होम / Dify Workflow Basics · English Dify Workflow Basics
Build LLM apps visually with Dify: workflows and chatflows, prompts and variables, knowledge bases, routing, iteration, code nodes, structured extraction, API calls and streaming, with runnable Python for every testable piece.
कोर्स शुरू करें →
आप क्या सीखेंगे Explain what Dify is, its app types, and how to choose between workflow and chatflow apps. Build workflows from start, LLM, knowledge retrieval, logic, code and end nodes with clean variables. Set up a knowledge base with sensible chunking and retrieval settings, and recognise retrieval failures. Route and loop with if/else, question classifiers, iteration and variable aggregation, and test routing accuracy. Call published workflows through the API in blocking and streaming modes from your own code. Debug, cost, secure and maintain Dify apps in production. पाठ्यक्रम Getting to Know Dify What Dify Is App Types: Chatbot, Agent, Chatflow and Workflow Setting Up: Cloud or Self-Hosted, and Model Providers Workflow Building Blocks Start Node and Variables LLM Nodes and Prompt Templates End Node and Outputs Knowledge Bases and Retrieval Creating a Knowledge Base and Chunking Retrieval Settings: Search Mode, Top K and Threshold Grounded Answers From Retrieved Context Routing, Classification and Iteration If/Else Branches Question Classifier Node Iteration Over Lists Variable Aggregator and Merging Branches Code, Extraction and External Calls Code Nodes Parameter Extraction HTTP Requests, Tools and Plugins Chatflows, Memory and Agents Chatflows Versus Workflows Memory and Context Length Agent Nodes and Tool Use Publishing and Calling Apps Calling a Workflow Through the API Streaming Responses Publishing, Web Apps and Versions Debugging, Cost and Production Readiness Logs, Tracing and Debugging Cost per Run A Production Readiness Checklist