# infiniflow/ragflow **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/infiniflow-ragflow).** 82,922 stars · 9,577 forks · Python · Apache-2.0 ## Links - GitHub: https://github.com/infiniflow/ragflow - Homepage: https://ragflow.io - awesome-repositories: https://awesome-repositories.com/repository/infiniflow-ragflow.md ## Topics `agent` `agentic` `agentic-ai` `agentic-workflow` `ai` `ai-search` `context-engineering` `context-retrieval` `deep-research` `deepseek` `deepseek-r1` `document-parser` `document-understanding` `graphrag` `llm` `mcp` `ollama` `openai` `rag` `retrieval-augmented-generation` ## Description This project is a comprehensive retrieval-augmented generation platform designed for building, managing, and deploying knowledge-based AI applications. It provides a unified environment for organizing datasets, configuring conversational chat assistants, and developing autonomous agents that execute multi-step reasoning workflows. By integrating document intelligence with advanced retrieval pipelines, the platform enables the creation of grounded, verifiable responses supported by traceable citations. The platform distinguishes itself through deep document understanding and sophisticated knowledge orchestration. It supports complex document parsing, including the extraction of tables and images, and utilizes graph-based indexing to enhance reasoning over large document collections. Users can configure multiple recall strategies and fused re-ranking to optimize retrieval accuracy, while the system maintains context through multi-turn dialogue management and flexible tool-use frameworks. The architecture is built on a modular, containerized microservice foundation that supports both local inference engines and external language model APIs. It includes asynchronous task processing for document ingestion and indexing, ensuring system responsiveness during heavy workloads. The platform also provides a standardized interface for model abstraction, allowing for seamless integration with existing language model ecosystems. Developers can interact with the platform through a comprehensive suite of RESTful endpoints and Python client libraries, which cover the full lifecycle of agents, datasets, and knowledge graphs. The system is designed for flexible deployment, offering configurable environment settings and support for custom containerized environments to facilitate local development and infrastructure portability. ## Tags ### Artificial Intelligence & ML - [Autonomous Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents.md) — Integrates large language models with custom knowledge bases and external tools to execute complex, multi-step autonomous workflows. - [Chat Assistants](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/integration-surfaces/chat-assistants.md) — Exposes API endpoints for creating and managing conversational AI assistant instances. ([source](https://ragflow.io/docs/http_api_reference)) - [Retrieval-Augmented Generation Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/platforms-and-runtime-environments/ai-application-platforms/retrieval-augmented-generation-platforms.md) — Delivers a comprehensive environment for building, managing, and deploying knowledge-based AI applications with advanced document parsing and retrieval capabilities. - [Grounded Answer Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/grounded-answer-generation.md) — Generates responses with traceable citations and visual chunking to reduce hallucinations and facilitate human verification of content. ([source](https://cdn.jsdelivr.net/gh/infiniflow/ragflow@main/README.md)) - [RAG Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation/rag-pipelines.md) — Coordinates multi-stage recall, re-ranking, and citation-based generation to produce grounded, verifiable responses from indexed datasets. - [Conversational and Voice Interaction](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction.md) — Enables the deployment of conversational agents that leverage indexed knowledge bases to provide context-aware, human-like interactions. ([source](https://ragflow.io/docs/category/user-guides)) - [Agent Management APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/management-and-discovery/agent-management-apis.md) — Handles the lifecycle of autonomous agents through dedicated API endpoints for listing, managing, and interacting with system entities. ([source](https://ragflow.io/docs/http_api_reference)) - [Document Knowledge Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/knowledge-retrieval-and-documents/document-knowledge-extraction.md) — Processes unstructured data using deep document understanding to extract structured knowledge for high-quality information retrieval. ([source](https://cdn.jsdelivr.net/gh/infiniflow/ragflow@main/README.md)) - [Agentic Tool-Use Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agentic-tool-use-frameworks.md) — Empowers agents to perform multi-step reasoning tasks by bridging internal memory with external tools and knowledge sources. - [OpenAI-Compatible APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/ai-integration-apis/openai-compatible-apis.md) — Standardizes HTTP endpoints for chat completions to ensure compatibility with common AI model integration interfaces. ([source](https://ragflow.io/docs/http_api_reference)) - [Chat Assistant Management APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-interfaces/chat-assistant-management-apis.md) — Provides API endpoints for listing, filtering, and retrieving metadata about configured chat assistants. ([source](https://ragflow.io/docs/http_api_reference)) - [Knowledge Graph Construction](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/knowledge-graph-engineering/knowledge-graph-construction.md) — Automates the construction of knowledge graph structures from datasets via dedicated API endpoints. ([source](https://ragflow.io/docs/http_api_reference)) - [Document Chunking Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation/document-chunking-strategies.md) — Segments source documents using explainable templates to optimize retrieval accuracy during knowledge base indexing. ([source](https://cdn.jsdelivr.net/gh/infiniflow/ragflow@main/README.md)) - [Chat and API Access](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/deployment-pipelines-and-endpoints/chat-and-api-access.md) — Maintains multi-turn dialogue context and streams model outputs via interactive chat interfaces and programmatic endpoints. ([source](https://ragflow.io/docs/faq)) - [Graph-Based Knowledge Indexers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/knowledge-retrieval-and-documents/graph-based-knowledge-indexers.md) — Builds hierarchical summaries and multi-layered knowledge graphs to enhance reasoning over extensive document collections. - [Local LLM Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/local-llm-configurations.md) — Configures local inference engines and external model providers through a unified interface for seamless deployment. ([source](https://ragflow.io/docs/faq)) - [Orchestration and Multi-Agent Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent.md) — Deploys autonomous agents that leverage memory, tools, and knowledge to complete complex, multi-step reasoning workflows. ([source](https://ragflow.io/docs/category/user-guides)) - [OpenAI-Compatible Inference Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/command-line-inference-interfaces/openai-compatible-inference-servers.md) — Provides an API layer compatible with standard interfaces to ensure interoperability with existing large language model ecosystems. - [Knowledge Graph Deletion](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/knowledge-graph-engineering/knowledge-graph-deletion.md) — Purges relational knowledge graph structures associated with specific datasets via targeted API calls. ([source](https://ragflow.io/docs/http_api_reference)) - [Semantic Parsing Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/document-data-intelligence/semantic-parsing-tools.md) — Interprets complex documents to produce traceable, cited answers that reduce hallucinations in retrieval tasks. ([source](https://ragflow.io/docs/faq)) ### Data & Databases - [Knowledge Dataset Managers](https://awesome-repositories.com/f/data-databases/data-governance-modeling/data-management-governance/dataset-orchestration-apis/knowledge-dataset-managers.md) — Organizes knowledge by uploading, parsing, and indexing documents into structured datasets for retrieval-augmented generation. ([source](https://ragflow.io/docs/category/user-guides)) - [Semantic Search Engines](https://awesome-repositories.com/f/data-databases/search-indexing-technologies/search-indexing/search-information-retrieval/semantic-search-engines.md) — Executes semantic searches across indexed datasets to retrieve relevant information and document snippets for answering complex queries. ([source](https://ragflow.io/docs/category/user-guides)) - [Document Parsing Pipelines](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-extraction-ingestion/data-ingestion/document-parsing-pipelines.md) — Parses diverse file formats into structured text chunks using advanced layout analysis and OCR for downstream analysis. - [Dataset Management APIs](https://awesome-repositories.com/f/data-databases/data-governance-modeling/data-management-governance/dataset-orchestration-apis/dataset-management-apis.md) — Modifies dataset configurations programmatically through dedicated administrative endpoints. ([source](https://ragflow.io/docs/http_api_reference)) - [Automated Document Ingestion](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-extraction-ingestion/document-processing-tools/automated-document-ingestion.md) — Uploads and transforms various file types into structured knowledge base entries through automated ingestion routines. ([source](https://ragflow.io/docs/http_api_reference)) ### Content Management & Publishing - [Knowledge Graph APIs](https://awesome-repositories.com/f/content-management-publishing/content-management-systems/content-management-platforms/enterprise-specialized-systems/knowledge-management-systems/knowledge-mapping-graph-tools/knowledge-graphs/knowledge-graph-apis.md) — Facilitates the retrieval and management of dataset-specific knowledge graph structures through dedicated API endpoints. ([source](https://ragflow.io/docs/http_api_reference)) - [Document Parsing Services](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/document-automation-interfaces/document-parsing-services.md) — Offers programmatic methods to asynchronously parse and extract content from various document types for further processing. ([source](https://ragflow.io/docs/python_api_reference)) - [AI-Powered Extraction Engines](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/intelligent-extraction-frameworks/ai-powered-extraction-engines.md) — Employs machine learning to accurately isolate structured data, tables, and text from complex document layouts for retrieval. - [Knowledge Graph