The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense embedding, sparse embedding, tensor and full-text
Infinity is a cutting-edge AI-native database that provides a wide range of search capabilities for rich data types such as dense vector, sparse vector, tensor, full-text, and structured data. It provides robust support for various LLM applications, including search, recommenders, question-answering, conversational AI, copilot, content generation, and many more RAG (Retrieval-augmented Generation) applications.
Infinity comes with high performance, flexibility, ease-of-use, and many features designed to address the challenges facing the next-generation AI applications:
- Achieves 0.1 milliseconds query latency and 15K+ QPS on million-scale vector datasets.
- Achieves 1 millisecond latency and 12K+ QPS in full-text search on 33M documents.
See the Benchmark report for more information.
- Supports a hybrid search of dense embedding, sparse embedding, tensor, and full text, in addition to filtering.
- Supports several types of rerankers including RRF, weighted sum and ColBERT.
Supports a wide range of data types including strings, numerics, vectors, and more.
- Intuitive Python API. See the Python API
- A single-binary architecture with no dependencies, making deployment a breeze.
- Embedded in Python as a module and friendly to AI developers.
This section provides guidance on deploying the Infinity database using Docker, with the client and server as separate processes.
- CPU: x86_64 with AVX2 support.
- OS:
- Linux with glibc 2.17+.
- Windows 10+ with WSL/WSL2.
- MacOS
- Python: Python 3.10+.
sudo mkdir -p /var/infinity && sudo chown -R $USER /var/infinity
docker pull infiniflow/infinity:nightly
docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightlyIf you are on Windows 10+, you must enable WSL or WSL2 to deploy Infinity using Docker. Suppose you've installed Ubuntu in WSL2:
-
Follow this to enable systemd inside WSL2.
-
Install docker-ce according to the instructions here.
-
If you have installed Docker Desktop version 4.29+ for Windows: Settings > Features in development, then select Enable host networking.
-
Pull the Docker image and start Infinity:
sudo mkdir -p /var/infinity && sudo chown -R $USER /var/infinity docker pull infiniflow/infinity:nightly docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightly
pip install infinity-sdk==0.6.0.dev3
import infinity
infinity_obj = infinity.connect(infinity.NetworkAddress("<SERVER_IP_ADDRESS>", 23817))
db_object = infinity_object.get_database("default_db")
table_object = db_object.create_table("my_table", {"num": {"type": "integer"}, "body": {"type": "varchar"}, "vec": {"type": "vector, 4, float"}})
table_object.insert([{"num": 1, "body": "unnecessary and harmful", "vec": [1.0, 1.2, 0.8, 0.9]}])
table_object.insert([{"num": 2, "body": "Office for Harmful Blooms", "vec": [4.0, 4.2, 4.3, 4.5]}])
res = table_object.output(["*"])
.match_dense("vec", [3.0, 2.8, 2.7, 3.1], "float", "ip", 2)
.to_pl()
print(res)If you wish to deploy Infinity using binary with the server and client as separate processes, see the Deploy infinity using binary guide.
See the Build from Source guide.
See the Infinity Roadmap 2025