feat: add tool params #210
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
0xArdi
commented
Apr 9, 2024
| @@ -396,7 +399,8 @@ def _prepare_task(self, task_data: Dict[str, Any]) -> None: | |||
| executing_task = cast(Dict[str, Any], self._executing_task) | |||
| executing_task["timeout_deadline"] = time.time() + self.params.task_deadline | |||
| executing_task["tool"] = task_data["tool"] | |||
| executing_task["model"] = task_data.get("model", None) | |||
| executing_task["model"] = task_data.get("model", tool_params.pop('default_model', None)) | |||
There was a problem hiding this comment.
default model will be picked up here
0xArdi
commented
Apr 9, 2024
| @@ -11,6 +11,8 @@ fingerprint: | |||
| fingerprint_ignore_patterns: [] | |||
| entry_point: prediction_request_rag_claude.py | |||
| callable: run | |||
| params: | |||
| default_model: claude-3-haiku-20240307 | |||
There was a problem hiding this comment.
any param defined here will be reflected in the metadata stored on-chain
|
@0xArdi should we rebase/merge from main? |
cyberosa
reviewed
Apr 24, 2024
| fingerprint_ignore_patterns: [] | ||
| entry_point: prediction_request_rag.py | ||
| callable: run | ||
| params: | ||
| default_model: claude-3-sonnet-20240229 |
There was a problem hiding this comment.
Where is this parameter used? At the python file the default model is hard coded
There was a problem hiding this comment.
You can see in Ardian's comments above.
| fingerprint_ignore_patterns: [] | ||
| entry_point: prediction_request_reasoning.py | ||
| callable: run | ||
| params: | ||
| default_model: claude-3-sonnet-20240229 |
| temperature: Optional[float] = LLM_SETTINGS[DEFAULT_MODEL]["temperature"], | ||
| max_tokens: Optional[int] = LLM_SETTINGS[DEFAULT_MODEL]["default_max_tokens"], | ||
| temperature: Optional[float] = LLM_SETTINGS["gpt-4-0125-preview"]["temperature"], | ||
| max_tokens: Optional[int] = LLM_SETTINGS["gpt-4-0125-preview"]["default_max_tokens"], |
There was a problem hiding this comment.
you don't use the same default model as defined in the component.yaml file
There was a problem hiding this comment.
I don't think this default can ever be used (was the same before I made the changes). Could change them from optional in future I guess.
cyberosa
approved these changes
Apr 24, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds tool params.