Feat : Support AWS bedrock base models

[detunjiSamuel]

This is a draft.I'm cleaning in up the comments , notes and external links on my machine

AWS Bedrock Provider Integration

Added support for AWS Bedrock as a new LLM provider:

• Anthropic Claude models
• Amazon Titan models (text & embeddings)
• AI21 Jurassic models

Key Changes

Added Bedrock provider implementation with model-specific handlers:

• Anthropic: Reused existing Anthropic provider code with Bedrock-specific modifications ( no actual changes)
• Titan: Added chat completion and embedding support
• AI21: Added completion and chat completion support
• Request/response mapping between Hub formats and Bedrock formats

Testing Notes

All tests pass using AWS credentials in us-east-1/2 regions
Verified error handling for invalid credentials/models
Tested non-streaming responses ( models in Bedrock don't seem to have streaming types )

Review notes

The model ID from AWS link does not work consistently.
Instead, use the Inference profile ARN or Inference profile ID from the cross-region reference tab as your model_id.

Issue: #20

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[detunjiSamuel]

Hey @nirga ,

Quick question about integrating Stability AI models in our Hub. I'm looking at AWS Bedrock's Stable Diffusion 3.5 integration (from their model catalog).

Not sure about the best format to implement this:

1. Should we use the existing chat_completions since it takes a similar prompt format?
2. Or would it make more sense to create a new Content type specifically for image generation?

Would appreciate your thoughts on this.

Thanks!

[nirga]

I think it should be in a new api @detunjiSamuel
But we can do it in a separate PR