Practical overview
When it fits
Use it when a team wants to organize a defined set of regulations and explore their contents through semantic search, Q&A, or rule mapping.
Who it is for
- Compliance teams examining alcohol-beverage pricing regulations.
- Developers or organizations seeking a self-hosted regulatory document analysis workflow.
Documented uses
- Ingest and organize PDF or HTML regulatory documents.
- Search regulations semantically and ask questions grounded in uploaded material.
- Extract legal entities and relationships into a JSON knowledge graph.
- Generate a compliance-analysis report with risk evaluation, potential violations, and recommendations from a business type and description.
Requirements & limits
The README documents a self-hosted setup using Python and an Alibaba Cloud Bailian API key. It does not state service pricing.
- Alibaba Cloud Bailian provides the embedding service and Qwen-Turbo model, so cloud credentials and network access are prerequisites.
- The listed document formats are PDF and HTML.
- The documented backend uses FastAPI; the README also lists API routes and interactive API documentation after startup.
- Uploaded files are stored on the local file system, while document, vector, and graph data use JSON files.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Prepare and start the application
Configure the documented Python environment and start the local web service.
Before you start
- Python 3.8 or later
- Project dependencies installed from requirements.txt
- Alibaba Cloud Bailian API key and network access to Alibaba Cloud
- Configured model and data directory environment variables
Steps
Install the project dependencies with pip install -r requirements.txt.
Create a .env file containing ALIBABA_API_KEY, QWEN_MODEL, EMBEDDING_MODEL, DATA_DIR, and UPLOAD_DIR.
Start the service with uvicorn main:app --host 0.0.0.0 --port 8000.
Open http://localhost:8000 to access the system.
Expected outcome
The application’s local web interface is available for regulatory document workflows.
Guide limitations
- A valid Alibaba Cloud Bailian API key with sufficient quota and a stable network connection are required for cloud services.
- The README specifies PDF and HTML input formats.
Upload a regulation and ask a question
Use an uploaded PDF or HTML regulation as the basis for a regulatory question.
Before you start
- A running application
- A readable regulatory document in PDF or HTML format
Steps
Open the Document Upload tab, select a PDF or HTML regulation, and upload it.
Open the Regulatory Q&A tab.
Enter a regulation-related question.
Expected outcome
The system returns an answer based on retrieval-augmented generation over the uploaded regulatory material.
Guide limitations
- Only PDF and HTML input formats are listed.
- The application depends on Alibaba Cloud services for its AI capabilities.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 16 October 2026
- Original website title
- Ramseygithub/ai-legal-compliance-assistant · Official homepage title · retained in its source language