notes.md

NOTES

Agent's questions submissions time 2025-05-21 17:36:23 commit a2b205e6ac1b79be5119793116172bc6225f9007

Takeaways

-It was helpful keeping track of what the files were (here).

• Building tests along with the tools was good practice.
• I lost track of what I was doing when trying to push the project forward while tired.
• I must have being more thorough with the requirements since the start. Right now I am not sure of what the agent must deliver and how.
• The HF Spaces environment required a little more study.
• Patching the questions was brilliant.

general notes

• There are 5 questions that require the interpretation of a file

utilities/ Python scripts:

• random_questions.py: fetches random questions from the GAIA API
• compare_question_set.py: checks if 2 sets of questions are the same
• fetch_all_questions.py: fetches all questions from the GAIA API
• random_question_submit.py: fetches a random question and submits the answer to the GAIA API
• evaluate_local.py: evaluates questions locally
• common_questions.py: finds common questions between validation.json and gaia_questions.json, and formats them in json.
• check_gpt4all.py: checks if the gpt4all model is working

src/ agent's source files

• speech_to_text.py: speech-to-text tool
• file_processing.py: file processing tool

data

• /downloaded_files/: folder with the 5 question's files
• /question_set/: files with the different jsons
  • gaia_questions.json and new_gaia_questions.json: 20 original questions
  • validation.json: full GAIA validation set
  • common_questions.json: gaia_questions with the answers from validation.json

docs/ Project documentation:

• project_overview.md: overview of the project
• API.md: API documentation
• scorer.py: GAIA scoring function
• submission_instructions.py: GAIA submission instructions
• pdf/: PDF files for the project
• testing_recipe.md: testing recipe for the project (not used yet)
• evaluate_local_commands.md: commands to evaluate the agent locally
• log.md: log of the project

question_set: GAIS question set

• gaia_questions.json: JSON file with the GAIA question set
• new_gaia_questions.json: JSON file with the new GAIA question set
• validation.json: JSON file with the validation set from GAIA
• common_questions.json: JSON file with the common questions between validation.json and gaia_questions.json, including the answers

tests/

• conftest.py: tests configuration
• different test for the different tools

answers/ agent's answers

• agent_answers.json: JSON file with the agent's answers