<div align="center">
[](https://www.python.org/downloads/)
</div>
<div align="center">
**_lesa_**
`[lee - saa]` • **Old Norse** <br/>
(v.) to read, to study, to learn
<!-- <div align="center">
<sub>Prepared by <a href="https://github.com/shxntanu">Shantanu Wable</a> and <a href="https://github.com/omkargwagholikar">Omkar Wagholikar</a> </sub>
</div> -->
</div>
`lesa` is a CLI tool built in Python that allows you to converse with your documents from the terminal, completely offline and on-device using **Ollama**. Open the terminal in the directory of your choice and start a conversation with any document!
## Usage
To start a conversation with a document (`.pdf` and `.docx` for now), simply run:
```bash
lesa read path/to/your/document --page <page_number> (optional)
```
Or start a conversation with an already-embedded directory, run:
```bash
lesa chat
```
### Embed
To embed all files from your current working directory, run:
```bash
lesa embed
```
This creates a `.lesa` config folder in your current working directory that stores the embeddings of all the documents in the directory.
<!-- ## Features
- 🖥️ **Completely On-Device**: Uses Ollama under the hood to interface with LLMs, so you can be sure your data is not leaving your device.
- 📚 **Converse with (almost) all documents**: Supports PDF, DOCX and Text files.
- 🤖 **Wide Range of LLMs**: Choose the Large Language Model of your choice. Whether you want to keep it quick and concise, or want to go all in with a huge context window, the choice is yours. -->
## Setup
`lesa` uses [Ollama](https://ollama.com/) under the hood to utilize the power of large language models.
To install and setup Ollama, run the setup script [`setup-ollama.sh`](scripts/setup-ollama.sh).
```bash
curl -fsSL https://raw.githubusercontent.com/shxntanu/lesa/master/scripts/setup-ollama.sh | bash
```
This script automatically installs the Ollama CLI and pulls the default model (llama3.1:latest) for you. Then install the package using pip.
## Installation
Simply install the package using pip:
```bash
pip install lesa
```
To upgrade to the latest version, run:
```bash
pip install -U lesa
```
## Contribute
We welcome contributions! If you'd like to improve `lesa` or have any feedback, feel free to open an issue or submit a pull request.
## Credits
1. [Typer](https://typer.tiangolo.com/) and [Rich](https://github.com/Textualize/rich): CLI library and terminal formatting.
2. [Ollama](https://ollama.com/): On-device language model inference.
3. [Langchain](https://langchain.com/): Pipeline for language model inference.
4. [FAISS](https://github.com/facebookresearch/faiss): Similarity Search and Vector Store library from Meta AI.
## License
Apache-2.0
Raw data
{
"_id": null,
"home_page": "https://github.com/shxntanu/lesa",
"name": "lesa",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.10.14",
"maintainer_email": null,
"keywords": "lesa, rag pipeline, document chatbot",
"author": "Shantanu Wable",
"author_email": "shantanuwable2003@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/27/5f/a67eb2f43d0f39cbe647567630dc09dfc29721b9166851e7005c0337a3b4/lesa-0.1.0.7.tar.gz",
"platform": null,
"description": "\n\n<div align=\"center\">\n\n[](https://www.python.org/downloads/)\n\n\n\n</div>\n\n<div align=\"center\">\n\n**_lesa_**\n`[lee - saa]` \u2022 **Old Norse** <br/>\n(v.) to read, to study, to learn\n\n<!-- <div align=\"center\">\n <sub>Prepared by <a href=\"https://github.com/shxntanu\">Shantanu Wable</a> and <a href=\"https://github.com/omkargwagholikar\">Omkar Wagholikar</a> </sub>\n</div> -->\n\n</div>\n\n`lesa` is a CLI tool built in Python that allows you to converse with your documents from the terminal, completely offline and on-device using **Ollama**. Open the terminal in the directory of your choice and start a conversation with any document!