Refactor tutorials #3
Open
Conversation
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
This commit refactors the AI agent tutorial scripts in the repository to enhance clarity, robustness, adherence to best practices, and educational value.
Key changes include:
**Part 1: `1_phidata_finance_agent` Tutorials**
- Standardized Configuration: LLM model IDs are now configurable via environment variables (e.g., `GROQ_MODEL_ID`, `OPENAI_MODEL_ID`) with defaults. I added checks for API key presence (`GROQ_API_KEY`, `OPENAI_API_KEY`).
- Dependencies: I created `requirements.txt` for this set of tutorials.
- Enhanced `2_finance_agent_llama.py`: I improved the `get_company_symbol` tool by expanding the example dictionary and adding comments about using a proper API/database in real applications.
- Refined `3_agent_teams_openai.py`: I added detailed comments explaining how to switch between OpenAI and Groq models and clarified the agent team/delegation concept.
- General Code Quality: I added `try-except` blocks for agent API calls, improved comments for clarity, and ensured consistent formatting across all three finance agent scripts.
**Part 2: `2_mcp_leave_management` MCP Server Tutorial**
- Improved Project Metadata: I updated `pyproject.toml` with a more relevant name (`mcp_leave_management_tutorial`) and description.
- Database Refactoring: I replaced the in-memory Python dictionary with an SQLite database (`leave_management.db`).
- I created `database.py` to handle all SQLite operations (connection, table creation, data initialization, CRUD operations for leave data).
- I updated `main.py` to use `database.py` for all data persistence.
- Enhanced Tool Logic in `main.py`:
- I significantly improved the `apply_leave` tool with comprehensive input validation for `leave_dates` (format, valid date values, past dates, already booked dates).
- General Code Quality:
- I reviewed and improved `main.py` and `database.py` for clarity, adding module-level and inline comments, ensuring consistent type hinting, and updating docstrings.
- I updated `README.md` in `2_mcp_leave_management/` to include information about the new SQLite database, its creation, and initialization.
I made all changes according to the established plan, and I conducted a final review of all modified files.
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.
No description provided.