mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
feat: function tools in OpenAI Responses (#2094)
# What does this PR do? This is a combination of what was previously 3 separate PRs - #2069, #2075, and #2083. It turns out all 3 of those are needed to land a working function calling Responses implementation. The web search builtin tool was already working, but this wires in support for custom function calling. I ended up combining all three into one PR because they all had lots of merge conflicts, both with each other but also with #1806 that just landed. And, because landing any of them individually would have only left a partially working implementation merged. The new things added here are: * Storing of input items from previous responses and restoring of those input items when adding previous responses to the conversation state * Handling of multiple input item messages roles, not just "user" messages. * Support for custom tools passed into the Responses API to enable function calling outside of just the builtin websearch tool. Closes #2074 Closes #2080 ## Test Plan ### Unit Tests Several new unit tests were added, and they all pass. Ran via: ``` python -m pytest -s -v tests/unit/providers/agents/meta_reference/test_openai_responses.py ``` ### Responses API Verification Tests I ran our verification run.yaml against multiple providers to ensure we were getting a decent pass rate. Specifically, I ensured the new custom tool verification test passed across multiple providers and that the multi-turn examples passed across at least some of the providers (some providers struggle with the multi-turn workflows still). Running the stack setup for verification testing: ``` llama stack run --image-type venv tests/verifications/openai-api-verification-run.yaml ``` Together, passing 100% as an example: ``` pytest -s -v 'tests/verifications/openai_api/test_responses.py' --provider=together-llama-stack ``` ## Documentation We will need to start documenting the OpenAI APIs, but for now the Responses stuff is still rapidly evolving so delaying that. --------- Signed-off-by: Derek Higgins <derekh@redhat.com> Signed-off-by: Ben Browning <bbrownin@redhat.com> Co-authored-by: Derek Higgins <derekh@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
Ben Browning
GitHub
parent
e0d10dd0b1
commit
8e316c9b1e
13 changed files with 1099 additions and 370 deletions
|
|
@ -31,7 +31,7 @@ from llama_stack.apis.tools import ToolDef
|
|||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
from .openai_responses import (
|
||||
OpenAIResponseInputMessage,
|
||||
OpenAIResponseInput,
|
||||
OpenAIResponseInputTool,
|
||||
OpenAIResponseObject,
|
||||
OpenAIResponseObjectStream,
|
||||
|
|
@ -593,7 +593,7 @@ class Agents(Protocol):
|
|||
@webmethod(route="/openai/v1/responses", method="POST")
|
||||
async def create_openai_response(
|
||||
self,
|
||||
input: str | list[OpenAIResponseInputMessage],
|
||||
input: str | list[OpenAIResponseInput],
|
||||
model: str,
|
||||
previous_response_id: str | None = None,
|
||||
store: bool | None = True,
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import Annotated, Literal
|
||||
from typing import Annotated, Any, Literal
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
|
@ -17,6 +17,28 @@ class OpenAIResponseError(BaseModel):
|
|||
message: str
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputMessageContentText(BaseModel):
|
||||
text: str
|
||||
type: Literal["input_text"] = "input_text"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputMessageContentImage(BaseModel):
|
||||
detail: Literal["low"] | Literal["high"] | Literal["auto"] = "auto"
|
||||
type: Literal["input_image"] = "input_image"
|
||||
# TODO: handle file_id
|
||||
image_url: str | None = None
|
||||
|
||||
|
||||
# TODO: handle file content types
|
||||
OpenAIResponseInputMessageContent = Annotated[
|
||||
OpenAIResponseInputMessageContentText | OpenAIResponseInputMessageContentImage,
|
||||
Field(discriminator="type"),
|
||||
]
|
||||
register_schema(OpenAIResponseInputMessageContent, name="OpenAIResponseInputMessageContent")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseOutputMessageContentOutputText(BaseModel):
|
||||
text: str
|
||||
|
|
@ -31,13 +53,22 @@ register_schema(OpenAIResponseOutputMessageContent, name="OpenAIResponseOutputMe
|
|||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseOutputMessage(BaseModel):
|
||||
id: str
|
||||
content: list[OpenAIResponseOutputMessageContent]
|
||||
role: Literal["assistant"] = "assistant"
|
||||
status: str
|
||||
class OpenAIResponseMessage(BaseModel):
|
||||
"""
|
||||
Corresponds to the various Message types in the Responses API.
|
||||
They are all under one type because the Responses API gives them all
|
||||
the same "type" value, and there is no way to tell them apart in certain
|
||||
scenarios.
