Merge pull request #4074 from pipecat-ai/pk/openai-responses-llm-service
feat: add OpenAI Responses API LLM service
This commit is contained in:
kompfner
254
src/pipecat/adapters/services/open_ai_responses_adapter.py
Normal file
254
src/pipecat/adapters/services/open_ai_responses_adapter.py
Normal file
@@ -0,0 +1,254 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""OpenAI Responses API adapter for Pipecat."""
|
||||
|
||||
import copy
|
||||
from typing import Any, Dict, List, Optional, TypedDict
|
||||
|
||||
from loguru import logger
|
||||
from openai._types import NotGiven as OpenAINotGiven
|
||||
from openai.types.responses import FunctionToolParam, ResponseInputItemParam
|
||||
|
||||
from pipecat.adapters.base_llm_adapter import BaseLLMAdapter
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
from pipecat.processors.aggregators.llm_context import (
|
||||
LLMContext,
|
||||
LLMContextMessage,
|
||||
LLMSpecificMessage,
|
||||
NotGiven,
|
||||
)
|
||||
|
||||
|
||||
class OpenAIResponsesLLMInvocationParams(TypedDict, total=False):
|
||||
"""Context-based parameters for invoking OpenAI Responses API."""
|
||||
|
||||
input: List[ResponseInputItemParam]
|
||||
tools: List[FunctionToolParam] | OpenAINotGiven
|
||||
instructions: str
|
||||
|
||||
|
||||
class OpenAIResponsesLLMAdapter(BaseLLMAdapter[OpenAIResponsesLLMInvocationParams]):
|
||||
"""OpenAI Responses API adapter for Pipecat.
|
||||
|
||||
Handles:
|
||||
|
||||
- Converting LLMContext messages to Responses API input items
|
||||
- Converting Pipecat's standardized tools schema to Responses API function tool format
|
||||
- Extracting and sanitizing messages from the LLM context for logging
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the adapter."""
|
||||
super().__init__()
|
||||
self._warned_system_instruction = False
|
||||
|
||||
@property
|
||||
def id_for_llm_specific_messages(self) -> str:
|
||||
"""Get the identifier used in LLMSpecificMessage instances."""
|
||||
return "openai_responses"
|
||||
|
||||
def get_llm_invocation_params(
|
||||
self,
|
||||
context: LLMContext,
|
||||
*,
|
||||
system_instruction: Optional[str] = None,
|
||||
) -> OpenAIResponsesLLMInvocationParams:
|
||||
"""Get Responses API invocation parameters from a universal LLM context.
|
||||
|
||||
Args:
|
||||
context: The LLM context containing messages, tools, etc.
|
||||
system_instruction: Optional system instruction from service settings.
|
||||
|
||||
Returns:
|
||||
Dictionary of parameters for the Responses API.
|
||||
"""
|
||||
messages = self.get_messages(context)
|
||||
input_items = self._convert_messages_to_input(messages)
|
||||
|
||||
params: OpenAIResponsesLLMInvocationParams = {
|
||||
"input": input_items,
|
||||
"tools": self.from_standard_tools(context.tools),
|
||||
}
|
||||
|
||||
if system_instruction:
|
||||
# Compatibility: The Responses API requires at least one input
|
||||
# message when instructions are provided. Contexts that worked with
|
||||
# OpenAILLMService (system_instruction + empty messages) need the
|
||||
# instructions converted to an initial developer message.
|
||||
#
|
||||
# NOTE: if/when we support `previous_response_id` and/or
|
||||
# `conversation_id`, we'll need to revisit this logic, as it'll
|
||||
# be legit to provide instructions without input items. Worth
|
||||
# noting that OpenAI's docs suggest these parameters are primarily
|
||||
# for development convenience rather than performance (the model
|
||||
# still processes the full context), and come with the tradeoff
|
||||
# of requiring OpenAI-side 30-day conversation storage, which may
|
||||
# not be desirable for many users. But it could give folks an easy
|
||||
# way to store/switch between conversations without needing to
|
||||
# manage that storage themselves.
|
||||
if not input_items:
|
||||
params["input"] = [{"role": "developer", "content": system_instruction}]
|
||||
else:
|
||||
params["instructions"] = system_instruction
|
||||
|
||||
return params
|
||||
|
||||
def to_provider_tools_format(self, tools_schema: ToolsSchema) -> List[FunctionToolParam]:
|
||||
"""Convert function schemas to Responses API function tool format.
|
||||
|
||||
Args:
|
||||
tools_schema: The Pipecat tools schema to convert.
|
||||
|
||||
Returns:
|
||||
List of Responses API function tool definitions.
|
||||
"""
|
||||
functions_schema = tools_schema.standard_tools
|
||||
result = []
|
||||
for func in functions_schema:
|
||||
d = func.to_default_dict()
|
||||
tool: FunctionToolParam = {
|
||||
"type": "function",
|
||||
"name": d["name"],
|
||||
"parameters": d.get("parameters", {}),
|
||||
"strict": d.get("strict", None),
|
||||
}
|
||||
if "description" in d:
|
||||
tool["description"] = d["description"]
|
||||
result.append(tool)
|
||||
return result
|
||||
|
||||
def get_messages_for_logging(self, context: LLMContext) -> List[Dict[str, Any]]:
|
||||
"""Get messages from context in a format ready for logging.
|
||||
|
||||
Removes or truncates sensitive data like image content for safe logging.
|
||||
|
||||
Args:
|
||||
context: The LLM context containing messages.
|
||||
|
||||
Returns:
|
||||
List of messages in a format ready for logging.
|
||||
"""
|
||||
msgs = []
|
||||
for message in self.get_messages(context):
|
||||
msg = copy.deepcopy(message)
|
||||
if "content" in msg:
|
||||
if isinstance(msg["content"], list):
|
||||
for item in msg["content"]:
|
||||
if item.get("type") == "image_url":
|
||||
if item["image_url"]["url"].startswith("data:image/"):
|
||||
item["image_url"]["url"] = "data:image/..."
|
||||
if item.get("type") == "input_audio":
|
||||
item["input_audio"]["data"] = "..."
|
||||
msgs.append(msg)
|
||||
return msgs
|
||||
|
||||
def _convert_messages_to_input(
|
||||
self, messages: List[LLMContextMessage]
|
||||
) -> List[ResponseInputItemParam]:
|
||||
"""Convert LLMContext messages to Responses API input items.
|
||||
|
||||
Args:
|
||||
messages: Messages from the LLMContext.
|
||||
|
||||
Returns:
|
||||
List of Responses API input items.
|
||||
"""
|
||||
result: List[ResponseInputItemParam] = []
|
||||
is_first = True
|
||||
|
||||
for message in messages:
|
||||
if isinstance(message, LLMSpecificMessage):
|
||||
result.append(message.message)
|
||||
is_first = False
|
||||
continue
|
||||
|
||||
role = message.get("role")
|
||||
|
||||
if role == "system":
|
||||
if is_first and not self._warned_system_instruction:
|
||||
logger.warning(
|
||||
"System messages in LLMContext are converted to 'developer' role for the "
|
||||
"Responses API. Consider using settings.system_instruction instead, which "
|
||||
"maps to the 'instructions' parameter."
