Cezzis Cocktail RAG System: End-to-End Intelligent Retrieval-Augmented Generation Workflow

This article introduces cezzis-com-ingestion-agentic-wf—an end-to-end RAG system for the cocktail domain, providing intelligent search and Q&A capabilities for cezzis.com. The system is based on Python, Qdrant vector database, and Ollama local large model, combined with Azure Cosmos DB data sources and E5 embedding model, offering REST API services for semantic search and conversational Q&A. Its core value lies in improving answer accuracy, timeliness, and traceability through retrieval-augmented generation, while integrating agent capabilities to optimize user experience.

RAG (Retrieval-Augmented Generation) is an AI architecture combining information retrieval and text generation, divided into three stages: retrieval, augmentation, and generation. Compared to pure generation models, RAG has significant advantages: reducing hallucinations based on real data, ensuring timeliness through dynamically updatable knowledge bases, enabling traceability of answers to sources, and lowering costs by eliminating the need for fine-tuning large models. This system addresses the needs of cocktail enthusiasts, solving the problem that traditional search struggles to handle natural language queries and professional knowledge Q&A.

Core Technology Stack: Python backend (asynchronous frameworks like FastAPI/Flask), Qdrant vector database (vector storage, semantic search), Ollama local large model (text generation, embedding, privacy protection), Azure Cosmos DB (cocktail data storage), E5 embedding model deployed via TEI service (excellent semantic similarity).

System Architecture is divided into two stages: Data Preparation (extract Cosmos DB data → document chunking → embedding generation → vector storage in Qdrant); Online Service (query embedding → semantic retrieval → context construction → Ollama answer generation).

This system integrates agent capabilities, differing from the traditional single-step RAG process: Query Understanding (judge multi-step retrieval needs), Tool Calling (use tools like search/computation as needed), Iterative Optimization (adjust retrieval strategies), Self-Correction (correct errors). In the cocktail scenario, this manifests as: multi-round retrieval (e.g., first search for summer cocktails then low-alcohol ones), reasoning ability (recommend recipes based on available ingredients), clarification interaction (proactively ask preferences when queries are ambiguous).

Core API Endpoints: Semantic Search (POST /api/search, supports filtering and top_k), Conversational Q&A (POST /api/chat, supports streaming output), Ingredient Recommendation (POST /api/recommend, based on available ingredients).

Deployment uses Docker Compose orchestration (API service, Qdrant, TEI, Ollama), supports incremental data synchronization (scheduled updates from Cosmos DB), and includes monitoring (request latency, retrieval quality, generation quality) and log alerts.

Application Scenarios: Website search enhancement (natural language queries like "pink cocktails suitable for girls"), virtual bartender assistant (recipe guidance, ingredient substitution, cultural background), content creation assistance (auto-generate descriptions, recommend topics).

Technical Highlights: Modular design (separated components for easy expansion), local-first (Ollama/TEI local inference for privacy protection), production-ready (complete error handling and monitoring), extensible to other domains (just replace the data source).

cezzis-com-ingestion-agentic-wf is an excellent practical case of RAG systems, integrating modern AI technologies for practical knowledge services. It provides developers with a clear architectural reference, demonstrating how to build domain-specific intelligent Q&A systems. As RAG technology matures, such systems will be widely applied in more industries like food and tourism, providing users with more accurate and personalized knowledge services.