mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
# What does this PR do? ## Test Plan # What does this PR do? ## Test Plan # What does this PR do? ## Test Plan Completes the refactoring started in previous commit by: 1. **Fix library client** (critical): Add logic to detect Pydantic model parameters and construct them properly from request bodies. The key fix is to NOT exclude any params when converting the body for Pydantic models - we need all fields to pass to the Pydantic constructor. Before: _convert_body excluded all params, leaving body empty for Pydantic construction After: Check for Pydantic params first, skip exclusion, construct model with full body 2. **Update remaining providers** to use new Pydantic-based signatures: - litellm_openai_mixin: Extract extra fields via __pydantic_extra__ - databricks: Use TYPE_CHECKING import for params type - llama_openai_compat: Use TYPE_CHECKING import for params type - sentence_transformers: Update method signatures to use params 3. **Update unit tests** to use new Pydantic signature: - test_openai_mixin.py: Use OpenAIChatCompletionRequestParams This fixes test failures where the library client was trying to construct Pydantic models with empty dictionaries. The previous fix had a bug: it called _convert_body() which only keeps fields that match function parameter names. For Pydantic methods with signature: openai_chat_completion(params: OpenAIChatCompletionRequestParams) The signature only has 'params', but the body has 'model', 'messages', etc. So _convert_body() returned an empty dict. Fix: Skip _convert_body() entirely for Pydantic params. Use the raw body directly to construct the Pydantic model (after stripping NOT_GIVENs). This properly fixes the ValidationError where required fields were missing. The streaming code path (_call_streaming) had the same issue as non-streaming: it called _convert_body() which returned empty dict for Pydantic params. Applied the same fix as commit 7476c0ae: - Detect Pydantic model parameters before body conversion - Skip _convert_body() for Pydantic params - Construct Pydantic model directly from raw body (after stripping NOT_GIVENs) This fixes streaming endpoints like openai_chat_completion with stream=True. The streaming code path (_call_streaming) had the same issue as non-streaming: it called _convert_body() which returned empty dict for Pydantic params. Applied the same fix as commit 7476c0ae: - Detect Pydantic model parameters before body conversion - Skip _convert_body() for Pydantic params - Construct Pydantic model directly from raw body (after stripping NOT_GIVENs) This fixes streaming endpoints like openai_chat_completion with stream=True.
265 lines
7.3 KiB
JSON
265 lines
7.3 KiB
JSON
{
|
|
"test_id": null,
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful assistant"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "What is 2 + 2?"
|
|
}
|
|
],
|
|
"max_tokens": 0,
|
|
"stream": true,
|
|
"extra_body": null
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "2",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " +",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " ",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "2",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " =",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " ",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "4",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": ".",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-064df9630ae8",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|