mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 12:32:30 +08:00
ed6a76dcc0
## 🚀 Firecrawl Integration for RAGFlow This PR implements the Firecrawl integration for RAGFlow as requested in issue https://github.com/firecrawl/firecrawl/issues/2167 ### ✅ Features Implemented - **Data Source Integration**: Firecrawl appears as a selectable data source in RAGFlow - **Configuration Management**: Users can input Firecrawl API keys through RAGFlow's interface - **Web Scraping**: Supports single URL scraping, website crawling, and batch processing - **Content Processing**: Converts scraped content to RAGFlow's document format with chunking - **Error Handling**: Comprehensive error handling for rate limits, failed requests, and malformed content - **UI Components**: Complete UI schema and workflow components for RAGFlow integration ### 📁 Files Added - `intergrations/firecrawl/` - Complete integration package - `intergrations/firecrawl/integration.py` - RAGFlow integration entry point - `intergrations/firecrawl/firecrawl_connector.py` - API communication - `intergrations/firecrawl/firecrawl_config.py` - Configuration management - `intergrations/firecrawl/firecrawl_processor.py` - Content processing - `intergrations/firecrawl/firecrawl_ui.py` - UI components - `intergrations/firecrawl/ragflow_integration.py` - Main integration class - `intergrations/firecrawl/README.md` - Complete documentation - `intergrations/firecrawl/example_usage.py` - Usage examples ### 🧪 Testing The integration has been thoroughly tested with: - Configuration validation - Connection testing - Content processing and chunking - UI component rendering - Error handling scenarios ### 📋 Acceptance Criteria Met - ✅ Integration appears as selectable data source in RAGFlow's data source options - ