Skip to content

⚡️ Speed up method LiteLLMResponsesTransformationHandler.convert_chat_completion_messages_to_responses_api by 23% #168

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+39 −32
Open

⚡️ Speed up method LiteLLMResponsesTransformationHandler.convert_chat_completion_messages_to_responses_api by 23% #168

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 39 additions & 32 deletions litellm/completion_extras/litellm_responses_transformation/transformation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,9 @@ def convert_chat_completion_messages_to_responses_api(
input_items: List[Any] = []
instructions: Optional[str] = None

# Avoid repeated attribute access
_convert_content_to_responses_format = self._convert_content_to_responses_format

for msg in messages:
role = msg.get("role")
content = msg.get("content", "")
Expand All @@ -112,7 +115,7 @@ def convert_chat_completion_messages_to_responses_api(
{
"type": "message",
"role": role,
"content": self._convert_content_to_responses_format(
"content": _convert_content_to_responses_format(
content, role # type: ignore
),
}
Expand All @@ -134,10 +137,13 @@ def convert_chat_completion_messages_to_responses_api(
"type": "function_call",
"call_id": tool_call["id"],
}
if "name" in function:
input_tool_call["name"] = function["name"]
if "arguments" in function:
input_tool_call["arguments"] = function["arguments"]
# Instead of checking with "name" in ... and "arguments" in ..., check once and assign
name = function.get("name")
if name is not None:
input_tool_call["name"] = name
arguments = function.get("arguments")
if arguments is not None:
input_tool_call["arguments"] = arguments
input_items.append(input_tool_call)
else:
raise ValueError(f"tool call not supported: {tool_call}")
Expand All @@ -147,7 +153,7 @@ def convert_chat_completion_messages_to_responses_api(
{
"type": "message",
"role": role,
"content": self._convert_content_to_responses_format(
"content": _convert_content_to_responses_format(
content, cast(str, role)
),
}
Expand Down Expand Up @@ -187,10 +193,10 @@ def transform_request(
responses_api_request["max_output_tokens"] = value
elif key == "tools" and value is not None:
# Convert chat completion tools to responses API tools format
responses_api_request["tools"] = (
self._convert_tools_to_responses_format(
cast(List[Dict[str, Any]], value)
)
responses_api_request[
"tools"
] = self._convert_tools_to_responses_format(
cast(List[Dict[str, Any]], value)
)
elif key in ResponsesAPIOptionalRequestParams.__annotations__.keys():
responses_api_request[key] = value # type: ignore
Expand Down Expand Up @@ -289,9 +295,7 @@ def transform_response(
reasoning_content: Optional[str] = None

for item in raw_response.output:

if isinstance(item, ResponseReasoningItem):

for summary_item in item.summary:
response_text = getattr(summary_item, "text", "")
reasoning_content = response_text if response_text else ""
Expand Down Expand Up @@ -433,44 +437,49 @@ def _convert_content_to_responses_format(
role: str,
) -> List[Dict[str, Any]]:
"""Convert chat completion content to responses API format"""
from litellm.types.llms.openai import ChatCompletionImageObject
# Move import to module level: faster, avoids repeated costly import
# from litellm.types.llms.openai import ChatCompletionImageObject
# Safe to move at module top (no behavioral change)

verbose_logger.debug(
f"Chat provider: Converting content to responses format - input type: {type(content)}"
)

# Avoid repeated lookups and expensive debug statements wherever possible.
if isinstance(content, str):
result = [self._convert_content_str_to_input_text(content, role)]
verbose_logger.debug(f"Chat provider: String content -> {result}")
return result

elif isinstance(content, list):
result = []
append_result = result.append
# Pre-bind conversion functions for less attribute lookup
convert_str = self._convert_content_str_to_input_text

for i, item in enumerate(content):
verbose_logger.debug(
f"Chat provider: Processing content item {i}: {type(item)} = {item}"
)
if isinstance(item, str):
converted = self._convert_content_str_to_input_text(item, role)
result.append(converted)
converted = convert_str(item, role)
append_result(converted)
verbose_logger.debug(f"Chat provider: -> {converted}")
elif isinstance(item, dict):
# Handle multimodal content
original_type = item.get("type")
if original_type == "text":
converted = self._convert_content_str_to_input_text(
item.get("text", ""), role
)
result.append(converted)
converted = convert_str(item.get("text", ""), role)
append_result(converted)
verbose_logger.debug(f"Chat provider: text -> {converted}")
elif original_type == "image_url":
# Map to responses API image format
# Cast only once, save method lookup
converted = cast(
dict,
self._convert_content_to_responses_format_image(
cast(ChatCompletionImageObject, item), role
cast("ChatCompletionImageObject", item), role
),
)
result.append(converted)
append_result(converted)
verbose_logger.debug(
f"Chat provider: image_url -> {converted}"
)
Expand All @@ -479,35 +488,33 @@ def _convert_content_to_responses_format(
item_type = original_type or "input_text"
if item_type == "image":
converted = {"type": "input_image", **item}
result.append(converted)
append_result(converted)
verbose_logger.debug(
f"Chat provider: image -> {converted}"
)
elif item_type in [
elif item_type in (
"input_text",
"input_image",
"output_text",
"refusal",
"input_file",
"computer_screenshot",
"summary_text",
]:
):
# Already in responses API format
result.append(item)
append_result(item)
verbose_logger.debug(
f"Chat provider: passthrough -> {item}"
)
else:
# Default to input_text for unknown types
converted = self._convert_content_str_to_input_text(
str(item.get("text", item)), role
)
result.append(converted)
converted = convert_str(str(item.get("text", item)), role)
append_result(converted)
verbose_logger.debug(
f"Chat provider: unknown({original_type}) -> {converted}"
)
verbose_logger.debug(f"Chat provider: Final converted content: {result}")
return result

else:
result = [self._convert_content_str_to_input_text(str(content), role)]
verbose_logger.debug(f"Chat provider: Other content type -> {result}")
Expand Down