Note: This project is still a work-in-progress. It works, but it doesn't have many features yet. Please suggest features, report problems (bugs should go in Issues), or just say hi in Discussions!
# :mag: DeepSearchKit
A small, fast, and easy package that allows easy semantic searching using :brain: artificial intelligence. It is based on and similar to the closed-source DeepSearch system.
## :computer: Installation
You can install the latest stable version from the registry:
```
pip3 install deepsearchkit
```
You can install the very latest version directly from the Git repository, however certain features may not work:
```
pip3 install git+https://github.com/fakerybakery/deepsearchkit
```
## :white_check_mark: Features
* CPU, CUDA, and MPS support (enhanced GPU acceleration)!
* Simple usage
## :newspaper: Usage
Documentation is available [here](DOCUMENTATION.md).
## :thought_balloon: Todo
- [ ] Integrate DeepSearch into DeepSearchKit
- [ ] Open-source DeepSearch
- [ ] Add Web Interface (from DeepSearch)
- [ ] Add document search demo
- [ ] Add document chat demo
- [ ] Add upsert feature ([txtai#251](https://github.com/neuml/txtai/issues/251))
- [ ] Add more data support, e.g. parquet, MySQL/hosted DBs
- [ ] Custom prompt/data format for multiple columns in JSON
- [ ] Custom progress callback for indexing
- [ ] Make some example projects
- [ ] Chat with a folder using open-sourced conversational models
- [ ] Search an entire directory
- [ ] Allow easy publishing with a `.dskpkg` file - compressed DeepSearchKit package that includes the index, the data, and some attributes (name, author, license, etc)
- [ ] Maybe in the future: "DSK Hub" - hub for DSK packages
## :memo: Credits
We would like to thank the authors of the following open source projects:
* [sentence-transformers](https://github.com/UKPLab/sentence-transformers)
* [txtai](https://github.com/neuml/txtai)
## :briefcase: Disclaimer/Agreement (Read BEFORE you contribute!)
In every new issue/PR, make sure to include "I agree to the disclaimer!"
By using/contributing to this software, you agree to the [agreement](DISCLAIMER.md).
Raw data
{
"_id": null,
"home_page": "https://github.com/fakerybakery/deepsearchkit",
"name": "deepsearchkit",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "mrfakename",
"author_email": "me@mrfake.name",
"download_url": "https://files.pythonhosted.org/packages/c1/48/161cd2c6653baa37e80ae10cca5db52d2cd7cbe57e0ed8d13cb9ac9a0069/deepsearchkit-1.0.1.tar.gz",
"platform": null,
"description": "Note: This project is still a work-in-progress. It works, but it doesn't have many features yet. Please suggest features, report problems (bugs should go in Issues), or just say hi in Discussions!\n\n\n\n# :mag: DeepSearchKit\n\nA small, fast, and easy package that allows easy semantic searching using :brain: artificial intelligence. It is based on and similar to the closed-source DeepSearch system.\n\n## :computer: Installation\n\nYou can install the latest stable version from the registry:\n\n```\npip3 install deepsearchkit\n```\n\nYou can install the very latest version directly from the Git repository, however certain features may not work:\n\n```\npip3 install git+https://github.com/fakerybakery/deepsearchkit\n```\n\n## :white_check_mark: Features\n\n * CPU, CUDA, and MPS support (enhanced GPU acceleration)!\n * Simple usage\n\n## :newspaper: Usage\n\nDocumentation is available [here](DOCUMENTATION.md).\n\n## :thought_balloon: Todo\n\n- [ ] Integrate DeepSearch into DeepSearchKit\n - [ ] Open-source DeepSearch\n- [ ] Add Web Interface (from DeepSearch)\n- [ ] Add document search demo\n - [ ] Add document chat demo\n- [ ] Add upsert feature ([txtai#251](https://github.com/neuml/txtai/issues/251))\n- [ ] Add more data support, e.g. parquet, MySQL/hosted DBs\n- [ ] Custom prompt/data format for multiple columns in JSON\n- [ ] Custom progress callback for indexing\n- [ ] Make some example projects\n - [ ] Chat with a folder using open-sourced conversational models\n - [ ] Search an entire directory\n- [ ] Allow easy publishing with a `.dskpkg` file - compressed DeepSearchKit package that includes the index, the data, and some attributes (name, author, license, etc)\n - [ ] Maybe in the future: \"DSK Hub\" - hub for DSK packages\n\n## :memo: Credits\n\nWe would like to thank the authors of the following open source projects:\n\n * [sentence-transformers](https://github.com/UKPLab/sentence-transformers)\n * [txtai](https://github.com/neuml/txtai)\n\n## :briefcase: Disclaimer/Agreement (Read BEFORE you contribute!)\n\nIn every new issue/PR, make sure to include \"I agree to the disclaimer!\"\n\nBy using/contributing to this software, you agree to the [agreement](DISCLAIMER.md).\n",
"bugtrack_url": null,
"license": "",
"summary": "A small, fast, and easy package for semantic searching using artificial intelligence.",
"version": "1.0.1",
"project_urls": {
"Homepage": "https://github.com/fakerybakery/deepsearchkit"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5ab00a4d6081110d6335316df3b886b183847c4f6d42f000b74f1e357ebb6c17",
"md5": "e732fa802fc4173b4c1ce806f0e4a82d",
"sha256": "35ab29c450bbf9a31e6c3db176a909db1756aae51d5b68a5478079006a77ca36"
},
"downloads": -1,
"filename": "deepsearchkit-1.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e732fa802fc4173b4c1ce806f0e4a82d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 4919,
"upload_time": "2023-09-15T23:32:35",
"upload_time_iso_8601": "2023-09-15T23:32:35.335334Z",
"url": "https://files.pythonhosted.org/packages/5a/b0/0a4d6081110d6335316df3b886b183847c4f6d42f000b74f1e357ebb6c17/deepsearchkit-1.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c148161cd2c6653baa37e80ae10cca5db52d2cd7cbe57e0ed8d13cb9ac9a0069",
"md5": "b7751a6b3e39fad1ce3abe453efdd711",
"sha256": "06c2165033474119242ce3875a1a15ef95b6aa851a63ae79f34000fd8c2e45b9"
},
"downloads": -1,
"filename": "deepsearchkit-1.0.1.tar.gz",
"has_sig": false,
"md5_digest": "b7751a6b3e39fad1ce3abe453efdd711",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 3997,
"upload_time": "2023-09-15T23:32:36",
"upload_time_iso_8601": "2023-09-15T23:32:36.797308Z",
"url": "https://files.pythonhosted.org/packages/c1/48/161cd2c6653baa37e80ae10cca5db52d2cd7cbe57e0ed8d13cb9ac9a0069/deepsearchkit-1.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-15 23:32:36",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "fakerybakery",
"github_project": "deepsearchkit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "deepsearchkit"
}
JSON
