-
Notifications
You must be signed in to change notification settings - Fork 0
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
LLM analysis #6
LLM analysis #6
Conversation
The `validate_tcx_file` function now returns a tuple with a boolean indicating the validation result and the TCXReader object. This change allows for performing LLM analysis on the TCX data if the user chooses to do so.
The `requirements.txt` file has been updated to include specific versions for the `defusedxml`, `pandas`, `python-dotenv`, and `questionary` packages. This ensures that the project uses the specified versions of these dependencies. Note: The recent user commits and recent repository commits are not directly related to the code changes in this case, so they are not considered for the commit message.
This commit adds an AI Assistant prompt for LLM analysis in the `perform_llm_analysis` function. The prompt provides guidance to athletes on how to improve their performance based on the training session data. The prompt includes information about the sport, the data, and an optional plan. This feature aims to enhance the user experience and help athletes make informed decisions to improve their performance.
This commit improves the AI Assistant prompt in the `perform_llm_analysis` function for LLM analysis. The prompt now includes a CSV data section, providing athletes with a clearer understanding of the training session data. This enhancement aims to help athletes identify positive and negative points in their performance and provides recommendations for improvement in the next session. Note: The recent user commits and recent repository commits are not directly related to the code changes in this case, so they are not considered for the commit message.
This commit adds the OpenAI language model for LLM analysis in the `perform_llm_analysis` function. The model is initialized with the OpenAI API key and configured with the `gpt-4o` model name and a maximum token limit of 500. The AI analysis is performed using the model, and the response is logged. This enhancement aims to provide more accurate and insightful analysis for athletes to improve their performance.
This commit refactors the perform_llm_analysis function by extracting the preprocessing of trackpoints data into a separate function called preprocess_trackpoints_data. The function takes the TCXReader object as input and returns a preprocessed DataFrame. This refactoring improves code readability and maintainability by separating concerns and promoting code reuse.
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.
Thanks for contributing this PR! We will validade soon.
This commit refactors the ask_file_path function in the main.py file. The function now includes separate logic for when the file location is "Provide path" and when it is not. It also introduces a validation function to check if the provided path is a valid file or an empty string. This refactoring improves code readability and maintainability by separating concerns and promoting code reuse.
…peaks into llm-analysis
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #6 +/- ##
==========================================
- Coverage 99.30% 99.26% -0.05%
==========================================
Files 2 2
Lines 289 407 +118
==========================================
+ Hits 287 404 +117
- Misses 2 3 +1
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
No description provided.