|
||||
)
|
||||
self._warned_system_instruction = True
|
||||
content = message.get("content", "")
|
||||
if isinstance(content, list):
|
||||
content = self._convert_multimodal_content(content)
|
||||
result.append({"role": "developer", "content": content})
|
||||
|
||||
elif role == "user":
|
||||
content = message.get("content", "")
|
||||
if isinstance(content, list):
|
||||
content = self._convert_multimodal_content(content)
|
||||
result.append({"role": "user", "content": content})
|
||||
|
||||
elif role == "assistant":
|
||||
tool_calls = message.get("tool_calls")
|
||||
if tool_calls:
|
||||
for tc in tool_calls:
|
||||
func = tc.get("function", {})
|
||||
result.append(
|
||||
{
|
||||
"type": "function_call",
|
||||
"call_id": tc.get("id", ""),
|
||||
"name": func.get("name", ""),
|
||||
"arguments": func.get("arguments", ""),
|
||||
}
|
||||
)
|
||||
else:
|
||||
content = message.get("content", "")
|
||||
if isinstance(content, list):
|
||||
content = self._convert_multimodal_content(content)
|
||||
result.append({"role": "assistant", "content": content})
|
||||
|
||||
elif role == "tool":
|
||||
content = message.get("content", "")
|
||||
if not isinstance(content, str):
|
||||
content = str(content)
|
||||
result.append(
|
||||
{
|
||||
"type": "function_call_output",
|
||||
"call_id": message.get("tool_call_id", ""),
|
||||
"output": content,
|
||||
}
|
||||
)
|
||||
|
||||
is_first = False
|
||||
|
||||
return result
|
||||
|
||||
def _convert_multimodal_content(self, content: list) -> list:
|
||||
"""Convert multimodal content parts to Responses API format.
|
||||
|
||||
Args:
|
||||
content: List of content parts from the LLMContext message.
|
||||
|
||||
Returns:
|
||||
List of content parts in Responses API format.
|
||||
"""
|
||||
result = []
|
||||
for part in content:
|
||||
part_type = part.get("type")
|
||||
if part_type == "text":
|
||||
result.append({"type": "input_text", "text": part.get("text", "")})
|
||||
elif part_type == "image_url":
|
||||
image_url_obj = part.get("image_url", {})
|
||||
result.append(
|
||||
{
|
||||
"type": "input_image",
|
||||
"image_url": image_url_obj.get("url", ""),
|
||||
"detail": image_url_obj.get("detail", "auto"),
|
||||
}
|
||||
)
|
||||
else:
|
||||
# Pass through other types as-is. Note: "input_audio" is not
|
||||
# yet supported by the Responses API (coming soon per OpenAI
|
||||
# docs) but the LLMContext format already matches the expected
|
||||
# shape, so it should work once support is enabled.
|
||||
result.append(part)
|
||||
return result
|
||||
@@ -11,6 +11,7 @@ from pipecat.services import DeprecatedModuleProxy
|
||||
from .image import *
|
||||
from .llm import *
|
||||
from .realtime import *
|
||||
from .responses.llm import *
|
||||
from .stt import *
|
||||
from .tts import *
|
||||
|
||||
|
||||
5
src/pipecat/services/openai/responses/__init__.py
Normal file
5
src/pipecat/services/openai/responses/__init__.py
Normal file
@@ -0,0 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
400
src/pipecat/services/openai/responses/llm.py
Normal file
400
src/pipecat/services/openai/responses/llm.py
Normal file
@@ -0,0 +1,400 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""OpenAI Responses API LLM service implementation."""
|
||||
|
||||
import json
|
||||
from contextlib import asynccontextmanager
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Dict, List, Mapping, Optional
|
||||
|
||||
import httpx
|
||||
from loguru import logger
|
||||
from openai import NOT_GIVEN, AsyncOpenAI, AsyncStream, DefaultAsyncHttpxClient
|
||||
from openai.types.responses import (
|
||||
ResponseCompletedEvent,
|
||||
ResponseFunctionCallArgumentsDeltaEvent,
|
||||
ResponseFunctionCallArgumentsDoneEvent,
|
||||
ResponseFunctionToolCall,
|
||||
ResponseOutputItemAddedEvent,
|
||||
ResponseOutputItemDoneEvent,
|
||||
ResponseStreamEvent,
|
||||
ResponseTextDeltaEvent,
|
||||
)
|
||||
|
||||
from pipecat.adapters.services.open_ai_responses_adapter import (
|
||||
OpenAIResponsesLLMAdapter,
|
||||
OpenAIResponsesLLMInvocationParams,
|
||||
)
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
LLMFullResponseEndFrame,
|
||||
LLMFullResponseStartFrame,
|
||||
)
|
||||
from pipecat.metrics.metrics import LLMTokenUsage
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.frame_processor import FrameDirection
|
||||
from pipecat.services.llm_service import FunctionCallFromLLM, LLMService
|
||||
from pipecat.services.settings import NOT_GIVEN as _NOT_GIVEN
|
||||
from pipecat.services.settings import LLMSettings, _NotGiven
|
||||
from pipecat.utils.tracing.service_decorators import traced_llm
|
||||
|
||||
|
||||
@dataclass
|
||||
class OpenAIResponsesLLMSettings(LLMSettings):
|
||||
"""Settings for OpenAIResponsesLLMService.
|
||||
|
||||
Parameters:
|
||||
max_completion_tokens: Maximum completion tokens to generate.
|
||||
"""
|
||||
|
||||
max_completion_tokens: int | _NotGiven = field(default_factory=lambda: _NOT_GIVEN)
|
||||
|
||||
|
||||
class OpenAIResponsesLLMService(LLMService):
|
||||
"""OpenAI Responses API LLM service.
|
||||
|
||||
This service works with the universal LLMContext and LLMContextAggregatorPair.
|
||||
|
||||
Example::
|
||||
|
||||
llm = OpenAIResponsesLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAIResponsesLLMService.Settings(
|
||||
model="gpt-4.1",
|
||||
system_instruction="You are a helpful assistant.",
|
||||
),
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = OpenAIResponsesLLMSettings
|
||||
_settings: Settings
|
||||
|
||||
adapter_class = OpenAIResponsesLLMAdapter
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
api_key=None,
|
||||
base_url=None,
|
||||
organization=None,
|
||||
project=None,
|
||||
default_headers: Optional[Mapping[str, str]] = None,
|
||||
service_tier: Optional[str] = None,
|
||||
settings: Optional[Settings] = None,
|
||||
**kwargs,
|
||||
):
|
||||
"""Initialize the OpenAI Responses API LLM service.
|
||||
|
||||
Args:
|
||||
api_key: OpenAI API key. If None, uses environment variable.
|
||||
base_url: Custom base URL for OpenAI API. If None, uses default.
|
||||
organization: OpenAI organization ID.
|
||||
project: OpenAI project ID.
|
||||
default_headers: Additional HTTP headers to include in requests.
|
||||
service_tier: Service tier to use (e.g., "auto", "flex", "priority").
|
||||
settings: Runtime-updatable settings.
|
||||
**kwargs: Additional arguments passed to the parent LLMService.
|
||||
"""
|
||||
default_settings = self.Settings(
|
||||
model="gpt-4.1",
|
||||
system_instruction=None,
|
||||
frequency_penalty=None,
|
||||
presence_penalty=None,
|
||||
seed=None,
|
||||
temperature=NOT_GIVEN,
|
||||
top_p=NOT_GIVEN,
|
||||
top_k=None,
|
||||
max_tokens=None,
|
||||
max_completion_tokens=NOT_GIVEN,
|
||||
filter_incomplete_user_turns=False,
|
||||
user_turn_completion_config=None,
|
||||
extra={},
|
||||
)
|
||||
|
||||
if settings is not None:
|
||||
default_settings.apply_update(settings)
|
||||
|
||||
super().__init__(
|
||||
settings=default_settings,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
self._service_tier = service_tier
|
||||
self._client = self._create_client(
|
||||
api_key=api_key,
|
||||
base_url=base_url,
|
||||
organization=organization,
|
||||
project=project,
|
||||
default_headers=default_headers,
|
||||
)
|
||||
|
||||
if self._settings.system_instruction:
|
||||
logger.debug(f"{self}: Using system instruction: {self._settings.system_instruction}")
|
||||
|
||||
def _create_client(
|
||||
self,
|
||||
api_key=None,
|
||||
base_url=None,
|
||||
organization=None,
|
||||
project=None,
|
||||
default_headers=None,
|
||||
) -> AsyncOpenAI:
|
||||
"""Create an AsyncOpenAI client instance.
|
||||
|
||||
Args:
|
||||
api_key: OpenAI API key.
|
||||
base_url: Custom base URL for the API.
|
||||
organization: OpenAI organization ID.
|
||||
project: OpenAI project ID.
|
||||
default_headers: Additional HTTP headers.
|
||||
|
||||
Returns:
|
||||
Configured AsyncOpenAI client instance.
|
||||
"""
|
||||
return AsyncOpenAI(
|
||||
api_key=api_key,
|
||||
base_url=base_url,
|
||||
organization=organization,
|
||||
project=project,
|
||||
http_client=DefaultAsyncHttpxClient(
|
||||
limits=httpx.Limits(
|
||||
max_keepalive_connections=100, max_connections=1000, keepalive_expiry=None
|
||||
)
|
||||
),
|
||||
default_headers=default_headers,
|
||||
)
|
||||
|
||||
def can_generate_metrics(self) -> bool:
|
||||
"""Check if this service can generate processing metrics."""
|
||||
return True
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
"""Process frames for LLM completion requests.
|
||||
|
||||
Args:
|
||||
frame: The frame to process.
|
||||
direction: The direction of frame processing.
|
||||
"""
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
context = None
|
||||
if isinstance(frame, LLMContextFrame):
|
||||
context = frame.context
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
if context:
|
||||
try:
|
||||
await self.push_frame(LLMFullResponseStartFrame())
|
||||
await self.start_processing_metrics()
|
||||
await self._process_context(context)
|
||||
except httpx.TimeoutException as e:
|
||||
await self._call_event_handler("on_completion_timeout")
|
||||
await self.push_error(error_msg="LLM completion timeout", exception=e)
|
||||
except Exception as e:
|
||||
await self.push_error(error_msg=f"Error during completion: {e}", exception=e)
|
||||
finally:
|
||||
await self.stop_processing_metrics()
|
||||
await self.push_frame(LLMFullResponseEndFrame())
|
||||
|
||||
@traced_llm
|
||||
async def _process_context(self, context: LLMContext):
|
||||
adapter: OpenAIResponsesLLMAdapter = self.get_llm_adapter()
|
||||
logger.debug(
|
||||
f"{self}: Generating response from universal context "
|
||||
f"{adapter.get_messages_for_logging(context)}"
|
||||
)
|
||||
|
||||
invocation_params = adapter.get_llm_invocation_params(
|
||||
context, system_instruction=self._settings.system_instruction
|
||||
)
|
||||
|
||||
params = self._build_response_params(invocation_params)
|
||||
|
||||
await self.start_ttfb_metrics()
|
||||
|
||||
stream: AsyncStream[ResponseStreamEvent] = await self._client.responses.create(**params)
|
||||
|
||||
# Track function calls across stream events
|
||||
function_calls: Dict[str, Dict[str, str]] = {} # item_id -> {name, call_id, arguments}