\n\n## Usage\n\nTo start a conversation with a document (`.pdf` and `.docx` for now), simply run:\n\n```bash\nlesa read path/to/your/document --page <page_number> (optional)\n```\n\nOr start a conversation with an already-embedded directory, run:\n\n```bash\nlesa chat\n```\n\n### Embed\n\nTo embed all files from your current working directory, run:\n\n```bash\nlesa embed\n```\n\nThis creates a `.lesa` config folder in your current working directory that stores the embeddings of all the documents in the directory.\n\n<!-- ## Features\n\n- \ud83d\udda5\ufe0f **Completely On-Device**: Uses Ollama under the hood to interface with LLMs, so you can be sure your data is not leaving your device.\n- \ud83d\udcda **Converse with (almost) all documents**: Supports PDF, DOCX and Text files.\n- \ud83e\udd16 **Wide Range of LLMs**: Choose the Large Language Model of your choice. Whether you want to keep it quick and concise, or want to go all in with a huge context window, the choice is yours. -->\n\n## Setup\n\n`lesa` uses [Ollama](https://ollama.com/) under the hood to utilize the power of large language models.\nTo install and setup Ollama, run the setup script [`setup-ollama.sh`](scripts/setup-ollama.sh).\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/shxntanu/lesa/master/scripts/setup-ollama.sh | bash\n```\n\nThis script automatically installs the Ollama CLI and pulls the default model (llama3.1:latest) for you. Then install the package using pip.\n\n## Installation\n\nSimply install the package using pip:\n\n```bash\npip install lesa\n```\n\nTo upgrade to the latest version, run:\n\n```bash\npip install -U lesa\n```\n\n## Contribute\n\nWe welcome contributions! If you'd like to improve `lesa` or have any feedback, feel free to open an issue or submit a pull request.\n\n## Credits\n\n1. [Typer](https://typer.tiangolo.com/) and [Rich](https://github.com/Textualize/rich): CLI library and terminal formatting.\n2. [Ollama](https://ollama.com/): On-device language model inference.\n3. [Langchain](https://langchain.com/): Pipeline for language model inference.\n4. [FAISS](https://github.com/facebookresearch/faiss): Similarity Search and Vector Store library from Meta AI.\n\n## License\n\nApache-2.0\n\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "A CLI tool to converse with any document locally using Ollama.",
"version": "0.1.0.7",
"project_urls": {
"Homepage": "https://github.com/shxntanu/lesa",
"Repository": "https://github.com/shxntanu/lesa"
},
"split_keywords": [
"lesa",
" rag pipeline",
" document chatbot"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f26768f1b4ef8883847c99ea70fe7cfedd3ff5019835918f6fc2b58c48dc6515",
"md5": "95bc08ab3c33d886f40f9e4bd1c9bf05",
"sha256": "3856193113f3426681c82455d29ee00f32b91003dba3c6b1ebdd7e18d57de8a9"
},
"downloads": -1,
"filename": "lesa-0.1.0.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "95bc08ab3c33d886f40f9e4bd1c9bf05",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.10.14",
"size": 557161,
"upload_time": "2025-01-03T07:23:38",
"upload_time_iso_8601": "2025-01-03T07:23:38.480415Z",
"url": "https://files.pythonhosted.org/packages/f2/67/68f1b4ef8883847c99ea70fe7cfedd3ff5019835918f6fc2b58c48dc6515/lesa-0.1.0.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "275fa67eb2f43d0f39cbe647567630dc09dfc29721b9166851e7005c0337a3b4",
"md5": "acc9d4bf4d70ffb23e8be3791b73fe1a",
"sha256": "9b6d2a5c06f593603e5c67cfb45e907866980a4dd575a045c7c994d9cb03fe34"
},
"downloads": -1,
"filename": "lesa-0.1.0.7.tar.gz",
"has_sig": false,
"md5_digest": "acc9d4bf4d70ffb23e8be3791b73fe1a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.10.14",
"size": 554478,
"upload_time": "2025-01-03T07:23:41",
"upload_time_iso_8601": "2025-01-03T07:23:41.496104Z",
"url": "https://files.pythonhosted.org/packages/27/5f/a67eb2f43d0f39cbe647567630dc09dfc29721b9166851e7005c0337a3b4/lesa-0.1.0.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-03 07:23:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "shxntanu",
"github_project": "lesa",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "lesa"
}
JSON
