Metadata-Version: 2.1
Name: doccano-mini
Version: 0.0.2
Summary: Generate LangChain config quickly
Home-page: https://github.com/doccano/doccano-mini
License: MIT
Author: Hironsan
Author-email: hiroki.nakayama.py@gmail.com
Requires-Python: >=3.10,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.10
Requires-Dist: langchain (>=0.0.112,<0.0.113)
Requires-Dist: openai (>=0.27.2,<0.28.0)
Requires-Dist: streamlit (>=1.20.0,<2.0.0)
Project-URL: Repository, https://github.com/doccano/doccano-mini
Description-Content-Type: text/markdown

# doccano-mini

doccano-mini is a few-shot annotation tool to assist the development of applications with Large language models (LLMs). Once you annotate a few text, you can test your task (e.g. text classification) with LLMs, then download the [LangChain](https://github.com/hwchase17/langchain)'s config.

![Demo](./docs/images/demo.jpg)

Note: This is an experimental project.

## Installation

```bash
pip install doccano-mini
```

## Usage

For this example, we will be using OpenAI’s APIs, so we need to set the environment variable in the terminal.

```bash
export OPENAI_API_KEY="..."
```

If you want to change the model, set the environment variable in the terminal.  
We use `text-davinci-003` by default.

```bash
export OPENAI_MODEL_NAME="gpt-3.5-turbo"
```

Then, we can run the server.

```bash
doccano-mini
```

Now, we can open the browser and go to `http://localhost:8501/` to see the interface.

## Development

```bash
poetry install
streamlit run doccano_mini/app.py
```

