Skip to main content
Version: v0.3.0

Quickstart

Prerequisites​

  • CPU: x86_64 with AVX2
  • OS: Linux with glibc ≥ 2.17
  • Python: Python 3.10+

Install Infinity locally using pip​

Infinity, also available as a Python module, eliminates the need for a separate back-end server and all the complex communication settings. Using pip install and import infinity, you can quickly build a local AI application in Python, leveraging the world's fastest and the most powerful RAG database:

  1. Install Infinity as a Python module: 
    pip install infinity-sdk==0.3.0
  2. Use Infinity to conduct a KNN search: 
    import infinity

    # Connect to infinity
    infinity_object = infinity.connect("/path/to/save/to")
    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)

Deploy Infinity as a separate server​

If you wish to deploy Infinity with the server and client as separate processes, see Deploy infinity server.

🛠️ Build from Source​

See Build from Source.

Try our Python examples​

Python API reference​

For detailed information about Infinity's Python API, see the Python API Reference.