audio routes for groq and response_format for bedrock

[narengogi]

Author Description

(optional)

• Detailed change 1
• Detailed change 2

Title: Audio routes for groq and response_format for bedrock

🔄 What Changed

• Added support for audio-related API routes (transcription, translation, speech) in Groq provider
• Added response_format parameter support for Bedrock provider
• Implemented createSpeech parameters and response transformer in open-ai-base
• Enhanced header handling for audio routes in Groq API configuration

🔍 Impact of the Change

• Extends Groq provider with audio capabilities (transcription, translation, speech)
• Adds response_format parameter support to Bedrock provider
• Enhances the open-ai-base module with speech generation functionality
• Improves API compatibility with audio-related features

📁 Total Files Changed

• 5 files modified with 115 additions and 5 deletions

🧪 Test Added

N/A - No tests were added in this PR

🔒 Security Vulnerabilities

No security vulnerabilities detected

Quality Recommendations

1. Add unit tests for the new audio routes and response_format functionality

2. Consider adding validation for response_format values in the Bedrock implementation

3. Add error handling for potential failures in audio processing routes

4. Add documentation comments for the new createSpeechParams function

[rahulbansal16]

When can we expect this PR to be merged?

[rahulbansal16]

@VisargD @b4s36t4 can you take a look.

[rahulbansal16]

@narengogi Any update on DPR?

[narengogi]

hey @rahulbansal16 we'll get this merged and release today
cc: @VisargD

[matterai-app]

Summary By MatterAI

🔄 What Changed

• Added support for response_format parameter in Bedrock provider
• Added audio routes for Groq provider (transcriptions, translations, speech)
• Implemented createSpeechParams and CreateSpeechResponseTransformer in open-ai-base
• Updated headers configuration for audio routes in Groq provider

🔍 Impact of the Change

This PR enhances the gateway's capabilities by adding support for audio-related functionalities in the Groq provider and improving the Bedrock provider with response_format support. These changes allow clients to use audio transcription, translation, and speech generation with Groq, and have more control over response formatting with Bedrock.

📁 Total Files Changed

5 files changed with 115 additions and 5 deletions:

• src/providers/bedrock/chatComplete.ts (+5, -0)
• src/providers/bedrock/utils.ts (+3, -0)
• src/providers/groq/api.ts (+15, -2)
• src/providers/groq/index.ts (+10, -2)
• src/providers/open-ai-base/index.ts (+82, -1)

🧪 Test Added

N/A - No tests were included in this PR.

🔒Security Vulnerabilities

N/A - No security vulnerabilities detected.

Type of Change

• New feature (non-breaking change which adds functionality)
• Bug fix (non-breaking change which fixes an issue)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)

How Has This Been Tested?

• Unit Tests
• Integration Tests
• Manual Testing

Screenshots (if applicable)

N/A

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

Related Issues

N/A

Sequence Diagram

sequenceDiagram
    participant Client
    participant Gateway
    participant Bedrock
    participant Groq
    
    Client->>Gateway: Request with response_format parameter
    alt Bedrock Provider
        Gateway->>Bedrock: transformAdditionalModelRequestFields(params)
        Note over Gateway,Bedrock: Add response_format to additionalModelRequestFields
        Bedrock-->>Gateway: Response with formatted output
    end
    
    alt Groq Provider
        Client->>Gateway: Audio API Request
        alt createTranscription
            Gateway->>Groq: POST /audio/transcriptions
            Note over Gateway,Groq: Content-Type: multipart/form-data
            Groq-->>Gateway: Transcription Response
        else createTranslation
            Gateway->>Groq: POST /audio/translations
            Note over Gateway,Groq: Content-Type: multipart/form-data
            Groq-->>Gateway: Translation Response
        else createSpeech
            Gateway->>Groq: POST /audio/speech
            Note over Gateway,Groq: Parameters: model, input, voice, response_format, speed
            Groq-->>Gateway: Speech Response
        end
    end
    
    Gateway-->>Client: Transformed Response

Loading