🧠 AI & Machine Learning · Sequence
RAG Question Answering Sequence
What happens when a user asks the document chatbot a question: permission check, embedding, vector search, prompt building and a cited answer.
Drawing diagram…
What this diagram shows
- Only documents the user may read are searched
- Top passages are re-ranked before they go to the model
- The answer is streamed back with source links
Prompt used
Sequence for a RAG chatbot: the user sends a question to the chat API. The API gets the user's allowed document groups from the identity service, asks the embedding model for a vector, searches the vector store with a permission filter, re-ranks the top 20 passages to keep the best 5, builds a prompt and calls the LLM, then streams the answer with citations back to the user and logs the exchange.
Mermaid code
sequenceDiagram actor U as User participant API as Chat API participant ID as Identity Service participant EMB as Embedding Model participant VS as Vector Store participant RR as Re-ranker participant LLM as Language Model participant LOG as Chat Log U->>API: Ask question API->>ID: Get allowed document groups ID-->>API: Groups API->>EMB: Embed question EMB-->>API: Vector API->>VS: Top 20 passages in allowed groups VS-->>API: Passages API->>RR: Re-rank passages RR-->>API: Best 5 passages API->>LLM: Prompt with question and passages LLM-->>API: Answer tokens API-->>U: Streamed answer with sources API->>LOG: Save question, answer, sources
Related templates
RAG Chatbot over Company Documents
A chatbot that answers staff questions from company documents: documents are split and indexed in a vector database, and each question pulls the most relevant passages before the language model writes an answer.
Document Ingestion for Vector Search
How documents become searchable passages for an AI assistant: extraction, cleaning, chunking, embedding and indexing, with changed files re-processed automatically.
AI Agent Tool-Use Workflow
How an AI agent completes a task by planning, calling tools, checking results and asking a person to approve risky actions before it finishes.
MLOps Model Training Pipeline
Where each part of an MLOps setup runs: feature store, training jobs on GPU nodes, experiment tracking, model registry and automated deployment to serving.
ML Model Lifecycle
The states a machine learning model moves through, from experiment to production to retirement, including rollback when live performance drops.
LLM Gateway with Cost and Safety Controls
One gateway that every app in a company uses to reach language models: it applies budgets, rate limits, content filters and caching, and records usage per team.