Metadata-Version: 2.1
Name: structure-llm
Version: 0.1.0
Summary: Data structuring with LLM
License: MIT
Author: Matthieu
Author-email: matthieu@structure.tech
Requires-Python: >=3.11,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: datamodel-code-generator (>=0.18.0,<0.19.0)
Requires-Dist: langchain (>=0.0.147,<0.0.148)
Requires-Dist: openai (>=0.27.4,<0.28.0)
Requires-Dist: pandas (>=2.0.0,<3.0.0)
Requires-Dist: tiktoken (>=0.3.3,<0.4.0)
Requires-Dist: uvicorn (>=0.21.1,<0.22.0)
Description-Content-Type: text/markdown

# Structure

## Overview 

Structure can be used both as a server and as a standalone package. 

## Steps

1. Before starting, set the OPENAI_API_KEY variable. 
2. Create a schema 
3. Load your unstructured data and receive it in a structured format. 

## Server mode
### Start the server

    structure server --host 0.0.0.0 --port 8080 --log-level info

### API calls 

    curl -X POST -H "Content-Type: multipart/form-data" -F "file=@file.pdf" http://localhost:8000/cv-parser

### Load from DockerHub 

If you prefer the image, simply download it from DockerHub. 
