phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Update OpenAPI generator to add param and field documentation (#896)

Browse source 
We desperately need to document our APIs. This is the basic requirement
of having a Spec :)

This PR updates the OpenAPI generator so documentation for request
parameters and object fields can be properly added to the OpenAPI specs.
From there, this should get picked by Stainless, etc.

## Test Plan:

Updated client-sdk (See
https://github.com/meta-llama/llama-stack-client-python/pull/104) and
then ran:

```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=../../llama_stack/templates/fireworks/run.yaml pytest -s -v inference/test_inference.py agents/test_agents.py
```
This commit is contained in:
Ashwin Bharambe 2025-01-29 10:04:30 -08:00 • committed by GitHub
parent 53721e91ad
commit 0d96070af9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 1059 additions and 2122 deletions
Download patch file Download diff file Expand all files Collapse all files

33
llama_stack/apis/batch_inference/batch_inference.py
View file

@ -7,13 +7,15 @@
from typing import List, Optional, Protocol, runtime_checkable
from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel, Field
from pydantic import BaseModel
from llama_stack.apis.inference import (
CompletionMessage,
ChatCompletionResponse,
CompletionResponse,
InterleavedContent,
LogProbConfig,
Message,
ResponseFormat,
SamplingParams,
ToolChoice,
ToolDefinition,
@ -21,35 +23,14 @@ from llama_stack.apis.inference import (
)
@json_schema_type
class BatchCompletionRequest(BaseModel):
model: str
content_batch: List[InterleavedContent]
sampling_params: Optional[SamplingParams] = SamplingParams()
logprobs: Optional[LogProbConfig] = None
@json_schema_type
class BatchCompletionResponse(BaseModel):
completion_message_batch: List[CompletionMessage]
@json_schema_type
class BatchChatCompletionRequest(BaseModel):
model: str
messages_batch: List[List[Message]]
sampling_params: Optional[SamplingParams] = SamplingParams()
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = Field(default_factory=list)
tool_choice: Optional[ToolChoice] = Field(default=ToolChoice.auto)
tool_prompt_format: Optional[ToolPromptFormat] = Field(default=None)
logprobs: Optional[LogProbConfig] = None
batch: List[CompletionResponse]
@json_schema_type
class BatchChatCompletionResponse(BaseModel):
completion_message_batch: List[CompletionMessage]
batch: List[ChatCompletionResponse]
@runtime_checkable
@ -60,6 +41,7 @@ class BatchInference(Protocol):
model: str,
content_batch: List[InterleavedContent],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...
@ -73,5 +55,6 @@ class BatchInference(Protocol):
tools: Optional[List[ToolDefinition]] = list,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = None,
response_format: Optional[ResponseFormat] = None,
logprobs: Optional[LogProbConfig] = None,
) -> BatchChatCompletionResponse: ...