pgai


Namepgai JSON
Version 0.1.0 PyPI version JSON
download
home_pageNone
SummaryAI workflows in your PostgreSQL database
upload_time2024-10-24 17:39:06
maintainerNone
docs_urlNone
authorNone
requires_python>=3.10
licenseNone
keywords ai postgres
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls. 
            <p></p>
<div align=center>

# pgai

<h3>pgai brings AI workflows to your PostgreSQL database</h3>

[![Discord](https://img.shields.io/badge/Join_us_on_Discord-black?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/KRdHVXAmkp)
[![Try Timescale for free](https://img.shields.io/badge/Try_Timescale_for_free-black?style=for-the-badge&logo=timescale&logoColor=white)](https://tsdb.co/gh-pgai-signup)

</div>

pgai simplifies the process of building [search](https://en.wikipedia.org/wiki/Similarity_search), and
[Retrieval Augmented Generation](https://en.wikipedia.org/wiki/Prompt_engineering#Retrieval-augmented_generation) (RAG) AI applications with PostgreSQL.

pgai brings embedding and generation AI models closer to the database. With pgai, you can now do the following directly from within PostgreSQL in a SQL query:

- [Create vector embeddings for your data](https://github.com/timescale/pgai/blob/main/docs/vectorizer-quick-start.md).
- Retrieve LLM chat completions from models like [Claude Sonnet 3.5](https://github.com/timescale/pgai/blob/main/docs/anthropic.md), [OpenAI GPT4o](https://github.com/timescale/pgai/blob/main/docs/openai.md), [Cohere Command](https://github.com/timescale/pgai/blob/main/docs/cohere.md), and [Llama 3 (via Ollama)](https://github.com/timescale/pgai/blob/main/docs/ollama.md).
- Reason over your data and facilitate use cases like [classification, summarization, and data enrichment](https://github.com/timescale/pgai/blob/main/docs/openai.md) on your existing relational data in PostgreSQL.

Here's how to get started with pgai:

- **TL;DR**:
  - [Try out automatic embedding vectorization](https://github.com/timescale/pgai/blob/main/docs/vectorizer-quick-start.md): quickly create embeddings using
    a pre-built Docker developer environment with a self-hosted Postgres instance with pgai and our vectorizer worker
    installed. This takes less than 10 minutes!
- **Everyone**: Use pgai in your PostgreSQL database.
  1. [Install pgai](https://github.com/timescale/pgai/blob/main/README.md#installation) in Timescale Cloud, a pre-built Docker image or from source.
  1. Use pgai to integrate AI from your provider:
     - [Ollama](https://github.com/timescale/pgai/blob/main/docs/ollama.md) - configure pgai for Ollama, then use the model to embed, chat complete and generate.
     - [OpenAI](https://github.com/timescale/pgai/blob/main/docs/openai.md) - configure pgai for OpenAI, then use the model to tokenize, embed, chat complete and moderate. This page also includes advanced examples.
     - [Anthropic](https://github.com/timescale/pgai/blob/main/docs/anthropic.md) - configure pgai for Anthropic, then use the model to generate content.
     - [Cohere](https://github.com/timescale/pgai/blob/main/docs/cohere.md) - configure pgai for Cohere, then use the model to tokenize, embed, chat complete, classify, and rerank.
- **Extension contributor**: Contribute to pgai and improve the project.
  - [Develop and test changes to the pgai extension](https://github.com/timescale/pgai/blob/main/DEVELOPMENT.md).
  - See the [Issues tab](https://github.com/timescale/pgai/issues) for a list of feature ideas to contribute.

**Learn more about pgai:** To learn more about the pgai extension and why we built it, read this blog post [pgai: Giving PostgreSQL Developers AI Engineering Superpowers](http://www.timescale.com/blog/pgai-giving-postgresql-developers-ai-engineering-superpowers).

