lixx21/legal-document-assistant

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

36
/ 100
Emerging

Implements a dual-retrieval architecture combining PostgreSQL for structured metadata storage with Elasticsearch for full-text indexing, enabling fast relevance-ranked document retrieval before feeding results to a fine-tuned BERT model for extractive question-answering. The end-to-end pipeline orchestrates document ingestion via Airflow DAGs, containerizes all services (Elasticsearch, BERT inference, monitoring) with Docker Compose, and exposes query capabilities through a Streamlit frontend while tracking system metrics in Grafana.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

97

Forks

19

Language

Jupyter Notebook

License

Last pushed

Sep 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/lixx21/legal-document-assistant"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.