An open-source Slack knowledge assistant that answers your team's questions by searching across all of your company's tools using Airweave.

Elastic + Vertex AI hybrid search and labeling agent that fuses BM25 + vector retrieval with Gemini reasoning for intelligent enterprise discovery.

A production-grade Retrieval-Augmented Generation (RAG) system built with FastAPI, LangChain, Pinecone, and SentenceTransformers. This project demonstrates high-fidelity retrieval, cross-encoder reranking, and rigorous evaluation methodologies.

Production Hybrid RAG assistant using LangChain, GPT-4o-mini, and ChromaDB with caching, retry logic, confidence scoring, and CI/CD

Beginner-friendly Python RAG project that turns StackOverflow Q&A data into a grounded knowledge assistant using sentence-transformer embeddings, FAISS retrieval, and strict citation-based LLM answering.

Recallr – From storing to learning 📂➡️📘

End-to-end telecom fraud prevention on Databricks — data pipeline, AI/BI dashboards, and a 3-view analyst workbench (Executive, Management, Analyst) with Lakebase, Genie Spaces, and Foundation Model API.

Self-hosted, local-first semantic search and knowledge assistant for Discord using Ollama embeddings and Postgres vector storage

AI-powered Retrieval-Augmented Generation (RAG) Knowledge Assistant built with Python, LangChain, FAISS, and Streamlit for intelligent document question answering.

An AI-powered knowledge assistant built with FastAPI, React, and Retrieval-Augmented Generation (RAG).

A professional RAG (Retrieval-Augmented Generation) system built with FastAPI and LangChain. This assistant allows users to upload PDF documents and query them using OpenAI's LLMs with high accuracy and source citations.

Lightweight RAG knowledge assistant with Gradio UI, persistent ChromaDB vectors, Groq-hosted LLM answering, and SQLite chat history + summarization.

AI-powered Knowledge Assistant using LangChain, Mistral AI, ChromaDB and Streamlit with RAG for document and website question answering.

RAG-based AI assistant for retrieving and answering questions from structured knowledge sources.

An enterprise knowledge assistant built with Retrieval-Augmented Generation (RAG), semantic search (FAISS + SentenceTransformers), and Mistral via OpenRouter to provide accurate, context-aware answers from enterprise documentation.

AI-powered knowledge assistant for intelligent document interaction built with Next.js, TypeScript and RAG.

Local-first personal knowledge assistant built on zeroclaw, local models, and an observable RHEL-oriented deployment path.

A modular Retrieval-Augmented Generation (RAG) pipeline with ingestion, chunking, vector search, and multi-turn chat built using FastAPI and SQLAlchemy.

Reference architecture for enterprise knowledge assistants with semantic routing, ACL-aware RAG, structured queries, DSPy, Redis Stack, and grounded answers with citations.