Where is the engineering part in "prompt engineer"?

• simpleaichat

  22 3,376 8.7 Python

  Python package for easily interfacing with chat apps, with robust features and minimal code complexity.

Source: I spend a lot of time working with prompts/ChatGPT and have developed open source libraries based on system prompt engineering.

• guidance

  89 12,248 9.5 Jupyter Notebook

  Discontinued A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance] (by microsoft)

  

If you learn a prompt templating language like Guidance, and use it to produce semantic, valid, parseable output (maybe you want valid json, xml, yaml etc) interweaves with clear structure (eg interweave prompt response into a numbered bullet list with a fixed template) you can call it Prompt Design and it’s less cringey than “prompt engineering”.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• babyds

  5 66 3.5 Python

  An AI-powered data science pipeline

  

Try chaining a few prompts together with langchain. You can build cool things like an automated data analysis bot.

• aitextgen

  19 1,826 1.8 Python

  A robust Python tool for text-based AI training and generation using GPT-2.

It's literally a wrapper for the ChatGPT API (currently). I have another library for training models from scratch but haven't had time to work on it.

Suggest a related project