Orchestrators](https://awesome-repositories.com/f/content-management-publishing/content-management-systems/content-management-platforms/enterprise-specialized-systems/knowledge-management-systems/knowledge-mapping-graph-tools/knowledge-graph-orchestrators.md) — Combines relational data structures with vector-based search to improve context-aware response generation. - [Document Deletion APIs](https://awesome-repositories.com/f/content-management-publishing/content-management-systems/content-management-platforms/enterprise-specialized-systems/document-management-systems/document-deletion-apis.md) — Deletes stored documents programmatically to maintain clean and updated knowledge repositories. ([source](https://ragflow.io/docs/http_api_reference)) - [Document Parsing Controls](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-apis/document-parsing-controls.md) — Terminates active document parsing tasks through specific API endpoints to manage resource utilization. ([source](https://ragflow.io/docs/http_api_reference)) ### Development Tools & Productivity - [Source-Based Execution Environments](https://awesome-repositories.com/f/development-tools-productivity/platforms-runtimes-language-services/source-based-execution-environments.md) — Supports running the platform directly from source code to facilitate real-time debugging and local development testing. ([source](https://ragflow.io/docs/category/developer-guides)) - [RESTful APIs](https://awesome-repositories.com/f/development-tools-productivity/api-development-sdks/restful-apis.md) — Exposes core platform functionality through a comprehensive suite of HTTP interfaces for external application integration. ([source](https://ragflow.io/docs/category/references)) - [Python SDKs](https://awesome-repositories.com/f/development-tools-productivity/api-development-sdks/python-sdks.md) — Offers a native library for Python developers to interact with platform services and manage retrieval workflows. ([source](https://ragflow.io/docs/category/references)) ### DevOps & Infrastructure - [Configuration Management](https://awesome-repositories.com/f/devops-infrastructure/configuration-management.md) — Adjusts environment parameters to manage application behavior, resource allocation, and backend operations. ([source](https://ragflow.io/docs/category/administrator-guides)) - [System Service Configurations](https://awesome-repositories.com/f/devops-infrastructure/infrastructure/infrastructure-as-code/management/infrastructure-configuration/system-service-configurations.md) — Utilizes YAML templates to define core platform service dependencies, including database connections, object storage, and authentication providers. ([source](https://ragflow.io/docs/dev/configurations)) ### Part of an Awesome List - [Development Frameworks and Tools](https://awesome-repositories.com/f/awesome-lists/ai/development-frameworks-and-tools.md) — Open-source RAG (Retrieval-Augmented Generation) workflow platform. - [RAG and Data Pipelines](https://awesome-repositories.com/f/awesome-lists/ai/rag-and-data-pipelines.md) — RAG engine fusing retrieval with agentic capabilities. - [Retrieval Augmented Generation](https://awesome-repositories.com/f/awesome-lists/ai/retrieval-augmented-generation.md) — RAG engine focused on deep document understanding. - [Databases and RAG](https://awesome-repositories.com/f/awesome-lists/data/databases-and-rag.md) — RAG engine based on deep document understanding. - [RAG Frameworks](https://awesome-repositories.com/f/awesome-lists/devtools/rag-frameworks.md) — Deep document parsing and RAG engine with multi-path retrieval. ### Business & Productivity Software - [Document Management APIs](https://awesome-repositories.com/f/business-productivity-software/task-workflow-automation/productivity-task-management/productivity-software/document-management-apis.md) — Updates document configurations and storage settings programmatically through a structured management interface. ([source](https://ragflow.io/docs/http_api_reference)) - [Document Retrieval APIs](https://awesome-repositories.com/f/business-productivity-software/task-workflow-automation/productivity-task-management/productivity-software/document-management-apis/document-retrieval-apis.md) — Queries and lists documents within datasets using flexible filtering, pagination, and sorting parameters. ([source](https://ragflow.io/docs/http_api_reference)) ### Software Engineering & Architecture - [RAG Pipeline Optimizers](https://awesome-repositories.com/f/software-engineering-architecture/performance-reliability/performance-optimization/data-handling-throughput/rag-pipeline-optimizers.md) — Tunes batch processing, OCR engines, and parsing services to minimize latency in retrieval-augmented generation pipelines. ([source](https://ragflow.io/docs/faq)) ### Web Development - [Chat Management APIs](https://awesome-repositories.com/f/web-development/api-management-tools/api-development-management/api-infrastructure/resource-management-interfaces/chat-management-apis.md) — Manages chat assistant lifecycles, including creation, updates, and deletion, via dedicated API endpoints. ([source](https://ragflow.io/docs/http_api_reference)) - [Dataset Management](https://awesome-repositories.com/f/web-development/api-management-tools/api-development-management/api-infrastructure/resource-management-interfaces/dataset-management.md) — Removes datasets from the system by their unique identifiers using simple administrative commands. ([source](https://ragflow.io/docs/http_api_reference))