|
||||
current_arguments: Dict[str, str] = {} # item_id -> accumulated arguments
|
||||
|
||||
# Ensure stream and its async iterator are closed on cancellation/exception
|
||||
# to prevent socket leaks and uvloop crashes. Closing the iterator first
|
||||
# cascades cleanup through nested async generators (httpx/httpcore internals),
|
||||
# preventing uvloop's broken asyncgen finalizer from firing on Python 3.12+
|
||||
# (MagicStack/uvloop#699).
|
||||
@asynccontextmanager
|
||||
async def _closing(stream):
|
||||
chunk_iter = stream.__aiter__()
|
||||
try:
|
||||
yield chunk_iter
|
||||
finally:
|
||||
# Close the iterator first to cascade cleanup through
|
||||
# nested async generators (httpx/httpcore internals).
|
||||
if hasattr(chunk_iter, "aclose"):
|
||||
await chunk_iter.aclose()
|
||||
# Then close the stream to release HTTP resources.
|
||||
if hasattr(stream, "close"):
|
||||
await stream.close()
|
||||
elif hasattr(stream, "aclose"):
|
||||
await stream.aclose()
|
||||
|
||||
async with _closing(stream) as event_iter:
|
||||
async for event in event_iter:
|
||||
if isinstance(event, ResponseTextDeltaEvent):
|
||||
await self.stop_ttfb_metrics()
|
||||
await self._push_llm_text(event.delta)
|
||||
|
||||
elif isinstance(event, ResponseOutputItemAddedEvent):
|
||||
await self.stop_ttfb_metrics()
|
||||
item = event.item
|
||||
if isinstance(item, ResponseFunctionToolCall):
|
||||
item_id = item.id or ""
|
||||
function_calls[item_id] = {
|
||||
"name": item.name,
|
||||
"call_id": item.call_id,
|
||||
"arguments": "",
|
||||
}
|
||||
current_arguments[item_id] = ""
|
||||
|
||||
elif isinstance(event, ResponseFunctionCallArgumentsDeltaEvent):
|
||||
item_id = event.item_id
|
||||
if item_id in current_arguments:
|
||||
current_arguments[item_id] += event.delta
|
||||
|
||||
elif isinstance(event, ResponseFunctionCallArgumentsDoneEvent):
|
||||
item_id = event.item_id
|
||||
if item_id in function_calls:
|
||||
function_calls[item_id]["arguments"] = event.arguments
|
||||
|
||||
elif isinstance(event, ResponseOutputItemDoneEvent):
|
||||
item = event.item
|
||||
if isinstance(item, ResponseFunctionToolCall):
|
||||
item_id = item.id or ""
|
||||
if item_id in function_calls:
|
||||
function_calls[item_id]["name"] = item.name
|
||||
function_calls[item_id]["call_id"] = item.call_id
|
||||
function_calls[item_id]["arguments"] = item.arguments
|
||||
|
||||
elif isinstance(event, ResponseCompletedEvent):
|
||||
response = event.response
|
||||
if response.usage:
|
||||
tokens = LLMTokenUsage(
|
||||
prompt_tokens=response.usage.input_tokens,
|
||||
completion_tokens=response.usage.output_tokens,
|
||||
total_tokens=response.usage.total_tokens,
|
||||
cache_read_input_tokens=response.usage.input_tokens_details.cached_tokens,
|
||||
reasoning_tokens=response.usage.output_tokens_details.reasoning_tokens,
|
||||
)
|
||||
await self.start_llm_usage_metrics(tokens)
|
||||
|
||||
# This field is used by @traced_llm for more detailed
|
||||
# model name in tracing spans
|
||||
self._full_model_name = response.model
|
||||
|
||||
# Process any function calls
|
||||
if function_calls:
|
||||
fc_list: List[FunctionCallFromLLM] = []
|
||||
for item_id, fc in function_calls.items():
|
||||
try:
|
||||
arguments = json.loads(fc["arguments"]) if fc["arguments"] else {}
|
||||
except json.JSONDecodeError:
|
||||
logger.warning(
|
||||
f"{self}: Failed to parse function call arguments: {fc['arguments']}"
|
||||
)
|
||||
arguments = {}
|
||||
fc_list.append(
|
||||
FunctionCallFromLLM(
|
||||
context=context,
|
||||
tool_call_id=fc["call_id"],
|
||||
function_name=fc["name"],
|
||||
arguments=arguments,
|
||||
)
|
||||
)
|
||||
await self.run_function_calls(fc_list)
|
||||
|
||||
def _build_response_params(self, invocation_params: OpenAIResponsesLLMInvocationParams) -> dict:
|
||||
"""Build parameters for the responses.create() call.
