fix: enhance robustness in AgentComponent by checking attributes before getting them #7251
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
…sult handling * Added support for a detailed thinking feature in the NVIDIAModelComponent, allowing users to enable this functionality through the build configuration. * Refactored the get_chat_result method to prepend a detailed thinking prefix to the system message when the feature is enabled, with error handling for potential issues during this process. * Removed the detailed thinking logic from the LCModelComponent to streamline the codebase.
* Updated the _build_llm_model method to include a check for the existence of attributes before adding them to model_kwargs, preventing potential AttributeError exceptions and improving robustness.
* Standardized the "value" field in multiple starter project JSON files to ensure uniformity in code formatting and structure. * Improved readability by maintaining consistent import statements and function definitions across projects. * This change affects the following files: Instagram Copywriter.json, Market Research.json, News Aggregator.json, Price Deal Finder.json, Research Agent.json, SaaS Pricing.json, and Sequential Tasks Agents.json.
dosubot
bot
added
the
size:M
github-actions
bot
added
bug
| value=False, | ||
| info="Enable detailed thinking.", | ||
| advanced=True, | ||
| ).to_dict() |
There was a problem hiding this comment.
Why was this necessary? is this preferred to having it in inputs like it is:
BoolInput(
name="detailed_thinking",
display_name="Detailed Thinking",
info="If true, the model will return a detailed thought process. Only supported by reasoning models.",
value=False,
show=False,
),
There was a problem hiding this comment.
It is only used by the NVIDIA componenent from what I understand and it was as base input.
I was having a lot of trouble getting this to work, by the way.
There was a problem hiding this comment.
I'm not sure I understand. On line 49 of src/backend/base/langflow/components/models/nvidia.py, there's already the detailed_thinking input. Was that not working for you? I seemed to work during my testing.
CodSpeed Performance ReportMerging #7251 will degrade performances by 41.77%Comparing Summary
Benchmarks breakdown
|
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.
Introduce a detailed thinking feature for NVIDIA models, improving user configuration options. Enhance the robustness of model kwargs construction in the AgentComponent to prevent potential errors. Standardize JSON files in the starter project for better code consistency and readability.