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

JinHai-CN/infinity_new

This branch is 3 commits ahead of, 573 commits behind infiniflow/infinity:main.

Folders and files

NameName
Last commit message
Last commit date
Aug 28, 2024
Aug 27, 2024
Aug 24, 2024
Aug 26, 2024
Aug 15, 2024
Aug 28, 2024
Aug 23, 2024
Aug 28, 2024
Aug 14, 2024
Aug 28, 2024
Aug 28, 2024
Aug 28, 2024
Aug 21, 2024
Aug 28, 2024
May 14, 2024
Jul 24, 2024
Aug 26, 2024
Nov 8, 2023
Aug 24, 2024
Jul 4, 2024
Aug 26, 2024

Repository files navigation

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

🌟 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, 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:

pip install infinity-sdk==0.3.0.dev7
import infinity

# Connect to infinity
infinity_obj = infinity.connect("/path/to/save/to")
db = infinity_obj.get_database("default_db")
table = db.create_table("my_table", {"num": {"type": "integer"}, "body": {"type": "varchar"}, "vec": {"type": "vector, 4, float"}})
table.insert([{"num": 1, "body": "unnecessary and harmful", "vec": [1.0, 1.2, 0.8, 0.9]}])
table.insert([{"num": 2, "body": "Office for Harmful Blooms", "vec": [4.0, 4.2, 4.3, 4.5]}])
res = table.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 a standalone Infinity server and access it remotely:

See Deploy infinity server.

🛠️ Build from Source

See Build from Source.

💡 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

Releases

No releases published

Packages

No packages published

Languages

  • C++ 94.6%
  • Python 2.4%
  • Yacc 1.3%
  • CMake 0.6%
  • C 0.4%
  • Jupyter Notebook 0.3%
  • Other 0.4%