Skip to content
SPECIFICTION
Get listed

Infinity

infiniflow.org

WindowsmacOSLinuxAPISelf-hosted
Visit infiniflow.org
Spec score 7.8 #14 of 27 in Vector Databases

Spec sheet

Purpose
Infinity describes itself as an AI-native database for LLM applications that provides hybrid search.Read 8 Oct 2026 · infiniflow.org
Deployment
The quickstart documents deploying Infinity with Docker, while the binary guide offers Linux packages in deb, rpm, or tgz formats.Read 8 Oct 2026 · infiniflow.org
License
The project’s GitHub repository lists the Apache-2.0 license.Read 8 Oct 2026 · github.com
API options
The docs provide Python and HTTP API references, and the homepage says Infinity has a Python API.Read 8 Oct 2026 · infiniflow.org
Cluster storage
The cluster guide says supported shared storage is MinIO and describes a cluster with one leader, up to four followers, and learner nodes.Read 8 Oct 2026 · infiniflow.org
Community
The homepage links to Infinity's GitHub repository and Discord community.Read 8 Oct 2026 · infiniflow.org
Community support
The homepage links to the project’s X account, GitHub, and Discord community.Read 8 Oct 2026 · infiniflow.org
Data types
Infinity supports data types including strings, numerics, and vectors.Read 8 Oct 2026 · infiniflow.org
Developer interface
The homepage describes an intuitive Python API, and the docs provide a Python SDK and HTTP API reference.Read 8 Oct 2026 · infiniflow.org
Full-text search
The search guide says full-text indexing requires specifying a tokenizer or analyzer, and most built-in analyzers require resource files.Read 8 Oct 2026 · infiniflow.org
Intended use
The maker describes Infinity as designed for retrieval-augmented generation applications.Read 8 Oct 2026 · infiniflow.org
Performance
The homepage states 0.1 milliseconds query latency and up to 15K QPS on million-scale vector datasets.Read 8 Oct 2026 · infiniflow.org
Performance claims
The homepage claims 0.1 millisecond query latency and up to 15K QPS on million-scale vector datasets.Read 8 Oct 2026 · infiniflow.org
Python API
The homepage describes an intuitive Python API, and the docs show installing the client with pip.Read 8 Oct 2026 · infiniflow.org
Ranking
Its listed rerankers include RRF, weighted sum, and ColBERT.Read 8 Oct 2026 · infiniflow.org
Rerankers
The homepage names RRF, weighted sum, and ColBERT as supported rerankers.Read 8 Oct 2026 · infiniflow.org
Search
It supports hybrid search across dense embeddings, sparse embeddings, tensors, and full text, with filtering.Read 8 Oct 2026 · infiniflow.org
Search constraints
The search guide says conditional filters must work through an index; secondary-index filters support logical comparisons and membership expressions.Read 8 Oct 2026 · infiniflow.org
Search methods
It supports hybrid search across dense embeddings, sparse embeddings, tensors, and full text, as well as filtering.Read 8 Oct 2026 · infiniflow.org
Supported environments
The quickstart lists Linux, macOS, and Windows 10 or later with WSL or WSL2; it specifies x86_64 with AVX2 support and Python 3.10 or later.Read 8 Oct 2026 · infiniflow.org
Tensor guidance
The search guide cautions that tensor search can have significant storage overhead and recommends tensors for reranking in hybrid search.Read 8 Oct 2026 · infiniflow.org
Vector search
The search guide says HNSW is aimed at faster dense-vector search and IVF uses less memory; incoming streaming vectors are searched by brute force alongside indexed results.Read 8 Oct 2026 · infiniflow.org
Version requirement
The Python API documentation says client and server versions must match exactly in client-server mode.Read 8 Oct 2026 · infiniflow.org

Where Specifiction places it

Alternatives to InfinityAll alternatives →