A RAG-based conversational AI for knowledge seekers and autodidactic learners.
Premium full-stack monorepo RAG Q&A system for industrial documents. Built with React (Vite), FastAPI, Qdrant Cloud, Hugging Face Serverless, and Groq (Llama 3.1). Deployed on Vercel.
Semantic cache benchmark for Olostep web search using Qdrant Cloud Inference.
Safaricom Financial Intelligence Assistant — SQL + RAG over annual reports and BigQuery mart tables
Multi-agent RAG copilot for enterprise documentation using Gradio, FastAPI, LangGraph, Qdrant Cloud, Anthropic Claude, and Langfuse.
Chatbot administrable avec RAG (Qdrant) et tool-calling LLM réel - backend Symfony/API Platform, frontend Nuxt/Vue, modèles Ollama en local / Cloud
Real-time external memory and cognitive continuity layer for LLMs, autonomous agents, and model pretraining workflows. Built with zero PyTorch overhead using FastEmbed.
RAG chatbot demo (FastAPI + Qdrant + Ollama), cited-answer retrieval over PDF/DOCX/TXT, containerized with docker CI/CD
To associate your repository with the qdrant-cloud topic, visit your repo's landing page and select "manage topics."