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "pgai",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.10",
    "maintainer_email": null,
    "keywords": "ai, postgres",
    "author": null,
    "author_email": null,
    "download_url": "https://files.pythonhosted.org/packages/cc/0e/0d78aff9ddc4c6068a44e8ced9a8f705e85ba1e1f6c4d3f79165268b5936/pgai-0.1.0.tar.gz",
    "platform": null,
    "description": "<p></p>\n<div align=center>\n\n# pgai\n\n<h3>pgai brings AI workflows to your PostgreSQL database</h3>\n\n[![Discord](https://img.shields.io/badge/Join_us_on_Discord-black?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/KRdHVXAmkp)\n[![Try Timescale for free](https://img.shields.io/badge/Try_Timescale_for_free-black?style=for-the-badge&logo=timescale&logoColor=white)](https://tsdb.co/gh-pgai-signup)\n\n</div>\n\npgai simplifies the process of building [search](https://en.wikipedia.org/wiki/Similarity_search), and\n[Retrieval Augmented Generation](https://en.wikipedia.org/wiki/Prompt_engineering#Retrieval-augmented_generation) (RAG) AI applications with PostgreSQL.\n\npgai brings embedding and generation AI models closer to the database. With pgai, you can now do the following directly from within PostgreSQL in a SQL query:\n\n- [Create vector embeddings for your data](https://github.com/timescale/pgai/blob/main/docs/vectorizer-quick-start.md).\n- Retrieve LLM chat completions from models like [Claude Sonnet 3.5](https://github.com/timescale/pgai/blob/main/docs/anthropic.md), [OpenAI GPT4o](https://github.com/timescale/pgai/blob/main/docs/openai.md), [Cohere Command](https://github.com/timescale/pgai/blob/main/docs/cohere.md), and [Llama 3 (via Ollama)](https://github.com/timescale/pgai/blob/main/docs/ollama.md).\n- Reason over your data and facilitate use cases like [classification, summarization, and data enrichment](https://github.com/timescale/pgai/blob/main/docs/openai.md) on your existing relational data in PostgreSQL.\n\nHere's how to get started with pgai:\n\n- **TL;DR**:\n  - [Try out automatic embedding vectorization](https://github.com/timescale/pgai/blob/main/docs/vectorizer-quick-start.md): quickly create embeddings using\n    a pre-built Docker developer environment with a self-hosted Postgres instance with pgai and our vectorizer worker\n    installed. This takes less than 10 minutes!\n- **Everyone**: Use pgai in your PostgreSQL database.\n  1. [Install pgai](https://github.com/timescale/pgai/blob/main/README.md#installation) in Timescale Cloud, a pre-built Docker image or from source.\n  1. Use pgai to integrate AI from your provider:\n     - [Ollama](https://github.com/timescale/pgai/blob/main/docs/ollama.md) - configure pgai for Ollama, then use the model to embed, chat complete and generate.\n     - [OpenAI](https://github.com/timescale/pgai/blob/main/docs/openai.md) - configure pgai for OpenAI, then use the model to tokenize, embed, chat complete and moderate. This page also includes advanced examples.\n     - [Anthropic](https://github.com/timescale/pgai/blob/main/docs/anthropic.md) - configure pgai for Anthropic, then use the model to generate content.\n     - [Cohere](https://github.com/timescale/pgai/blob/main/docs/cohere.md) - configure pgai for Cohere, then use the model to tokenize, embed, chat complete, classify, and rerank.\n- **Extension contributor**: Contribute to pgai and improve the project.\n  - [Develop and test changes to the pgai extension](https://github.com/timescale/pgai/blob/main/DEVELOPMENT.md).\n  - See the [Issues tab](https://github.com/timescale/pgai/issues) for a list of feature ideas to contribute.\n\n**Learn more about pgai:** To learn more about the pgai extension and why we built it, read this blog post [pgai: Giving PostgreSQL Developers AI Engineering Superpowers](http://www.timescale.com/blog/pgai-giving-postgresql-developers-ai-engineering-superpowers).\n",
    "bugtrack_url": null,
    "license": null,
    "summary": "AI workflows in your PostgreSQL database",
    "version": "0.1.0",
    "project_urls": {
        "Bug Tracker": "https://github.com/timescale/pgai/issues",
        "Documentation": "https://github.com/timescale/pgai/tree/main/docs",
        "Homepage": "https://github.com/timescale/pgai",
        "Repository": "https://github.com/timescale/pgai"
    },
    "split_keywords": [
        "ai",
        " postgres"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "7a8b0362ac807336ba11d49e3afa0f725419d6d780eb204377051f051920efc2",
                "md5": "54068f3117b02f3f4839fc81d72dd7d1",
                "sha256": "139efc0f62818703721d55531b08c8a0190ce554f115837761a0e7a6156a32e7"
            },
            "downloads": -1,
            "filename": "pgai-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "54068f3117b02f3f4839fc81d72dd7d1",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.10",
            "size": 22479,
            "upload_time": "2024-10-24T17:39:05",
            "upload_time_iso_8601": "2024-10-24T17:39:05.588750Z",
            "url": "https://files.pythonhosted.org/packages/7a/8b/0362ac807336ba11d49e3afa0f725419d6d780eb204377051f051920efc2/pgai-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "cc0e0d78aff9ddc4c6068a44e8ced9a8f705e85ba1e1f6c4d3f79165268b5936",
                "md5": "df79960db3871d37c25ecea3fc279aa3",
                "sha256": "91941fd48efd75b6f57da7c505bb9f6ae27d9092ee01c9bed6a84c4d6f05223f"
            },
            "downloads": -1,
            "filename": "pgai-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "df79960db3871d37c25ecea3fc279aa3",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.10",
            "size": 21269,
            "upload_time": "2024-10-24T17:39:06",
            "upload_time_iso_8601": "2024-10-24T17:39:06.782286Z",
            "url": "https://files.pythonhosted.org/packages/cc/0e/0d78aff9ddc4c6068a44e8ced9a8f705e85ba1e1f6c4d3f79165268b5936/pgai-0.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-10-24 17:39:06",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "timescale",
    "github_project": "pgai",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "pgai"
}
None
Elapsed time: 0.35781s