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.
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.
Stars
97
Forks
19
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
Ramseygithub/ai-legal-compliance-assistant
AI-powered legal compliance assistant for alcohol beverage pricing laws — extracts, analyzes,...
adityaprasad-sudo/ExploreSingapore
A sophisticated RAG intelligence engine for Singaporean laws, policies, and history. Comes with...
petrosrapto/PAKTON
Code for "PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements",...
Debapriya-source/nyaya-gpt
AI agent with RAG+ReAct on Indian Constitution & BNS
GitWitAnish/Vidhi.ai
Vidhi.ai is an intelligent legal assistant and navigator built to make legal knowledge and...