A FastAPI + Streamlit app that shows how to ground LLM answers in organizational data using RAG, complete with synthetic data generators, FAISS indexes, and an ops-style dashboard
-
Updated
Nov 28, 2025 - Python
A FastAPI + Streamlit app that shows how to ground LLM answers in organizational data using RAG, complete with synthetic data generators, FAISS indexes, and an ops-style dashboard
AI-powered search assistant inspired by Perplexity — real-time web querying, multi-source cited answer synthesis, and follow-up conversation with source attribution.
Strict retrieval-first AI agent for policy Q&A. Uses vector search to ensure answers come ONLY from documents—no hallucinations, grounded in actual policy content.
An attempt to production-ready Retrieval-Augmented Generation (RAG) system with advanced features including hybrid retrieval, adaptive feedback loops, comprehensive evaluation, and explainable AI logging.
Articles and resources on retrieval pipelines, indexing, reranking, and knowledge grounding.
Configurable AI assistants grounded in business-unit knowledge, local roles, procedures, and escalation paths.
To associate your repository with the knowledge-grounding topic, visit your repo's landing page and select "manage topics."