Skip to content

The AI-native database built for LLM applications, providing incredibly fast vector and full-text search

License

Notifications You must be signed in to change notification settings

writinwaters/infinity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

13d3f9b · Dec 9, 2024
Nov 27, 2024
Nov 23, 2024
Nov 23, 2024
Aug 26, 2024
Dec 7, 2024
Dec 9, 2024
Dec 6, 2024
Nov 7, 2024
Dec 7, 2024
Nov 22, 2024
Dec 9, 2024
Dec 6, 2024
Nov 2, 2024
Dec 4, 2024
Nov 29, 2024
May 14, 2024
Oct 31, 2024
Nov 15, 2024
Nov 8, 2024
Oct 9, 2024
Nov 8, 2023
Dec 9, 2024
Sep 2, 2024
Nov 23, 2024

Repository files navigation

Infinity logo

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.

⚡️ Performance

Infinity performance comparison

🌟 Key Features

Infinity comes with high performance, flexibility, ease-of-use, and many features designed to address the challenges facing the next-generation AI applications:

🚀 Incredibly fast

  • 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.

🔮 Powerful search

  • 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.

🍔 Rich data types

Supports a wide range of data types including strings, numerics, vectors, and more.

🎁 Ease-of-use

  • 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.

🎮 Get Started

Infinity supports two working modes, embedded mode and client-server mode. Infinity's embedded mode enables you to quickly embed Infinity into your Python applications, without the need to connect to a separate backend server. The following shows how to operate in embedded mode:

pip install infinity-embedded-sdk==0.5.0.dev5

Use Infinity to conduct a dense vector search:

import infinity_embedded

# Connect to infinity
infinity_object = infinity_embedded.connect("/absolute/path/to/save/to")
# Retrieve a database object named default_db
db_object = infinity_object.get_database("default_db")
# Create a table with an integer column, a varchar column, and a dense vector column
table_object = db_object.create_table("my_table", {"num": {"type": "integer"}, "body": {"type": "varchar"}, "vec": {"type": "vector, 4, float"}})
# Insert two rows into the table
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]}])
# Conduct a dense vector search
res = table_object.output(["*"])
                  .match_dense("vec", [3.0, 2.8, 2.7, 3.1], "float", "ip", 2)
                  .to_pl()
print(res)

🔧 Deploy Infinity in client-server mode

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

🔧 Build from Source

See the Build from Source guide.

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

📚 Document

📜 Roadmap

See the Infinity Roadmap 2024

🙌 Community

About

The AI-native database built for LLM applications, providing incredibly fast vector and full-text search

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • C++ 84.7%
  • Python 11.9%
  • Yacc 1.1%
  • TypeScript 1.0%
  • CMake 0.4%
  • Shell 0.4%
  • Other 0.5%