TaskGen is an agentic framework which attempts to solve complex arbitrary problems by breaking them down into subtasks, and mapping each subtask to an equipped function to execute.
In order to reduce verbosity (and hence token usage) that is typical of conversational-based agents like AutoGen or BabyAGI, it uses a JSON format for outputs. Specifically, TaskGen uses StrictJSON, a Large Language Model (LLM) output parser with type checking which outputs in JSON format, ensuring concise output generation.
Key to the philosophy of TaskGen is the management of information/memory on a need-to-know basis. This reduces context length for each part of the process, which leads to a better functioning overall system.
0:00 Introduction
4:45 Imports
5:27 Basic Agent
23:55 Stepping through Agent one step at a time
27:24 When to use StrictJSON vs TaskGen
30:48 Agent with Functions
1:01:50 Function Calling
1:06:44 Shared Variables
1:26:55 Global Context
1:42:40 Discussion on Memory
~~
AI and ML enthusiast. Likes to think about the essences behind breakthroughs of AI and explain it in a simple and relatable way. Also, I am an avid game creator.
15