Rag
Build a RAG Chatbot from Scratch — Part 5: Deployment and Production Considerations
Final part: Deploy the RAG chatbot to production with Docker, including cost optimization, rate limiting, and monitoring setup.
Build a RAG Chatbot from Scratch — Part 4: Evaluation and Quality Metrics
Part 4: Evaluate RAG chatbot quality with retrieval metrics, answer faithfulness, and hallucination detection. Build an evaluation pipeline.
How to Get Started with Vector Databases: Embeddings, Similarity Search, and RAG
Introduction to vector databases for semantic search. Covers embeddings, similarity metrics, chunking strategies, metadata filtering, and RAG pipeline basics.
Build a RAG Chatbot from Scratch — Part 3: Streaming Responses with SSE
Part 3: Add real-time streaming responses using Server-Sent Events (SSE). Stream LLM tokens as they're generated for a ChatGPT-like experience.
Build a RAG Chatbot from Scratch — Part 2: Retrieval and Prompt Assembly
Part 2: Implement semantic retrieval from ChromaDB and assemble prompts with retrieved context. Build the core Q&A endpoint with source citations.
Build a RAG Chatbot from Scratch — Part 1: Architecture and Embeddings
Part 1: Design the architecture for a Retrieval-Augmented Generation chatbot and implement document embedding with OpenAI's text-embedding models.