# 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](https://github.com/ryzhakar/async-annoy).
## 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.
Raw data
{
"_id": null,
"home_page": "https://github.com/ryzhakar/wizz",
"name": "wizz",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.11",
"maintainer_email": null,
"keywords": "chat-client, local-LLMs, terminal, query-response, AI, natural-language-processing",
"author": "Arthur Ryzhak",
"author_email": "ryzhakar@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/f1/ad/4c4c2c1f3ba93e8aaedc791ec9fc8bb8f6ab59272f40cb72c200a2f8f035/wizz-0.2.2.tar.gz",
"platform": null,
"description": "# Wizz: AI-Enhanced Document Tool\n\nWizz 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.\n\n## What Wizz Does\n\n1. Stores your documents and organizes them\n2. Finds connections between different parts of your documents\n3. Lets you search through your documents quickly\n4. Uses AI to answer questions about your documents\n\n## How to Use Wizz\n\n1. Install it:\n ```\n pip install wizz\n ```\n\n2. Set up AI access (you'll need an OpenAI account):\n ```\n echo \"OPENAI_API_KEY=your_api_key_here\" > .env\n ```\n\n3. Use Wizz:\n ```\n wizz knowledge load --context-name \"my_docs\" --load-path \"/path/to/your/documents\"\n wizz knowledge index --context-name \"my_docs\"\n wizz knowledge interact --context-name \"my_docs\"\n ```\n\n## Main Commands\n\n- `load`: Add your documents to Wizz\n- `index`: Prepare your documents for searching and find connections\n- `search`: Look for information in your documents\n- `interact`: Ask questions about your documents and get AI-powered answers\n- `delete`: Remove a set of documents from Wizz\n\nFor more details, type:\n```\nwizz knowledge --help\n```\n\n## What You Need\n\n- Python 3.11 or newer\n- An OpenAI API key\n\n## Technical Notes\n\nWhile Wizz currently works as a standalone tool, its core features are designed with future web integration in mind.\nThe code uses async programming, preparing it for potential use with ASGI web servers in the future.\nI developed a custom async wrapper library called `async-annoy` for the vector search tool 'annoy' (by Spotify). You can find it [here](https://github.com/ryzhakar/async-annoy).\n\n## Important Note\n\nWizz 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.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A terminal-based LLM chat client with knowledge retrieval.",
"version": "0.2.2",
"project_urls": {
"Homepage": "https://github.com/ryzhakar/wizz",
"Repository": "https://github.com/ryzhakar/wizz"
},
"split_keywords": [
"chat-client",
" local-llms",
" terminal",
" query-response",
" ai",
" natural-language-processing"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "58122e67f951170c0278e228d192eb7dae4ff65834b431a023ad8184f6ad15b9",
"md5": "9d6d87f3d47a677468a2e2bc9524b358",
"sha256": "3783964a527fdf618808a65e4e0898c26ac07f5894a351286a2a20f35bf53624"
},
"downloads": -1,
"filename": "wizz-0.2.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9d6d87f3d47a677468a2e2bc9524b358",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.11",
"size": 19357,
"upload_time": "2024-07-03T20:53:08",
"upload_time_iso_8601": "2024-07-03T20:53:08.902105Z",
"url": "https://files.pythonhosted.org/packages/58/12/2e67f951170c0278e228d192eb7dae4ff65834b431a023ad8184f6ad15b9/wizz-0.2.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "f1ad4c4c2c1f3ba93e8aaedc791ec9fc8bb8f6ab59272f40cb72c200a2f8f035",
"md5": "2c434277873e1f0ec9f73922567df4d1",
"sha256": "d547c576330baffc604d42192a4d1cbbd2d53d10ee9eef40c87d8619d0de8503"
},
"downloads": -1,
"filename": "wizz-0.2.2.tar.gz",
"has_sig": false,
"md5_digest": "2c434277873e1f0ec9f73922567df4d1",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.11",
"size": 46531,
"upload_time": "2024-07-03T20:53:10",
"upload_time_iso_8601": "2024-07-03T20:53:10.388308Z",
"url": "https://files.pythonhosted.org/packages/f1/ad/4c4c2c1f3ba93e8aaedc791ec9fc8bb8f6ab59272f40cb72c200a2f8f035/wizz-0.2.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-03 20:53:10",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ryzhakar",
"github_project": "wizz",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "wizz"
}
JSON
