated in a hackathon at Williams College. He built a LangChain-powered chatbot focused on appendiceal cancer, aiming to make specialized knowledge more accessible to those in need. If you are interested in building a chatbot for another rare

Auto-Eval of Question-Answering Tasks

By Lance Martin Context LLM ops platforms, such as LangChain, make it easy to assemble LLM components (e.g., models, document retrievers, data loaders) into chains. Question-Answering is one of the most popular applications of these chains. But it is often not always obvious to determine what parameters (e.g.

Announcing LangChainJS Support for Multiple JS Environments

TLDR: We're announcing support for running LangChain.js in browsers, Cloudflare Workers, Vercel/Next.js, Deno, Supabase Edge Functions, alongside existing support for Node.js ESM and CJS. See install/upgrade docs and breaking changes list. Context Originally we designed LangChain.js to run in Node.js, which is the

LangChain x Supabase

Supabase is holding an AI Hackathon this week. Here at LangChain we are big fans of both Supabase and hackathons, so we thought this would be a perfect time to highlight the multiple ways you can use LangChain and Supabase together. The reason we like Supabase so much is that

Announcing our $10M seed round led by Benchmark

It was only six months ago that we released the first version of LangChain, but it seems like several years. When we launched, generative AI was starting to go mainstream: stable diffusion had just been released and was captivating people’s imagination and fueling an explosion in developer activity, Jasper

Custom Agents

One of the most common requests we've heard is better functionality and documentation for creating custom agents. This has always been a bit tricky - because in our mind it's actually still very unclear what an "agent" actually is, and therefor what the "right" abstractions for them may be. Recently,

Retrieval

TL;DR: We are adjusting our abstractions to make it easy for other retrieval methods besides the LangChain VectorDB object to be used in LangChain. This is done with the goals of (1) allowing retrievers constructed elsewhere to be used more easily in LangChain, (2) encouraging more experimentation with alternative

LangChain + Zapier Natural Language Actions (NLA)

We are super excited to team up with Zapier and integrate their new Zapier NLA API into LangChain, which you can now use with your agents and chains. With this integration, you have access to the 5k+ apps and 20k+ actions on Zapier's platform through a natural language API interface.

Evaluation

Evaluation of language models, and by extension applications built on top of language models, is hard. With recent model releases (OpenAI, Anthropic, Google) evaluation is becoming a bigger and bigger issue. People are starting to try to tackle this, with OpenAI releasing OpenAI/evals - focused on evaluating OpenAI models.

LLMs and SQL

Francisco Ingham and Jon Luo are two of the community members leading the change on the SQL integrations. We’re really excited to write this blog post with them going over all the tips and tricks they’ve learned doing so. We’re even more excited to announce that we’

Origin Web Browser

[Editor's Note]: This is the second of hopefully many guest posts. We intend to highlight novel applications building on top of LangChain. If you are interested in working with us on such a post, please reach out to harrison@langchain.dev. Authors: Parth Asawa (pgasawa@), Ayushi Batwara (ayushi.batwara@), Jason