Implementation:Infiniflow Ragflow TaskService Get Task

Knowledge Sources	RAGFlow
Domains	RAG, Task_Queue
Last Updated	2026-02-12 06:00 GMT

Overview

Concrete tool for hydrating task context from Redis queue messages provided by RAGFlow TaskService.

Description

TaskService.get_task takes a task ID from a Redis queue message and performs a multi-table JOIN across Task, Document, Knowledgebase, and Tenant to build a comprehensive task dictionary with 21 fields needed for document processing.

Usage

Called by the task executor worker after consuming a Redis message. Returns None if the task has exceeded retry limits.

Code Reference

Source Location

Repository: ragflow
File: api/db/services/task_service.py
Lines: L74-142

Signature

class TaskService(CommonService):
    @classmethod
    @DB.connection_context()
    def get_task(cls, task_id: str, doc_ids: list = []) -> dict | None:
        """Hydrate a task with full context from DB.

        Args:
            task_id: str - Task UUID from Redis message.
            doc_ids: list - Optional document ID filter.

        Returns:
            dict with 21 fields (task + document + KB + tenant info) or None if retry_count >= 3.
        """

Import

from api.db.services.task_service import TaskService

I/O Contract

Inputs

Name	Type	Required	Description
task_id	str	Yes	Task UUID from Redis message
doc_ids	list	No	Optional document ID filter

Outputs

Name	Type	Description
task_dict	dict or None	21-field dict: task.id, task.doc_id, task.from_page, task.to_page, task.retry_count, Document.kb_id, Document.parser_id, Document.parser_config, Document.name, Document.type, Document.location, Document.size, Knowledgebase.tenant_id, Knowledgebase.language, Knowledgebase.embd_id, Knowledgebase.pagerank, kb_parser_config, Tenant.img2txt_id, Tenant.asr_id, Tenant.llm_id, task.update_time

Usage Examples

from api.db.services.task_service import TaskService

task = TaskService.get_task("task-uuid-123")
if task:
    print(f"Processing: {task['name']} pages {task['from_page']}-{task['to_page']}")
    print(f"Parser: {task['parser_id']}, Language: {task['language']}")

Related Pages

Implements Principle

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment