Skip to content

Conversation

soumilinandi
Copy link

Motivation and Context

This change adds chat completion support with structured output to the existing NVIDIA connector, enabling developers to use NVIDIA's chat models through Semantic Kernel while building conversational AI applications that require structured, validated responses. The connector will support more model types iteratively, with future PRs introducing VLM models and additional capabilities.

Description

  • New Chat Completion Service:
    NvidiaChatCompletion: Chat completion service following same structure as other connectors

    • Extends existing NVIDIA embedding connector patterns and architecture
    • Custom logic for handling structured output specific to NVIDIA models
  • Enhanced Configuration:
    NvidiaChatPromptExecutionSettings: Chat-specific settings following existing connector patterns

Contribution Checklist

@soumilinandi soumilinandi requested a review from a team as a code owner August 14, 2025 16:55
@moonbox3 moonbox3 added python Pull requests for the Python Semantic Kernel documentation labels Aug 14, 2025
@github-actions github-actions bot changed the title Feature/chat models Python: Feature/chat models Aug 14, 2025
@soumilinandi
Copy link
Author

@microsoft-github-policy-service agree company="NVIDIA"

@moonbox3 moonbox3 changed the title Python: Feature/chat models Python: Introduce NvidiaChatCompletion AI Connector Sep 1, 2025
@moonbox3
Copy link
Collaborator

Python Test Coverage

Python Test Coverage Report •
FileStmtsMissCoverMissing
__init__.py40100% 
connectors/ai/nvidia
   __init__.py50100% 
connectors/ai/nvidia/prompt_execution_settings
   nvidia_prompt_execution_settings.py420100% 
connectors/ai/nvidia/services
   nvidia_chat_completion.py1243175%95–96, 129, 149, 172–174, 176–178, 181, 183–184, 186–190, 224–225, 227–231, 261, 276, 296, 298–300
   nvidia_handler.py63296%72, 107
   nvidia_model_types.py40100% 
   nvidia_text_embedding.py71395%71–72, 74
connectors/ai/nvidia/settings
   nvidia_settings.py90100% 
TOTAL27283476782% 

Python Unit Test Overview

Tests Skipped Failures Errors Time
3746 22 💤 0 ❌ 0 🔥 1m 45s ⏱️

@moonbox3
Copy link
Collaborator

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation python Pull requests for the Python Semantic Kernel
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants