ThinkGPT

Agent techniques to augment your LLM and push it beyong its limits

About ThinkGPT

ThinkGPT is a Python library developed by Jina AI aimed at implementing Chain of Thoughts for Large Language Models (LLMs), prompting the model to think, reason, and to create generative agents. The library aims to help with the following:

  • Solve limited context with long memory and compressed knowledge
  • Enhance LLMs' one-shot reasoning with higher order reasoning primitives
  • Add intelligent decisions to your code base

ThinkGPT features

  • Memory ūü߆: GPTs that can remember experience
  • Self-refinement ūüĒß: Improve model-generated content by addressing critics
  • Compress knowledge ūüĆź: Compress knowledge and fit it in LLM's context either by anstracring rules out of observations or summarize large content
  • Inference ūüí°ÔłŹ: Make educated guesses based on available information
  • Natural Language Conditions ūüďĚ: Easily express choices and conditions in natural language
  • Efficient and Measurable GPT context length ūüďź
  • Extremely easy setup and pythonic API ūüéĮ thanks to DocArray

ThinkGPT screenshots

Ready to start building?

At Apideck we're building the world's biggest API network. Discover and integrate over 12,000 APIs.

Check out the API Tracker