About Baby AGI

Baby AGI is an AI-powered task management system developed by Yohei Nakajima. This Python script uses OpenAI and vector databases like Chroma or Weaviate to create, prioritize, and execute tasks. The system generates tasks based on the outcomes of previous tasks and a predefined objective, leveraging OpenAI’s natural language processing capabilities for task creation and Chroma/Weaviate for storing and retrieving task results.

Here are four key features of Baby AGI

  1. Task Execution: The system pulls the first task from the task list and sends it to the execution agent, which uses OpenAI’s API to complete the task based on the context. The result is enriched and stored in Chroma/Weaviate.
  2. Task Creation: OpenAI’s API is used to create new tasks based on the objective and the result of the previous task. The function returns the new tasks as a list of dictionaries, where each dictionary contains the name of the task.
  3. Task Prioritization: OpenAI’s API is used to reprioritize the task list. The function takes one parameter, the ID of the current task, and returns the reprioritized task list as a numbered list.
  4. Data Storage and Retrieval: The script uses Chroma/Weaviate to store and retrieve task results for context. The script creates a Chroma/Weaviate collection based on the table name specified in the TABLE_NAME variable.