chore: create OpenAIMixin for inference providers with an OpenAI-compat API that need to implement openai_* methods (#2835)
Some checks failed
Coverage Badge / unit-tests (push) Failing after 3s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 6s
Python Package Build Test / build (3.12) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 6s
Integration Tests / discover-tests (push) Successful in 7s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 6s
Python Package Build Test / build (3.13) (push) Failing after 2s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 6s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 9s
Unit Tests / unit-tests (3.12) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 11s
Test External Providers / test-external-providers (venv) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 9s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 17s
Unit Tests / unit-tests (3.13) (push) Failing after 12s
Update ReadTheDocs / update-readthedocs (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 16s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 18s
Integration Tests / test-matrix (push) Failing after 18s
Pre-commit / pre-commit (push) Successful in 1m14s

# What does this PR do?

add an `OpenAIMixin` for use by inference providers who remote endpoints
support an OpenAI compatible API.

use is demonstrated by refactoring
- OpenAIInferenceAdapter
- NVIDIAInferenceAdapter (adds embedding support)
- LlamaCompatInferenceAdapter

## Test Plan

existing unit and integration tests
This commit is contained in:
Matthew Farrellee 2025-07-23 06:49:40 -04:00 committed by GitHub
parent fc67ad408a
commit e1ed152779
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 402 additions and 387 deletions

View file

@ -14,6 +14,41 @@ Here are some example PRs to help you get started:
- [Nvidia Inference Implementation](https://github.com/meta-llama/llama-stack/pull/355)
- [Model context protocol Tool Runtime](https://github.com/meta-llama/llama-stack/pull/665)
## Inference Provider Patterns
When implementing Inference providers for OpenAI-compatible APIs, Llama Stack provides several mixin classes to simplify development and ensure consistent behavior across providers.
### OpenAIMixin
The `OpenAIMixin` class provides direct OpenAI API functionality for providers that work with OpenAI-compatible endpoints. It includes:
#### Direct API Methods
- **`openai_completion()`**: Legacy text completion API with full parameter support
- **`openai_chat_completion()`**: Chat completion API supporting streaming, tools, and function calling
- **`openai_embeddings()`**: Text embeddings generation with customizable encoding and dimensions
#### Model Management
- **`check_model_availability()`**: Queries the API endpoint to verify if a model exists and is accessible
#### Client Management
- **`client` property**: Automatically creates and configures AsyncOpenAI client instances using your provider's credentials
#### Required Implementation
To use `OpenAIMixin`, your provider must implement these abstract methods:
```python
@abstractmethod
def get_api_key(self) -> str:
"""Return the API key for authentication"""
pass
@abstractmethod
def get_base_url(self) -> str:
"""Return the OpenAI-compatible API base URL"""
pass
```
## Testing the Provider