Skip to main content

Ctrl+K

LangChain Benchmarks 0.0.12

🦜💯 LangChain Benchmarks

Introduction

Getting Started
Model Registry
Datasets

Tool Usage

Introduction
Relational Data
Multiverse Math
Typewriter: Single Tool
Typewriter: 26 Tools
Benchmark All Tasks

Extraction

Introduction
Email Extraction
Chat Extraction
Extracting high-cardinality categoricals

RAG

Introduction
Q&A over LangChain Docs
Semi-structured RAG
Semi-structured eval: Chunk size tuning
Semi-structured eval: Long-context
Semi-structured eval: Multi vector
Multi-modal eval: Baseline
Multi-modal eval: GPT-4 w/ multi-modal embeddings and multi-vector retriever
Evaluating RAG Architectures on Benchmark Tasks

Benchmarking Without LangSmith

Running Locally

Repository
Open issue

Search

Ctrl+K

By Langchain AI

© Copyright 2023, Langchain AI.