Tool overview
RAGFlow is listed under AI Infrastructure & MLOps AI tools.
What is RAGFlow?
RAGFlow is an Apache-2.0 retrieval and agent engine that combines document parsing, ingestion pipelines, datasets, hybrid retrieval, chat, memory, agent workflows, connectors, APIs, and self-hosted infrastructure for context-rich AI applications.
Best for
Developers and platform teams operating self-hosted RAG and agent applications
Who is it for?
Decision note
Rebuilt from the original export under the complete V411 factual-source-verification workflow. Preview only. Apply remains blocked until Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0, all explicit clears are reviewed, image import is disabled or V380 accepts the asset, one representative WordPress edit screen is compared with the export and proposed row, and a post-Apply zero-change Preview is completed.
Key features
Document parsing and ingestion pipelines
Datasets, hybrid retrieval, and memory
Chat and agent workflow builder
REST APIs, Docker, and Kubernetes deployment
Use cases
Build enterprise RAG systems
Create data-connected agents
Parse complex documents
Publish controlled chat applications
Pros
- Apache-2.0 open-source project
- Active 2026 release cycle
- APIs and multiple deployment options
Limitations
Parsing, retrieval, memory, and agent output can be incorrect and require evaluation and monitoring.
Administrators must secure default credentials, connectors, sandboxes, model endpoints, and uploaded data.
Pricing details
Billing options
Pricing note
RAGFlow is free under Apache-2.0. Users pay for their own compute, storage, databases, model providers, OCR services, and operational infrastructure.
Supported languages
- English
Integrations
Elasticsearch
OceanBase
S3
Azure Blob
GitHub
Google Drive
Zendesk
Please log in to join the discussion.