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
- Stores your documents and organizes them
- Finds connections between different parts of your documents
- Lets you search through your documents quickly
- Uses AI to answer questions about your documents
How to Use Wizz
-
Install it:
pip install wizz
-
Set up AI access (you'll need an OpenAI account):
echo "OPENAI_API_KEY=your_api_key_here" > .env
-
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 Wizzindex
: Prepare your documents for searching and find connectionssearch
: Look for information in your documentsinteract
: Ask questions about your documents and get AI-powered answersdelete
: 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
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | d547c576330baffc604d42192a4d1cbbd2d53d10ee9eef40c87d8619d0de8503 |
|
MD5 | 2c434277873e1f0ec9f73922567df4d1 |
|
BLAKE2b-256 | f1ad4c4c2c1f3ba93e8aaedc791ec9fc8bb8f6ab59272f40cb72c200a2f8f035 |
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3783964a527fdf618808a65e4e0898c26ac07f5894a351286a2a20f35bf53624 |
|
MD5 | 9d6d87f3d47a677468a2e2bc9524b358 |
|
BLAKE2b-256 | 58122e67f951170c0278e228d192eb7dae4ff65834b431a023ad8184f6ad15b9 |