# ragflow | InfiniFlow | Knowledge Base | Instagit RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs GitHub Stars: 73.6k Repository: https://github.com/infiniflow/ragflow --- ## Articles ### [Debugging RAGFlow Applications: 8 Essential Techniques for Micro-Service Troubleshooting](/infiniflow/ragflow/ragflow-best-practices-debugging-applications) Master RAGFlow application debugging with 8 essential techniques. Learn to use centralized logging, control verbosity, and attach remote debuggers for efficient micro-service troubleshooting. - Tags: best-practices - Published: 2026-02-23 ### [How RAGFlow Supports Querying Heterogeneous Data Sources: Architecture and Implementation](/infiniflow/ragflow/ragflow-query-heterogeneous-data-sources) Discover how RAGFlow unifies heterogeneous data sources with its connector abstraction and unified doc-store for seamless cross-source querying without complex logic. Explore architecture and implementation. - Tags: architecture - Published: 2026-02-23 ### [How RAGFlow Implements Python and JavaScript Code Execution for AI Agents](/infiniflow/ragflow/ragflow-python-javascript-code-executor-implementation) Discover how RAGFlow securely executes Python and JavaScript code for AI agents using a novel three-layer sandbox architecture. Learn about its unified CodeExec component. - Tags: internals - Published: 2026-02-23 ### [How RAGFlow Manages Document Metadata for Efficient Retrieval and Indexing](/infiniflow/ragflow/ragflow-manage-document-metadata-indexing) Discover how RAGFlow manages document metadata for efficient retrieval and indexing. Leverage per-tenant search indices for millisecond-level filtering alongside vector search. - Tags: deep-dive - Published: 2026-02-23 ### [Scaling RAGFlow for Large Volumes of Documents and Queries: Architecture and Best Practices](/infiniflow/ragflow/ragflow-scaling-large-volumes-documents-queries) Discover how to scale RAGFlow for massive document volumes and high query loads. Explore architecture, best practices, and key considerations for enterprise-grade performance. - Tags: architecture - Published: 2026-02-23 ### [How RAGFlow Handles Authentication and Authorization for API Endpoints](/infiniflow/ragflow/ragflow-api-authentication-authorization) Learn how RAGFlow secures its API endpoints with a two layer authentication and authorization mechanism involving UUID tokens and login required decorators. - Tags: how-to-guide - Published: 2026-02-23 ### [How to Use the RAGFlow Python SDK to Build Custom RAG Applications](/infiniflow/ragflow/ragflow-python-sdk-build-custom-rag-applications) Build custom RAG applications with the RAGFlow Python SDK. Programmatically manage datasets, parse docs, and create chat sessions effortlessly without HTTP boilerplate. - Tags: how-to-guide - Published: 2026-02-23 ### [How RAGFlow Parses Multi-Modal Information from PDFs and DOCX Files: A Deep Dive into the DeepDoc Parser](/infiniflow/ragflow/ragflow-parse-multimodal-information-pdf-docx) Discover how RAGFlow's DeepDoc parser extracts text, tables, and figures from PDFs and DOCX files for advanced RAG pipelines. Learn about OCR, layout, and table detection for unified data representation. - Tags: deep-dive - Published: 2026-02-23 ### [How Cross-Language Query Support Works in RAGFlow: A Technical Deep Dive](/infiniflow/ragflow/ragflow-cross-language-query-support-implementation) Discover how RAGFlow implements cross-language query support. Learn how LLM translation and prompt templates enable seamless retrieval across multilingual documents. Read the technical deep dive. - Tags: deep-dive - Published: 2026-02-23 ### [How RAGFlow Manages State and Memory for Its AI Agents: A Deep Dive into the Document-Store Architecture](/infiniflow/ragflow/ragflow-manage-state-memory-ai-agents) Explore RAGFlow's document-level memory architecture for AI agents. Discover how per-user indices and hybrid retrieval manage conversational state across sessions efficiently. - Tags: deep-dive - Published: 2026-02-23 ### [How RAGFlow Handles Data Synchronization from Confluence, S3, Notion, Discord, and Google Drive](/infiniflow/ragflow/ragflow-data-synchronization-diverse-sources) Discover how RAGFlow synchronizes data from Confluence, S3, Notion, Discord, and Google Drive using its unified SyncBase abstraction and configurable batch processing for seamless updates. - Tags: how-to-guide - Published: 2026-02-23 ### [RAGFlow Agent Tools: Complete Catalog and Extension Guide](/infiniflow/ragflow/ragflow-available-agent-tools-extension) Explore RAGFlow agent tools: discover built-in tools like Wikipedia, Google Search & more, and learn how to extend RAGFlow by adding new tools to its agent tools directory. - Tags: api-reference - Published: 2026-02-23 ### [How RAGFlow's Agentic Workflow Leverages the `agent/canvas.py` Module](/infiniflow/ragflow/ragflow-agentic-workflow-agent-canvas-py) Discover how RAGFlow's agentic workflow utilizes agent canvas.py to parse DSL JSON, manage state, execute components, and stream events for an efficient user experience. - Tags: internals - Published: 2026-02-23 ### [How RAGFlow Implements Grounded Citations for Retrieved Information: A Technical Deep Dive](/infiniflow/ragflow/ragflow-implement-grounded-citations) Discover how RAGFlow ensures traceable answers with grounded citations. Learn about its three-stage pipeline: prompt templates, lexical chunk matching, and LLM enrichment. Infiniflow/ragflow. - Tags: deep-dive - Published: 2026-02-23 ### [How to Configure Custom Chunking Strategies Using RAGFlow's Template-Based Chunker](/infiniflow/ragflow/ragflow-configure-custom-chunking-strategies) Learn to configure custom chunking strategies in RAGFlow using template-based chunking. Control chunk size, overlap, and delimiters via parser_config for optimized RAG pipelines. - Tags: how-to-guide - Published: 2026-02-23 ### [How the RAG Pipeline Is Orchestrated in RAGFlow's `rag/flow/` Directory](/infiniflow/ragflow/ragflow-pipeline-orchestration-rag-flow) Discover how the RAG pipeline is orchestrated in RAGFlow's rag/flow/ directory. Explore the Pipeline class executing a DAG asynchronously from retrieval to merging. - Tags: internals - Published: 2026-02-23 ### [Core Components of the RAGFlow Backend API: Architecture and Interaction Patterns](/infiniflow/ragflow/ragflow-backend-api-components-interaction) Explore the core components of the RAGFlow backend API including Quart server, Blueprints, service classes, Peewee ORM, and Redis queues. Learn about their architecture and interaction patterns. - Tags: architecture - Published: 2026-02-23