summawise 0.5.4

Summarize information from vectorized files using OpenAI's powerful models, and explore data further with an interactive prompt for deep dives into content.

summawise

Summarize information from files, links, and vectorized data using OpenAI's powerful models. Explore data further and generate code/information using an interactive prompt for deep dives into content. The beta API features that are built in make it superior to a standard LLM in the context of code generation relative to existing context/codebases.

Installation

For the sake of convenience (and to be added to your $PATH), the program is available via PyPI:

pip install --upgrade summawise

Notes

This tool uses OpenAI API features which are currently in beta.

Resources:

• Assistants API
• Threads
• Vector Stores
• File Search (assistant tool)
• Code Interpreter (assistant tool)

Information

The following inputs are supported:

• YouTube video URLs. (Transcript is extracted and used as text)
• Local files. (Any type of content, file will be uploaded byte for byte)
• Local directories. (Includes files in nested directories)
• Other URLs, depending on the response content. (Text content, PDF files, and HTML are all supported)

Support for a wider variety of input may be added in the future.

Potential improvements:

• Archive support (Both URLs and local files - automatically extract/upload contents of .zip/.tar.gz files)
• Extract natural language from certain types of content. (Ex: html/pdf)