|
||||
|
||||
Args:
|
||||
invocation_params: Parameters derived from the LLM context.
|
||||
|
||||
Returns:
|
||||
Dictionary of parameters for the Responses API call.
|
||||
"""
|
||||
params: Dict[str, Any] = {
|
||||
"model": self._settings.model,
|
||||
"stream": True,
|
||||
"store": False,
|
||||
"input": invocation_params["input"],
|
||||
}
|
||||
|
||||
# instructions (set by the adapter when input is non-empty)
|
||||
if "instructions" in invocation_params:
|
||||
params["instructions"] = invocation_params["instructions"]
|
||||
|
||||
# Optional parameters - only include if given
|
||||
if isinstance(self._settings.temperature, (int, float)):
|
||||
params["temperature"] = self._settings.temperature
|
||||
|
||||
if isinstance(self._settings.top_p, (int, float)):
|
||||
params["top_p"] = self._settings.top_p
|
||||
|
||||
if isinstance(self._settings.max_completion_tokens, int):
|
||||
params["max_output_tokens"] = self._settings.max_completion_tokens
|
||||
|
||||
if self._service_tier is not None:
|
||||
params["service_tier"] = self._service_tier
|
||||
|
||||
# Tools
|
||||
tools = invocation_params.get("tools")
|
||||
if tools is not None and not isinstance(tools, type(NOT_GIVEN)):
|
||||
params["tools"] = tools
|
||||
|
||||
# Extra settings
|
||||
params.update(self._settings.extra)
|
||||
|
||||
return params
|
||||
|
||||
async def run_inference(
|
||||
self,
|
||||
context: LLMContext,
|
||||
max_tokens: Optional[int] = None,
|
||||
system_instruction: Optional[str] = None,
|
||||
) -> Optional[str]:
|
||||
"""Run a one-shot, out-of-band inference with the given LLM context.
|
||||
|
||||
Args:
|
||||
context: The LLM context containing conversation history.
|
||||
max_tokens: Optional maximum number of tokens to generate.
|
||||
system_instruction: Optional system instruction for this inference.
|
||||
|
||||
Returns:
|
||||
The LLM's response as a string, or None if no response is generated.
|
||||
"""
|
||||
adapter: OpenAIResponsesLLMAdapter = self.get_llm_adapter()
|
||||
effective_instruction = system_instruction or self._settings.system_instruction
|
||||
invocation_params = adapter.get_llm_invocation_params(
|
||||
context, system_instruction=effective_instruction
|
||||
)
|
||||
|
||||
params = self._build_response_params(invocation_params)
|
||||
|
||||
# Override for non-streaming
|
||||
params["stream"] = False
|
||||
|
||||
if max_tokens is not None:
|
||||
params["max_output_tokens"] = max_tokens
|
||||
|
||||
response = await self._client.responses.create(**params)
|
||||
|
||||
return response.output_text
|
||||
|
||||
|
||||
__all__ = ["OpenAIResponsesLLMService", "OpenAIResponsesLLMSettings"]
|
||||
@@ -51,8 +51,10 @@ def _get_model_name(service) -> str:
|
||||
check all the places we used to store it.
|
||||
"""
|
||||
return (
|
||||
getattr(getattr(service, "_settings", None), "model", None)
|
||||
or getattr(service, "_full_model_name", None)
|
||||
# Some services store an API-response-provided detailed "full" name,
|
||||
# which is distinct from the user-provided model name
|
||||
getattr(service, "_full_model_name", None)
|
||||
or getattr(getattr(service, "_settings", None), "model", None)
|
||||
or getattr(service, "model_name", None)
|
||||
or getattr(service, "_model_name", None)
|
||||
or "unknown"
|
||||
|
||||
Reference in New Issue
Block a user