aws-samples/aws-agentic-document-assistant
An agent based LLM assistant that extends RAG with batch entity extraction and SQL querying to improve performance on multi-step and analytical questions.
This assistant helps business professionals get fast, accurate answers from their complex business documents through natural language conversations. You input documents like contracts or financial reports, and the assistant can answer both factual questions by searching the text and analytical questions by querying extracted data. This is ideal for managers, analysts, or legal professionals who need to quickly extract insights and data points without manually sifting through piles of documents.
No commits in the last 6 months.
Use this if you need to quickly find specific information or analyze trends and relationships across many business documents without writing complex queries or reading every page.
Not ideal if your primary need is general creative text generation or summarization from unstructured text, rather than specific factual retrieval and data-driven analysis from business documents.
Stars
97
Forks
25
Language
Jupyter Notebook
License
MIT-0
Category
Last pushed
Jun 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/aws-samples/aws-agentic-document-assistant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
vectara/py-vectara-agentic
A python library for creating AI assistants with Vectara, using Agentic RAG