ai-legal-compliance-assistant
Analyzes legal regulations like alcohol beverage pricing laws using RAG and knowledge graphs for compliance checks.
Parse regulatory PDFs and HTML to extract entities, map violations, and evaluate business risks.
This system parses regulatory documents, builds structured knowledge graphs, and performs automated risk evaluations for legal compliance. It is designed for legal technology developers and compliance analysts handling state-level regulations. You can ingest PDF and HTML regulation files to generate explainable answers and violation assessments.
What it is
The application processes regulatory text using PyPDF2 and BeautifulSoup4, vectorizes content via Alibaba Cloud Bailian, and structures key legal entities into a JSON knowledge graph. It combines vector similarity search with graph context to power a Qwen-Turbo RAG pipeline. Through its web interface, you can view risk analysis reports, search indexed regulations, and query inter-entity legal relationships.
Who it's for
It suits legal engineering teams and compliance professionals who want to automate document mapping and rule extraction. It does not suit teams looking for a fully managed SaaS service, as you must self-host the application and configure cloud API credentials.
Key features
Regulatory Document Ingestion
Upload PDF or HTML legal texts to extract, segment, and index text metadata automatically.
Knowledge Graph Extraction
Identify legal articles, violations, and penalties to generate a structured JSON knowledge graph.
Graph-Enhanced RAG Q&A
Answer legal queries using vector similarity combined with knowledge graph context via Qwen-Turbo.
Multi-Factor Risk Evaluation
Assess business operations against parsed rules to generate risk levels and violation recommendations.
Interactive Web Dashboard
Manage documents, run live compliance checks, and explore knowledge graphs through a FastAPI web interface.
Up and running in 3 steps
Our honest verdict
What's great
- Combines vector search with structured JSON knowledge graphs for context-aware legal Q&A.
- Includes built-in risk evaluation workflows that output concrete compliance recommendations.
- Provides an interactive web frontend alongside FastAPI REST endpoints for direct integration.
- Comes with a command-line launcher script and test suite for rapid setup validation.
Where it falls short
- Requires an active Alibaba Cloud Bailian API key to run text embeddings and LLM reasoning.
- Stores vectors, graph data, and uploads in local JSON files rather than a production database.
- Lacks native user authentication and permission management out of the box.
Pricing & license
The software is free to host yourself from GitHub. Your primary expenses will come from running your local application host and paying for usage on the Alibaba Cloud Bailian API for embeddings and Qwen model calls.
Open remote AI-training roles
873 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Does this tool require a relational database?
No, the current project structure uses local JSON files and the local filesystem to store uploaded documents, vector indices, and graph nodes.
Which AI backend does this system depend on?
It uses the Alibaba Cloud Bailian API, specifically relying on `text-embedding-v1` for vectorization and `qwen-turbo` for legal reasoning.
What document formats are supported for upload?
The built-in parser handles PDF and HTML document formats.
