TaskGen Ask Me Anything #1

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.
Repo: github.com/simbianai/taskgen
Companion Notebook: github.com/simbianai/taskgen/...
~~
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.
Discord: / discord
LinkedIn: / chong-min-tan-94652288
Online AI blog: delvingintotech.wordpress.com/
Twitter: / johntanchongmin
Try out my games here: simmer.io/@chongmin

[@johntanchongmin]

Companion Notebook to this session: github.com/simbianai/taskgen/blob/main/TaskGen%20AMA_18May2024.ipynb

[@johntanchongmin]

After this session, I went to massively improve TaskGen so that it works better for non-structured tasks and also not return so many errors due to list constraining or enum constrainer in Agent subtask generation logic. The Agent is also much more receptive to environment outputs and can modify it's plan more dynamically as it is not constrained to a list of steps anymore. The notebook for this session has been updated accordingly. Try out the new TaskGen v2.0.1 today!

[@snehotoshbanerjee1938]

Hi John, any reason not going with yaml vis-a-vis JSON because yaml format consume less token consumption compared to json.

[@johntanchongmin]

I have considered yaml before. I don't think the llms are ready for it yet. I may change my mind in the future and do a yaml version of strictjson haha.