|
||||
"""
|
||||
|
||||
content: str | list[OpenAIResponseInputMessageContent] | list[OpenAIResponseOutputMessageContent]
|
||||
role: Literal["system"] | Literal["developer"] | Literal["user"] | Literal["assistant"]
|
||||
type: Literal["message"] = "message"
|
||||
|
||||
# The fields below are not used in all scenarios, but are required in others.
|
||||
id: str | None = None
|
||||
status: str | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseOutputMessageWebSearchToolCall(BaseModel):
|
||||
|
|
@ -46,8 +77,18 @@ class OpenAIResponseOutputMessageWebSearchToolCall(BaseModel):
|
|||
type: Literal["web_search_call"] = "web_search_call"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseOutputMessageFunctionToolCall(BaseModel):
|
||||
arguments: str
|
||||
call_id: str
|
||||
name: str
|
||||
type: Literal["function_call"] = "function_call"
|
||||
id: str
|
||||
status: str
|
||||
|
||||
|
||||
OpenAIResponseOutput = Annotated[
|
||||
OpenAIResponseOutputMessage | OpenAIResponseOutputMessageWebSearchToolCall,
|
||||
OpenAIResponseMessage | OpenAIResponseOutputMessageWebSearchToolCall | OpenAIResponseOutputMessageFunctionToolCall,
|
||||
Field(discriminator="type"),
|
||||
]
|
||||
register_schema(OpenAIResponseOutput, name="OpenAIResponseOutput")
|
||||
|
|
@ -90,32 +131,29 @@ register_schema(OpenAIResponseObjectStream, name="OpenAIResponseObjectStream")
|
|||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputMessageContentText(BaseModel):
|
||||
text: str
|
||||
type: Literal["input_text"] = "input_text"
|
||||
class OpenAIResponseInputFunctionToolCallOutput(BaseModel):
|
||||
"""
|
||||
This represents the output of a function call that gets passed back to the model.
|
||||
"""
|
||||
|
||||
call_id: str
|
||||
output: str
|
||||
type: Literal["function_call_output"] = "function_call_output"
|
||||
id: str | None = None
|
||||
status: str | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputMessageContentImage(BaseModel):
|
||||
detail: Literal["low"] | Literal["high"] | Literal["auto"] = "auto"
|
||||
type: Literal["input_image"] = "input_image"
|
||||
# TODO: handle file_id
|
||||
image_url: str | None = None
|
||||
|
||||
|
||||
# TODO: handle file content types
|
||||
OpenAIResponseInputMessageContent = Annotated[
|
||||
OpenAIResponseInputMessageContentText | OpenAIResponseInputMessageContentImage,
|
||||
Field(discriminator="type"),
|
||||
OpenAIResponseInput = Annotated[
|
||||
# Responses API allows output messages to be passed in as input
|
||||
OpenAIResponseOutputMessageWebSearchToolCall
|
||||
| OpenAIResponseOutputMessageFunctionToolCall
|
||||
| OpenAIResponseInputFunctionToolCallOutput
|
||||
|
|
||||
# Fallback to the generic message type as a last resort
|
||||
OpenAIResponseMessage,
|
||||
Field(union_mode="left_to_right"),
|
||||
]
|
||||
register_schema(OpenAIResponseInputMessageContent, name="OpenAIResponseInputMessageContent")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputMessage(BaseModel):
|
||||
content: str | list[OpenAIResponseInputMessageContent]
|
||||
role: Literal["system"] | Literal["developer"] | Literal["user"] | Literal["assistant"]
|
||||
type: Literal["message"] | None = "message"
|
||||
register_schema(OpenAIResponseInput, name="OpenAIResponseInput")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
|
|
@ -126,8 +164,35 @@ class OpenAIResponseInputToolWebSearch(BaseModel):
|
|||
# TODO: add user_location
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputToolFunction(BaseModel):
|
||||
type: Literal["function"] = "function"
|
||||
name: str
|
||||
description: str | None = None
|
||||
parameters: dict[str, Any] | None
|
||||
strict: bool | None = None
|
||||
|
||||
|
||||
class FileSearchRankingOptions(BaseModel):
|
||||
ranker: str | None = None
|
||||
score_threshold: float | None = Field(default=0.0, ge=0.0, le=1.0)
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIResponseInputToolFileSearch(BaseModel):
|
||||
type: Literal["file_search"] = "file_search"
|
||||
vector_store_id: list[str]
|
||||
ranking_options: FileSearchRankingOptions | None = None
|
||||
# TODO: add filters
|
||||
|
||||
|
||||
OpenAIResponseInputTool = Annotated[
|
||||
OpenAIResponseInputToolWebSearch,
|
||||
OpenAIResponseInputToolWebSearch | OpenAIResponseInputToolFileSearch | OpenAIResponseInputToolFunction,
|
||||
Field(discriminator="type"),
|
||||
]
|
||||
register_schema(OpenAIResponseInputTool, name="OpenAIResponseInputTool")
|
||||
|
||||
|
||||
class OpenAIResponseInputItemList(BaseModel):
|
||||
data: list[OpenAIResponseInput]
|
||||
object: Literal["list"] = "list"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue