pgai
pgai copied to clipboard
timescale
A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL
### **THIS IS AN EXPERIMENT** We would like to avoid long-lived feature branches and the git headaches that entails. Yet some features take a while to mature to a level...
Bumps the dependencies group with 6 updates in the /projects/pgai directory: | Package | From | To | | --- | --- | --- | | [ruff](https://github.com/astral-sh/ruff) | `0.6.9` |...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
:robot: Release ready --- ## [0.1.1](https://github.com/timescale/pgai/compare/pgai-v0.1.0...pgai-v0.1.1) (2024-11-01) ### Miscellaneous * add logo to pgai pypi ([3366368](https://github.com/timescale/pgai/commit/336636872b39ce371d801f4ffacd1ea57e67b9f5)) * separate the dev/test/build between the projects ([183be9e](https://github.com/timescale/pgai/commit/183be9e82632287c35081c4eefd81ff99d4bd4ba)) --- This PR was generated with...
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "github-actions[bot] avatar"){kind=avatar}
### What problem does the new feature solve? jina-clip-v1 is the best multi-modal embedding model now. ### What does the feature do? It can be used to build better image...
Using the latest development branch, I noticed in testing the OpenAI endpoints (chat_completion) that there is an issue with canceling the request if the user cancels the query for example....
Adding support to OCI Gen AI Services https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/ Just two simple functions: oci_list_models -> Returns available model per region/compartment oci_embed -> Return a vector from a string
We ported the vectorizer code from an internal repository, that tested against the lambda_handler. The tests and the lambda handler were ported as is, this enabled us to move everything...
