✨ Join the Context Engineers Discord community for an exclusive talk with the ZeroEntropy founders this Friday!

testing test

Nov 18, 2025

\mathcal{L} = -\sum_{i, j}{w_{ij}\log(\frac{p_{i}}{p_{i}+p_{j}})} = \sum_{i, j}{w_{ij}\log(1+e^{e_j-e_i})} \; .

Get started with

Our retrieval engine runs autonomously with the

accuracy of a human-curated system.

Our retrieval engine runs autonomously with the

accuracy of a human-curated system.

Our retrieval engine runs autonomously with the

accuracy of a human-curated system.

Start Now

View Docs

GitHub

Discord

Slack

Enterprise

LegalBench-RAG, the First Open-Source Retrieval Benchmark for the Legal Domain

Nov 29, 2024

LegalBench-RAG is the first open-source benchmark for legal RAG retrieval—6,800+ queries, 79M+ characters, human-annotated spans. Evaluate legal AI today.

LegalBench-RAG, the First Open-Source Retrieval Benchmark for the Legal Domain

Nov 29, 2024

LegalBench-RAG is the first open-source benchmark for legal RAG retrieval—6,800+ queries, 79M+ characters, human-annotated spans. Evaluate legal AI today.

LlamaChunk: A General and Cost Efficient Approach to Semantic Chunking

Dec 1, 2024

Learn how LlamaChunk delivers fast, accurate semantic chunking for RAG—outperforming regex and embedding methods with LLM-guided document splitting.

LlamaChunk: A General and Cost Efficient Approach to Semantic Chunking

Dec 1, 2024

Learn how LlamaChunk delivers fast, accurate semantic chunking for RAG—outperforming regex and embedding methods with LLM-guided document splitting.

AGI requires better retrieval, not just better LLMs

Dec 2, 2024

AGI needs more than LLMs—it needs smarter retrieval. Learn how to identify failure modes in RAG and evaluate search accuracy with ZeroEntropy’s benchmarks.

AGI requires better retrieval, not just better LLMs

Dec 2, 2024

AGI needs more than LLMs—it needs smarter retrieval. Learn how to identify failure modes in RAG and evaluate search accuracy with ZeroEntropy’s benchmarks.

LegalBench-RAG, the First Open-Source Retrieval Benchmark for the Legal Domain

Nov 29, 2024

LegalBench-RAG is the first open-source benchmark for legal RAG retrieval—6,800+ queries, 79M+ characters, human-annotated spans. Evaluate legal AI today.

LlamaChunk: A General and Cost Efficient Approach to Semantic Chunking

Dec 1, 2024

Learn how LlamaChunk delivers fast, accurate semantic chunking for RAG—outperforming regex and embedding methods with LLM-guided document splitting.

Abstract image of a dark background with blurry teal, blue, and pink gradients.

testing test

SHARE

Get started with

RELATED ARTICLES

LegalBench-RAG, the First Open-Source Retrieval Benchmark for the Legal Domain

LegalBench-RAG, the First Open-Source Retrieval Benchmark for the Legal Domain

LlamaChunk: A General and Cost Efficient Approach to Semantic Chunking

LlamaChunk: A General and Cost Efficient Approach to Semantic Chunking

AGI requires better retrieval, not just better LLMs

AGI requires better retrieval, not just better LLMs

LegalBench-RAG, the First Open-Source Retrieval Benchmark for the Legal Domain

LlamaChunk: A General and Cost Efficient Approach to Semantic Chunking