Skip to main content

A terminal-based LLM chat client with knowledge retrieval.

Project description

Wizz: AI-Enhanced Document Tool

Wizz is a proof-of-concept tool that helps you work with large collections of documents using AI. It can understand your documents and answer questions about them.

What Wizz Does

  1. Stores your documents and organizes them
  2. Finds connections between different parts of your documents
  3. Lets you search through your documents quickly
  4. Uses AI to answer questions about your documents

How to Use Wizz

  1. Install it:

    pip install wizz
    
  2. Set up AI access (you'll need an OpenAI account):

    echo "OPENAI_API_KEY=your_api_key_here" > .env
    
  3. Use Wizz:

    wizz knowledge load --context-name "my_docs" --load-path "/path/to/your/documents"
    wizz knowledge index --context-name "my_docs"
    wizz knowledge interact --context-name "my_docs"
    

Main Commands

  • load: Add your documents to Wizz
  • index: Prepare your documents for searching and find connections
  • search: Look for information in your documents
  • interact: Ask questions about your documents and get AI-powered answers
  • delete: Remove a set of documents from Wizz

For more details, type:

wizz knowledge --help

What You Need

  • Python 3.11 or newer
  • An OpenAI API key

Technical Notes

While Wizz currently works as a standalone tool, its core features are designed with future web integration in mind. The code uses async programming, preparing it for potential use with ASGI web servers in the future. I developed a custom async wrapper library called async-annoy for the vector search tool 'annoy' (by Spotify). You can find it here.

Important Note

Wizz is an experimental proof-of-concept and learning tool. It's not ready for real-world use. Using it with OpenAI's API may incur costs.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

wizz-0.2.2.tar.gz (46.5 kB view details)

Uploaded Source

Built Distribution

wizz-0.2.2-py3-none-any.whl (19.4 kB view details)

Uploaded Python 3

File details

Details for the file wizz-0.2.2.tar.gz.

File metadata

  • Download URL: wizz-0.2.2.tar.gz
  • Upload date:
  • Size: 46.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.6 Darwin/23.4.0

File hashes

Hashes for wizz-0.2.2.tar.gz
Algorithm Hash digest
SHA256 d547c576330baffc604d42192a4d1cbbd2d53d10ee9eef40c87d8619d0de8503
MD5 2c434277873e1f0ec9f73922567df4d1
BLAKE2b-256 f1ad4c4c2c1f3ba93e8aaedc791ec9fc8bb8f6ab59272f40cb72c200a2f8f035

See more details on using hashes here.

File details

Details for the file wizz-0.2.2-py3-none-any.whl.

File metadata

  • Download URL: wizz-0.2.2-py3-none-any.whl
  • Upload date:
  • Size: 19.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.6 Darwin/23.4.0

File hashes

Hashes for wizz-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 3783964a527fdf618808a65e4e0898c26ac07f5894a351286a2a20f35bf53624
MD5 9d6d87f3d47a677468a2e2bc9524b358
BLAKE2b-256 58122e67f951170c0278e228d192eb7dae4ff65834b431a023ad8184f6ad15b9

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page