infiniflow/infinity

What is it?

Key features

• 01Hybrid search combining dense vector, sparse vector, tensor and full-text queries with filtering.
• 02Rerankers including RRF, weighted sum and ColBERT.
• 03Python SDK for embedding the client in AI workflows.
• 04HTTP API alongside the Python interface.
• 05Single-binary server with no external dependencies, deployable via Docker.

Use cases

• Retrieval backend for RAG pipelines that need both semantic and keyword search.
• Semantic search over documents or product catalogs with metadata filters.
• Recommendation systems that combine embedding similarity with structured conditions.
• Prototyping LLM applications with an embedded Python-accessible database.

Quick start

1. 1

   Create the data directory for the Infinity server

   sudo mkdir -p /var/infinity && sudo chown -R $USER /var/infinity
2. 2

   Pull the Infinity server Docker image

   docker pull infiniflow/infinity:nightly
3. 3

   Start the Infinity server container

   docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightly
4. 4

   Install the Infinity Python client

   pip install infinity-sdk==0.7.5

Things to know

• !Requires an x86_64 CPU with AVX2 support.
• !Windows users must run it through WSL or WSL2 with Docker.

In collections

Topics

FAQ

What is infinity?

An AI-native database for LLM applications, offering hybrid search over dense vectors, sparse vectors, tensors and full-text. Infinity is a database built for LLM and RAG applications. It stores structured data alongside dense embeddings, sparse embeddings, tensors (multi-vector) and full-text content, and runs queries that combine these search types with filters in a single request.

Is infinity free to use? What license does it have?

infinity is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.

Is infinity still maintained?

Actively maintained. The last commit to infinity was on Nov 5, 2026.

What can I use infinity for?

Retrieval backend for RAG pipelines that need both semantic and keyword search. Semantic search over documents or product catalogs with metadata filters. Recommendation systems that combine embedding similarity with structured conditions. Prototyping LLM applications with an embedded Python-accessible database.

How do I install infinity?

Create the data directory for the Infinity server: sudo mkdir -p /var/infinity && sudo chown -R $USER /var/infinity Pull the Infinity server Docker image: docker pull infiniflow/infinity:nightly Start the Infinity server container: docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightly Install the Infinity Python client: pip install infinity-sdk==0.7.5

Where can I get infinity?

The source code and installation instructions are on GitHub: https://github.com/infiniflow/infinity