mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-21 17:33:12 +00:00
914c7be288
Add complete batches API implementation with protocol, providers, and tests: Core Infrastructure: - Add batches API protocol using OpenAI Batch types directly - Add Api.batches enum value and protocol mapping in resolver - Add OpenAI "batch" file purpose support - Include proper error handling (ConflictError, ResourceNotFoundError) Reference Provider: - Add ReferenceBatchesImpl with full CRUD operations (create, retrieve, cancel, list) - Implement background batch processing with configurable concurrency - Add SQLite KVStore backend for persistence - Support /v1/chat/completions endpoint with request validation Comprehensive Test Suite: - Add unit tests for provider implementation with validation - Add integration tests for end-to-end batch processing workflows - Add error handling tests for validation, malformed inputs, and edge cases Configuration: - Add max_concurrent_batches and max_concurrent_requests_per_batch options - Add provider documentation with sample configurations Test with - ``` $ uv run llama stack build --image-type venv --providers inference=YOU_PICK,files=inline::localfs,batches=inline::reference --run & $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/unit/providers/batches tests/integration/batches --text-model YOU_PICK ``` addresses #3066 --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
56 lines
1.4 KiB
JSON
56 lines
1.4 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Quick test"
|
|
}
|
|
],
|
|
"max_tokens": 5
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl-651",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'm ready to help",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 1755294941,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 5,
|
|
"prompt_tokens": 27,
|
|
"total_tokens": 32,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|