How opendatalab/mineru-ecosystem works
MinerU-Ecosystem is a collection of clients and integrations for MinerU’s document-parsing API. Users submit files or URLs through a CLI, SDK, MCP tool, or framework loader; the service returns parsed Markdown or structured results, with precision and quick/Flash modes documented. The graph highlights the Python and TypeScript SDK internals, the MCP request path, and the LangChain and LlamaIndex integrations. Some CLI and integration internals were not excerpted, so only documented or indexed relationships are shown.
Main entry points: client.py Python client · client.ts TypeScript client · extract.py MCP extraction · cmd CLI commands
Components 25
Command line
- CLI commands
cli/mineru-open-api/cmd - CLI entrypoint
cli/mineru-open-api/main.go
Client SDKs
- Go SDK
sdk/go/client.go - Python client
sdk/python/src/mineru/client.py - Precision API
sdk/python/src/mineru/_api.py - Flash API
sdk/python/src/mineru/_flash_api.py - Python results
sdk/python/src/mineru/models.py - ZIP parsing
sdk/python/src/mineru/_zip.py - Python errors
sdk/python/src/mineru/exceptions.py - TypeScript client
sdk/typescript/src/client.ts - Precision API
sdk/typescript/src/api.ts - Flash API
sdk/typescript/src/flash-api.ts - TypeScript results
sdk/typescript/src/models.ts - ZIP parsing
sdk/typescript/src/zip.ts - TypeScript errors
sdk/typescript/src/errors.ts
Agent access
- MCP server
mcp/src/mineru_open_mcp/server.py - MCP tools
mcp/src/mineru_open_mcp/tools/tools.py - MCP extraction
mcp/src/mineru_open_mcp/tools/extract.py - MCP configuration
mcp/src/mineru_open_mcp/config.py
RAG integrations
- LangChain loader
langchain_mineru/langchain_mineru/document_loaders/mineru.py - PDF utilities
langchain_mineru/langchain_mineru/utils/pdf.py - LlamaIndex reader
llama-index-readers-mineru/llama_index/readers/mineru/base.py
Parsing service
- MinerU Open API
- Markdown and results
Other components
- Developer or agent
Connections 34
- Developer or agent → CLI entrypoint: runs
README.md - CLI entrypoint → CLI commands: executes
cli/mineru-open-api/main.go - CLI commands → Go SDK: configures client
cli/mineru-open-api/cmd/client.go - CLI commands → MinerU Open API: submits parse and crawl
README.md - Developer or agent → Python client: calls
README.md - Python client → Precision API: uses
sdk/python/src/mineru/client.py - Python client → Flash API: uses
sdk/python/src/mineru/client.py - Python client → Python results: builds results
sdk/python/src/mineru/client.py - Python client → ZIP parsing: parses downloads
sdk/python/src/mineru/client.py - Python client → Python errors: raises
sdk/python/src/mineru/client.py - Precision API → Python errors: maps errors
sdk/python/src/mineru/_api.py - Python client → MinerU Open API: submits and polls
README.md - MinerU Open API → Markdown and results: returns parsed content
README.md - Developer or agent → TypeScript client: calls
README.md - TypeScript client → Precision API: uses
sdk/typescript/src/client.ts - TypeScript client → Flash API: uses
sdk/typescript/src/client.ts - TypeScript client → TypeScript results: builds results
sdk/typescript/src/client.ts - TypeScript client → ZIP parsing: parses downloads
sdk/typescript/src/client.ts - TypeScript client → TypeScript errors: raises
sdk/typescript/src/client.ts - Precision API → TypeScript errors: maps errors
sdk/typescript/src/api.ts - TypeScript client → MinerU Open API: submits and polls
README.md - Developer or agent → MCP server: connects
README.md - MCP server → MCP tools: registers tools
mcp/src/mineru_open_mcp/server.py - MCP tools → MCP extraction: dispatches extraction
mcp/src/mineru_open_mcp/tools/tools.py - MCP extraction → Python client: calls SDK
mcp/src/mineru_open_mcp/tools/extract.py - MCP server → MCP configuration: reads settings
mcp/src/mineru_open_mcp/server.py - MCP extraction → MCP configuration: uses configuration
mcp/src/mineru_open_mcp/tools/extract.py - MCP extraction → Markdown and results: saves parsed output
mcp/src/mineru_open_mcp/tools/extract.py - Developer or agent → LangChain loader: loads documents
README.md - LangChain loader → PDF utilities: uses PDF helpers
langchain_mineru/langchain_mineru/document_loaders/mineru.py - LangChain loader → MinerU Open API: parses sources
README.md - Developer or agent → LlamaIndex reader: loads documents
README.md - LlamaIndex reader → MinerU Open API: parses sources
README.md - Go SDK → MinerU Open API: submits parse requests
README.md