By LangChain - LangChain Blog (Page 4)

Benchmarking Question/Answering Over CSV Data

This is a bit of a longer post. It's a deep dive on question-answering over tabular data. We discuss (and use) CSV data

By LangChain 13 min read

GPT Researcher x LangChain

Here at LangChain we think that web research is fantastic use case for LLMs. So much so that we wrote a blog on it about

By LangChain 3 min read

Making Data Ingestion Production Ready: a LangChain-Powered Airbyte Destination

A big focus of ours over the past few months has been enabling teams to go from prototype to production. To take apps they developed

3 min read

Conversational Retrieval Agents

TL;DR: There have been several emerging trends in LLM applications over the past few months: RAG, chat interfaces, agents. Our newest functionality - conversational

4 min read

LangChain Expression Language

TL;DR: * We’re excited to announce a new syntax to create chains with composition. This comes along with a new interface that supports batch,

5 min read

Goodbye CVEs, Hello `langchain_experimental`

One of the things that LangChain seeks to enable is connecting language models to external sources of data and computation. This allows language models to

2 min read

Automating Web Research

Key Links * Web Researcher Repo * New LangChain Retriever and Documentation * Hosted Streamlit App Motivation Web research is one of the killer LLM applications: Greg Kamradt

4 min read

Announcing LangSmith, a unified platform for debugging, testing, evaluating, and monitoring your LLM applications

LangChain exists to make it as easy as possible to develop LLM-powered applications. We started with an open-source Python package when the main blocker for

8 min read

Analyzing User Interactions with LLMs to Improve our Documentation

Introduction We're strongly committed to consistently enhancing our documentation and its navigability. Using Mendable, a AI-enabled chat application, users can search our documentation

3 min read

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

4 min read

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

3 min read

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

4 min read