Metadata-Version: 2.4
Name: Orange3-DeepSeek-Constructor
Version: 0.0.1
Summary: DeepSeek add-on for Orange3: construct a text field with the DeepSeek LLM.
Home-page: https://github.com/zhangzuocughustccnu/Orange3-DeepSeek-Constructor
Author: ZZAKimi
Author-email: zhangzuocug@163.com
License: MIT
Project-URL: Homepage, https://github.com/zhangzuocughustccnu/Orange3-DeepSeek-Constructor
Project-URL: Source, https://github.com/zhangzuocughustccnu/Orange3-DeepSeek-Constructor
Project-URL: Bug Tracker, https://github.com/zhangzuocughustccnu/Orange3-DeepSeek-Constructor/issues
Keywords: orange3 add-on,orange3,deepseek,llm,text mining
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Plugins
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: Orange3
Requires-Dist: openai>=1.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# Orange3-DeepSeek-Constructor

DeepSeek add-on for [Orange3](https://orangedatamining.com/) data mining software.

Adds a **DeepSeek Constructor** widget that calls the DeepSeek API to construct
a new text column (e.g. generated responses) from an existing text variable.

## Widgets

- **DeepSeek Constructor** — reads a text column from the input data, sends each
  instance to DeepSeek with user-defined prompt start/end, and outputs the data
  with a new "DeepSeek Response" meta column.

## Installation

From Orange: `Options → Add-ons…` → check *Orange3-DeepSeek-Constructor* → OK.

Or with pip (use the Python environment that Orange uses):

```bash
pip install Orange3-DeepSeek-Constructor
```

## Usage

1. Place a **File** widget, load a dataset containing a text column.
2. Connect it to **DeepSeek Constructor** (category: *DeepSeek*).
3. Paste your [DeepSeek API key](https://platform.deepseek.com/), choose a model,
   select the text variable and write your prompt.
4. Click **Apply**. Connect the output to a **Data Table** to inspect the
   "DeepSeek Response" column.

The API key is stored with Orange's credential manager, never in the workflow.

## License

MIT
