> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Cookbooks and tutorials > Step-by-step tutorials for building AI applications with Orq.ai. Covers RAG chatbots, text-to-SQL, PDF extraction, and multi-agent systems. ## Common Architectures Proven implementation patterns for building AI applications, from simple LLM integrations to complex multi-agent systems. The most straightforward way to integrate LLM calls through **Orq.ai** as an AI Gateway. Build conversational AI with memory, context awareness, and intelligent escalation. Ground LLM responses in your knowledge base for accurate, context-aware answers. Add reranking, hybrid search, and query optimization to your RAG system. Build autonomous agents with tool calling, memory, and multi-agent coordination. Integrate **Orq.ai** with LangGraph, CrewAI, and AutoGen for observability and control. Understand the differences between the two core integration patterns. ## Chatbots & AI Apps End-to-end guides for building production chatbots, conversational AI, and multi-agent applications. Build a production-ready chatbot with streaming, fallbacks, caching, and RAG. Maintain conversation history across messages for stateful LLM interactions. Build a multilingual FAQ chatbot with RAG and dynamic language routing. Categorize user queries for chatbots, support, and task automation. Build RAG-powered FAQ bots using prompt-based development without a backend. Build a multi-agent system with specialized agents, memory, and knowledge bases. Build and compare a single-agent vs multi-agent claims system from your coding assistant via MCP. ## Data & Extraction Use AI to extract structured data from unstructured documents, images, and natural language inputs. Extract structured data from PDF invoices using vision models. Process receipt images into structured JSON with vendor names, amounts, and dates. Transform natural language into SQL queries for non-technical database access. ## Evaluation & Safety Test, evaluate, and red-team your LLM deployments to ensure quality, reliability, and security. Run evaluations in parallel at scale using evaluatorq. Probe LLM deployments and agents for security vulnerabilities with evaluatorq. Drive the full evaluator optimization loop from the terminal using Claude Code + **orq.ai** MCP. ## Integrations & Tooling Connect **Orq.ai** with your existing tools, workflows, and third-party infrastructure. Chain multiple LLM deployments and run evaluators across multi-step workflows. Use **Orq.ai** deployments and routing inside n8n workflow automation pipelines. Fetch deployment configurations at runtime while keeping control over your infrastructure. Implement structured user feedback to improve LLM responses over time. Connect Pinecone or other vector databases to **Orq.ai** for custom RAG pipelines. ## Learn Reference guides and conceptual explainers for LLM concepts, prompt engineering, and platform features. Definitions for 200+ LLM, LLMOps, and prompt engineering terms. Best practices for LLM optimization, structured prompts, and consistent outputs. Complete reference for Jinja and Mustache templates in deployments and experiments. Non-technical guide to monitoring AI agents, tracking costs, and staying in control.