Metadata-Version: 2.1
Name: lilac
Version: 0.0.20
Summary: Organize unstructured data
Home-page: https://github.com/lilacai/lilac
License: Apache-2.0
Author: Lilac AI Inc.
Author-email: info@lilacml.com
Requires-Python: >=3.9,<4.0
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Provides-Extra: all
Provides-Extra: cohere
Provides-Extra: embeddings
Provides-Extra: gmail
Provides-Extra: gte
Provides-Extra: lang-detection
Provides-Extra: langsmith
Provides-Extra: llms
Provides-Extra: ner
Provides-Extra: openai
Provides-Extra: palm
Provides-Extra: pii
Provides-Extra: sbert
Provides-Extra: signals
Provides-Extra: sources
Provides-Extra: text-stats
Requires-Dist: authlib (>=1.2.1,<2.0.0)
Requires-Dist: click (>=8.1.3,<9.0.0)
Requires-Dist: cohere (>=3.7.0,<4.0.0) ; extra == "all" or extra == "embeddings" or extra == "cohere"
Requires-Dist: dask (>=2023.3.2,<2024.0.0)
Requires-Dist: datasets (>=2.12.0,<3.0.0)
Requires-Dist: detect-secrets (>=1.4.0,<2.0.0) ; extra == "all" or extra == "signals" or extra == "pii"
Requires-Dist: distributed (>=2023.3.2.1,<2024.0.0.0)
Requires-Dist: duckdb (>=0.8.1,<0.9.0)
Requires-Dist: email-reply-parser (>=0.5.12,<0.6.0) ; extra == "all" or extra == "gmail"
Requires-Dist: fastapi (>=0.103.1,<0.104.0)
Requires-Dist: gcsfs (>=2023.4.0,<2024.0.0)
Requires-Dist: google-api-python-client (>=2.88.0,<3.0.0) ; extra == "all" or extra == "gmail"
Requires-Dist: google-auth-httplib2 (>=0.1.0,<0.2.0) ; extra == "all" or extra == "gmail"
Requires-Dist: google-auth-oauthlib (>=1.0.0,<2.0.0) ; extra == "all" or extra == "gmail"
Requires-Dist: google-cloud-storage (>=2.5.0,<3.0.0)
Requires-Dist: google-generativeai (>=0.1.0,<0.2.0) ; extra == "all" or extra == "embeddings" or extra == "palm"
Requires-Dist: gunicorn (>=20.1.0,<21.0.0)
Requires-Dist: hnswlib (>=0.7.0,<0.8.0)
Requires-Dist: httpx (>=0.24.1,<0.25.0)
Requires-Dist: instructor (>=0.2.7,<0.3.0)
Requires-Dist: itsdangerous (>=2.1.2,<3.0.0)
Requires-Dist: joblib (>=1.3.1,<2.0.0)
Requires-Dist: langdetect (>=1.0.9,<2.0.0) ; extra == "all" or extra == "signals" or extra == "lang-detection"
Requires-Dist: langsmith (>=0.0.29,<0.0.30) ; extra == "all" or extra == "sources" or extra == "langsmith"
Requires-Dist: openai (>=0.27.8,<0.28.0) ; extra == "all" or extra == "embeddings" or extra == "llms" or extra == "openai"
Requires-Dist: orjson (>=3.8.10,<4.0.0)
Requires-Dist: pandas (>=2.0.0,<2.1.0)
Requires-Dist: pillow (>=9.3.0,<10.0.0)
Requires-Dist: psutil (>=5.9.5,<6.0.0)
Requires-Dist: pyarrow (>=13.0.0,<14.0.0)
Requires-Dist: pydantic (>=2.0,<3.0)
Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
Requires-Dist: regex (>=2023.6.3,<2024.0.0) ; extra == "pii"
Requires-Dist: requests (>=2,<3)
Requires-Dist: scikit-learn (>=1.3.0,<2.0.0)
Requires-Dist: sentence-transformers (>=2.2.2,<3.0.0) ; extra == "all" or extra == "embeddings" or extra == "gte" or extra == "sbert"
Requires-Dist: spacy (>=3.5.1,<4.0.0) ; extra == "all" or extra == "signals" or extra == "ner" or extra == "text-stats"
Requires-Dist: tenacity (>=8.2.2,<9.0.0)
Requires-Dist: textacy (>=0.13.0,<0.14.0) ; extra == "all" or extra == "signals" or extra == "text-stats"
Requires-Dist: tqdm (>=4.65.0,<5.0.0)
Requires-Dist: types-psutil (>=5.9.5.12,<6.0.0.0)
Requires-Dist: typing-extensions (>=4.7.1,<5.0.0)
Requires-Dist: uvicorn[standard] (>=0.22.0,<0.23.0)
Project-URL: Repository, https://github.com/lilacai/lilac
Description-Content-Type: text/markdown

# 🌸 Lilac

[![Static Badge](https://img.shields.io/badge/Homepage-8A2BE2?link=http%3A%2F%2Flilacml.com%2F)](https://lilacml.com)
[![Downloads](https://static.pepy.tech/badge/lilac/month)](https://pepy.tech/project/lilac)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Twitter](https://img.shields.io/twitter/follow/lilac_ai)](https://twitter.com/lilac_ai)
[![](https://dcbadge.vercel.app/api/server/jNzw9mC8pp?compact=true&style=flat)](https://discord.gg/jNzw9mC8pp)

> **NEW: Try the [Lilac hosted demo with pre-loaded datasets](https://lilacai-lilac.hf.space/)**

## 👋 Welcome

[Lilac](http://lilacml.com) is an open-source product that helps you **analyze**, **structure**, and
**clean** unstructured data with AI.

Lilac can be used from our UI or from Python.

https://github.com/lilacai/lilac/assets/2294279/cb1378f8-92c1-4f2a-9524-ce5ddd8e0c53

## 💻 Install

To install Lilac on your machine:

```sh
pip install lilac
```

You can also use Lilac with no installation by
[forking our public HuggingFace Spaces demo](https://lilacai-lilac.hf.space/).

## 🔥 Getting started

Start a Lilac webserver from the CLI:

```sh
lilac start ~/my_project
```

Or start the Lilac webserver from Python:

```py
import lilac as ll

ll.start_server(project_dir='~/my_project')
```

This will open start a webserver at http://localhost:5432/.

## 📁 Documentation

Visit our website: [lilacml.com](http://lilacml.com)

## 💻 Why Lilac?

Lilac is a visual tool and a Python API that helps you:

- **Explore** datasets with natural language (e.g. documents)
- **Enrich** your dataset with metadata (e.g. PII detection, profanity, text statistics, etc.)
- Conceptually **search** and tag your data (e.g. find paragraphs about injury)
- **Remove** unwanted or problematic data based on your own criteria
- **Analyze** patterns in your data

Lilac runs completely **on device** using powerful open-source LLM technologies.

## 💬 Contact

For bugs and feature requests, please
[file an issue on GitHub](https://github.com/lilacai/lilac/issues).

For general questions, please [visit our Discord](https://discord.com/invite/jNzw9mC8pp).

