feat: Add Amazon Bedrock & OpenAI Compatible provider to Lighthouse AI

[0xbadshah]

Context

Lighthouse supports multi LLM provider as part of #8772
This PR adds support for Amazon Bedrock & OpenAI Compatible Providers.

Description

With multi LLM provider support, Lighthouse AI allows addition of new LLM providers. This PR adds support for Amazon Bedrock and OpenAI Compatible Providers.

As multi LLM support is limited to one provider config per tenant, the users can have 1 Amazon Bedrock configuration and 1 Open AI compatible provider (ex: OpenRouter, etc).

This PR also adds necessary code to validate the entered credentials.

Steps to review

After merge you should have the option of creating bedrock and openai_compatible provider configuration.

1. To create a configuration, send a POST request /api/v1/lighthouse/providers
   Sample POST body:

(OpenAI compatible)

{
  "data": {
    "type": "lighthouse-providers",
    "attributes": {
      "provider_type": "openai_compatible",
      "base_url": "https://openrouter.ai/api/v1/",
      "credentials": {
        "api_key": "sk-or-v1-xxx"
      }
    }
  }
}

(Amazon Bedrock)

{
  "data": {
    "type": "lighthouse-providers",
    "attributes": {
      "provider_type": "openai_compatible",
      "base_url": "https://openrouter.ai/api/v1/",
      "credentials": {
        "access_key_id": "AKIA....",
        "secret_access_key": "XXXXX....",
        "region": "us-east-1"
      }
    }
  }
}

2. To get list of providers, GET request to /api/v1/lighthouse/providers
3. To check the validity of the entered credential - POST request to /api/v1/lighthouse/providers/<UUID>/connection
4. To refresh models available from the provider - POST request to /api/v1/lighthouse/providers/<UUID>/refresh-models

Checklist

• Are there new checks included in this PR? Yes / No
  • If so, do we need to update permissions for the provider? Please review this carefully.
• Review if the code is being covered by tests.
• Review if code is being documented following this specification https://github.com/google/styleguide/blob/gh-pages/pyguide.md#38-comments-and-docstrings
• Review if backport is needed.
• Review if is needed to change the Readme.md
• Ensure new entries are added to CHANGELOG.md, if applicable.

API

• Verify if API specs need to be regenerated.
• Check if version updates are required (e.g., specs, Poetry, etc.).
• Ensure new entries are added to CHANGELOG.md, if applicable.

License

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

[vicferpoy]

Could you provide some examples of wrong payload's responses using POST and/or PATCH endpoints? To see the format of the response.