Description

This PR adds TwelveLabs model provider integration to the Strands SDK, enabling both semantic video search and video understanding capabilities. The implementation provides two specialized model providers:

• TwelveLabsSearchModel: Semantic video search using the Marengo model
• TwelveLabsPegasusModel: Video understanding and Q&A using the Pegasus model

Key Features

TwelveLabsSearchModel:

• Search TwelveLabs video indexes using natural language queries
• Search video and audio content with configurable modalities (visual, audio)
• Support for both clip-level and video-grouped results

TwelveLabsPegasusModel:

• Upload and index videos with automatic deduplication
• Chat with existing videos in your TwelveLabs index for Q&A

Related Issues

Documentation PR

Type of Change

New feature

Testing

How have you tested the change?

• I ran hatch run prepare - All linting and formatting checks pass
• Unit tests: 26/26 tests pass for the TwelveLabs model implementation
• Integration with existing SDK patterns verified
• Error handling tested for all TwelveLabs API error codes
• Type checking with mypy passes
• Code formatting with ruff passes

The integration tests failed due to missing API credentials for AWS/OpenAI services, which is expected and unrelated to the TwelveLabs implementation.

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.