[Good First Issue]: Replicate Existing Cookbooks and Create New Examples - Batch 3

[ijindal1]

trafficstars

For context, see: CONTRIBUTING.md and cookbooks/README.md

Overview

We're looking for contributors to help expand our collection of Jupyter notebooks (cookbooks) that demonstrate various AI and automation tasks using Julep's features. This is a great opportunity for newcomers to get familiar with Julep and contribute to the project!

Objectives

1. Replicate existing cookbooks to ensure they're up-to-date and functioning correctly.
2. Create new cookbooks based on the ideas listed in the cookbooks/README.md file.

Tasks

1. Replicating Existing Cookbooks

• Choose one or more of the existing cookbooks from the list in cookbooks/README.md.
• Follow the instructions in the notebook to run it in Google Colab.
• Verify that all cells execute without errors and produce the expected outputs.
• If you encounter any issues or outdated information, document them for updating.

2. Creating New Cookbooks

• Select an idea from the "Potential Cookbooks for Contributors" section in cookbooks/README.md.
• Create a new Jupyter notebook following the structure of existing cookbooks.
• Implement the chosen use case using Julep's features.
• Ensure your notebook includes:
  • A clear introduction and overview of the task
  • Step-by-step implementation with explanations
  • Proper error handling and user guidance
  • A conclusion summarizing the key learnings

Guidelines for Creating New Cookbooks

1. Naming Convention: Name your notebook following the pattern XX-Descriptive_Name.ipynb, where XX is the next available number in the sequence.

2. Structure:

   • Start with an introduction explaining the purpose of the cookbook.
   • Include a cell for installing the Julep client.
   • Create sections for each major step (e.g., Creating an Agent, Defining a Task, Creating an Execution).
   • Add markdown cells to explain concepts and code.

3. Code Quality:

   • Ensure your code is well-commented and follows PEP 8 style guidelines.
   • Use meaningful variable names.
   • Handle potential errors gracefully.

4. Documentation:

   • Explain each step clearly, assuming the reader is new to Julep.
   • Include links to relevant Julep documentation where appropriate.

5. Testing:

   • Test your notebook thoroughly in Google Colab to ensure it runs without errors.
   • Include sample outputs where relevant.

6. Update README.md:

   • Add your new cookbook to the table in cookbooks/README.md.
   • Include a brief description and mark it as implemented.

How to Contribute

1. Fork the repository.
2. Create a new branch for your cookbook (e.g., cookbook/weather-notification-service).
3. Develop your cookbook following the guidelines above.
4. Test your notebook thoroughly.
5. Commit your changes and push to your fork.
6. Open a pull request with a clear description of your contribution.

Resources

• Julep Documentation
• Existing Cookbooks
• CONTRIBUTING.md

Need Help?

If you have any questions or need assistance, please don't hesitate to ask in the comments of this issue or reach out on our Discord channel.

We're excited to see your contributions and help grow the Julep cookbook collection!

---

Long-ass list of ideas

17. Event-Driven Notification System Description: Triggers notifications based on specific events such as stock price changes, weather alerts, or user activities. Features: Tools: finance, weather, slack Step Types: Tool Call, Evaluate, Conditional Logic, Send Notification, Schedule
18. Automated Data Cleaning and Transformation Description: Cleans and transforms raw data by removing inconsistencies, normalizing formats, and preparing it for analysis. Features: Tools: wikipedia, huggingface Step Types: Tool Call, Evaluate, Conditional Logic, Log, Transform Data (Set)
19. Recursive Task Execution for Project Management Description: Breaks down large projects into smaller tasks, executes them recursively, and tracks overall progress. Features: Tools: google_calendar, sendgrid Step Types: Loop (Foreach), Tool Call, Conditional Logic, Set, Evaluate, Return
20. Parallel Data Processing Pipeline Description: Processes large datasets in parallel, aggregates results, and provides comprehensive reports. Features: Tools: hacker_news, finance Step Types: Parallel Execution, Tool Call, Evaluate, Aggregate Results (MapReduce), Generate Report (Prompt), Return
21. Dynamic Content Recommendation Engine Description: Analyzes user behavior, recommends personalized content, and updates recommendations based on feedback. Features: Tools: wikipedia, huggingface, slack Step Types: Tool Call, Evaluate, Conditional Logic, Update Recommendations (Set), Loop, Log
22. Automated Compliance Monitoring System Description: Monitors transactions and activities to ensure compliance with regulatory standards, flags violations, and generates reports. Features: Tools: finance, slack, sendgrid Step Types: Tool Call, Evaluate, Conditional Logic, Log, Send Alerts, Generate Reports
23. Intelligent Resume Screening Workflow Description: Screens resumes, evaluates candidates based on predefined criteria, and forwards qualified candidates to HR. Features: Tools: dummy, huggingface, slack Step Types: Tool Call, Evaluate, Conditional Logic, Log, Forward Resumes, Loop
24. Automated Code Review and Deployment Pipeline Description: Reviews code commits, runs automated tests, and deploys to production if all checks pass. Features: Tools: api_call, slack, sendgrid Step Types: Tool Call, Evaluate, Conditional Logic, Run Tests (Tool Call), Deploy (Tool Call), Send Notifications, Log