-
Notifications
You must be signed in to change notification settings - Fork 2.5k
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.
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
Stateless models #1976
base: main
Are you sure you want to change the base?
Stateless models #1976
Conversation
def set_functions(self, functions: Dict[str, Function]) -> None: | ||
self._functions = functions | ||
|
||
# @staticmethod |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
keeping around just in case, will be deleted once this PR is ready
@@ -238,60 +204,6 @@ def _get_function_calls_to_run( | |||
function_calls_to_run.append(_function_call) | |||
return function_calls_to_run | |||
|
|||
def add_tool( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Gemini will need a refactor, since it has a custom add_tools
if self.tool_choice is None: | ||
request_params["tool_choice"] = "auto" | ||
else: | ||
if self.tool_choice is not None: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
aren't you missing auto
as a default here?
libs/agno/agno/models/groq/groq.py
Outdated
|
||
# -*- Generate response | ||
metrics.start_response_timer() | ||
assistant_message.metrics.start_timer() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is nice
libs/agno/agno/models/groq/groq.py
Outdated
metrics.completion_tokens += 1 | ||
if metrics.completion_tokens == 1: | ||
metrics.time_to_first_token = metrics.response_timer.elapsed | ||
assistant_message.metrics.completion_tokens += 1 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should this not use the completion tokens from the response? I always thought this was weird, because a delta isn't necessarily one token right?
Description
Type of change
Please check the options that are relevant: