title | description |
---|---|
Azure Cosmos DB Vector Search with OpenAI API (Python) |
Demonstrating Azure Cosmos DB integration with OpenAI's API for vector-based search using Python. Explore practical examples and usage instructions. |
This project showcases the fusion of Azure Cosmos DB with OpenAI's API, enabling Python-driven vector-based search capabilities. By synergizing the strengths of Azure Cosmos DB and OpenAI, you can establish a resilient and effective system for performing sophisticated similarity searches within your data.
This repository also includes practical examples of Vector Search utilizing three Azure Cosmos DB APIs and Python.
- Wrangling raw CSV data into enhanced JSON documents with calculated and normalized values
- Vectorizing data with Azure OpenAI
- Vector Searching this data with the Azure Cosmos DB for MongoDB vCore API
- Vector Searching this data with the Azure Cosmos DB NoSQL API, with Azure Cognitive Search
- Vector Searching this data with the Azure Cosmos DB PostgreSQL API, with the pgvector extension
- Python 3.x
- Python 3.11.6 is recommended, not 3.12.x
- See https://www.python.org/downloads/release/python-3116/
- Azure PaaS Services: OpenAI, Cosmos DB account(s), Cognitive Search
To make the most of this project's capabilities, follow these steps:
- Clone this repository to your local environment.
- Provision your Azure PaaS services
- Configure your Workstation or VM
- Vectorize the provided data with OpenAI
- Explore the provided documentation for a range of usage examples.
- For each example, refer to the detailed instructions in the documentation to install and run them successfully.
Feel free to experiment with and adapt the code to your specific use cases and requirements. If you have any questions or need assistance, don't hesitate to create an issue on the GitHub repository.
Contributions to enhance this repository are welcome! Feel free to submit pull requests for bug fixes, additional features, or improvements.
This project is licensed under the MIT License.
This repository is not officially affiliated with Microsoft Azure or OpenAI. It serves as a community-driven resource to explore the capabilities of Azure Cosmos DB and OpenAI's API for vector-based search.
Willie Mays making "The Catch", with amazing search, 1954 World Series