tonykipkemboi / youtube_yapper_trapper

CrewAI agents that gather and analyze YouTube comments to generate insights to inform better content creation.

YoutubeYapperTrapper Crew

Welcome to the YoutubeYapperTrapper Crew project, powered by CrewAI + AgentOps for observability + YouTube Data API. This project allows agents to take a given YouTube URL, extracts all the comments, and generates a final report with insights to inform better content creation.

Crew architecture diagram

Video tutorial

Installation

Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses Poetry for dependency management and package handling, offering a seamless setup and execution experience.

First, if you haven't already, install Poetry:

pip install poetry

Next, navigate to your project directory and install the dependencies:

1. First lock the dependencies and then install them:

poetry lock

poetry install

Customizing

Add your OPENAI_API_KEY into the .env file if you want to use it.

• Modify src/youtube_yapper_trapper/config/agents.yaml to define your agents
• Modify src/youtube_yapper_trapper/config/tasks.yaml to define your tasks
• Modify src/youtube_yapper_trapper/crew.py to add your own logic, tools and specific args
• Modify src/youtube_yapper_trapper/main.py to add custom inputs for your agents and tasks

Running the Project

Rename the .env_example file to .env, add your API keys, and save the file.

To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:

poetry run youtube_yapper_trapper

This command initializes the youtube-yapper-trapper Crew, assembling the agents and assigning them tasks as defined in your configuration.

This example, unmodified, will run the create a report.md file with the output of a research on LLMs in the root folder.

Understanding Your Crew

The youtube-yapper-trapper Crew is composed of multiple AI agents, each with unique roles, goals, and tools. These agents collaborate on a series of tasks, defined in config/tasks.yaml, leveraging their collective skills to achieve complex objectives. The config/agents.yaml file outlines the capabilities and configurations of each agent in your crew.

Support

For support, questions, or feedback regarding the YoutubeYapperTrapper crew, CrewAI, or AgentOps.

• Visit CrewAI documentation
• Reach out to me through my GitHub repository
• Joing CrewAI Discord
• Chat wtih CrewAI docs
• Check out AgentOps!
• Also don't forget to subscribe to my channel for more awesome content!

Let's create wonders together with the power and simplicity of CrewAI.

youtube_yapper_trapper's Issues

task.yaml issue

Hi,

Hoping you can help me out. Is this a valid task definition? Specifically:

• Is it valid to refer to taks in the description using a list format ["report_writer_dashboard_task", "predictive_analyst_task"]
• Is it valid to define a context for a task using the 'context:>' passing it a list of tasks

trade_analyst_task:
description: >
Provide your detailed recommendation as to whether to BUY {investment}. Use bullet-points.
Input into this task are:
- the output contexts of the following tasks: ["report_writer_dashboard_task", "predictive_analyst_task"]

You review the written report and check if it meets the following BUY criteria - 
  1. Positive absolute amd relative performance over 7d, 30d and 90d
  2. Net Asset Value greater than $10,000,000
  3. No negative sentiment on the fund last 3 months.
  4. Redemption not exceeding 30 days
  5. Overall rating greater than 2 stars
  6. Overall exposure to developed countries greater than 60%
  7. Positive or neutral market sentiment
  8. Positive 7 day future value prediction from the ["predictive_analyst_task"]
  9. Positive 30 day future value prediction from the ["predictive_analyst_task"]
  10. Positive 60 day future value prediction from the ["predictive_analyst_task"]
  11. Positive 90 day future value prediction from the ["predictive_analyst_task"]

Make sure to support your findings by referencing actual performance values of {investment_name} alongside each criteria.

Agent Tool parameters are:
  - fund: {investment}

context: >
["report_writer_dashboard_task", "predictive_analyst_task"]
expected_output: >
Detailed BUY recommendation including referencing actual performance values alongside each criteria. Use bullet-points.

Best,
George.