This repository was archived by the owner on Nov 10, 2025. It is now read-only.
Allow setting custom LLM for the vision tool#294
Merged
danielfsbarreto merged 4 commits intomainfrom Apr 28, 2025
Merged
Conversation
Defaults to gpt-4o-mini otherwise
lorenzejay
suggested changes
Apr 28, 2025
Comment on lines
40
to
53
|
|
||
| def __init__(self, llm: LLM | None = None, **kwargs): | ||
| super().__init__(**kwargs) | ||
|
|
||
| self._llm = llm | ||
|
|
||
| @property | ||
| def client(self) -> OpenAI: | ||
| """Cached OpenAI client instance.""" | ||
| if self._client is None: | ||
| self._client = OpenAI() | ||
| return self._client | ||
| def llm(self) -> LLM: | ||
| """Default LLM instance.""" | ||
| if self._llm is None: | ||
| self._llm = LLM( | ||
| model="gpt-4o-mini", | ||
| ) | ||
| return self._llm |
Contributor
There was a problem hiding this comment.
what if user wants to add a specific model ?
lets add a model_name arg then just add that model.
ex) could be sonnet model with vision
Collaborator
Author
There was a problem hiding this comment.
@lorenzejay, they would be able to pass down a whole new LLM... including Sonnet
Contributor
There was a problem hiding this comment.
@danielfsbarreto did you try initialize a Tool this way
VisionTool(_client=YOUR_MODEL)I think it should works because _client is not a private attribute
lucasgomide
reviewed
Apr 28, 2025
| return self._llm | ||
|
|
||
| def _run(self, **kwargs) -> str: | ||
| def _run(self, **kwargs): |
Contributor
There was a problem hiding this comment.
Tools must return a string whenever possible
Comment on lines
40
to
53
|
|
||
| def __init__(self, llm: LLM | None = None, **kwargs): | ||
| super().__init__(**kwargs) | ||
|
|
||
| self._llm = llm | ||
|
|
||
| @property | ||
| def client(self) -> OpenAI: | ||
| """Cached OpenAI client instance.""" | ||
| if self._client is None: | ||
| self._client = OpenAI() | ||
| return self._client | ||
| def llm(self) -> LLM: | ||
| """Default LLM instance.""" | ||
| if self._llm is None: | ||
| self._llm = LLM( | ||
| model="gpt-4o-mini", | ||
| ) | ||
| return self._llm |
Contributor
There was a problem hiding this comment.
@danielfsbarreto did you try initialize a Tool this way
VisionTool(_client=YOUR_MODEL)I think it should works because _client is not a private attribute
- Added support for setting a custom model identifier with a default of "gpt-4o-mini". - Introduced properties for model management, allowing dynamic updates and resetting of the LLM instance. - Updated the initialization method to accept an optional LLM and model parameter. - Refactored the image processing logic for clarity and efficiency.
Contributor
|
@lucasgomide can you check the latest 2 commits 🙏🏼 |
lucasgomide
reviewed
Apr 28, 2025
|
|
||
| return response.choices[0].message.content | ||
|
|
||
| return response |
Contributor
There was a problem hiding this comment.
I guess response is not a string instance, right?
Suggested change
| return response | |
| return response.choices[0].message.content |
lucasgomide
approved these changes
Apr 28, 2025
lorenzejay
approved these changes
Apr 28, 2025
mplachta
pushed a commit
to mplachta/crewAI-tools
that referenced
this pull request
Aug 27, 2025
* Allow setting custom LLM for the vision tool Defaults to gpt-4o-mini otherwise * Enhance VisionTool with model management and improved initialization - Added support for setting a custom model identifier with a default of "gpt-4o-mini". - Introduced properties for model management, allowing dynamic updates and resetting of the LLM instance. - Updated the initialization method to accept an optional LLM and model parameter. - Refactored the image processing logic for clarity and efficiency. * docstrings * Add stop config --------- Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
This file contains hidden or 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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
3 participants
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.
Defaults to gpt-4o-mini otherwise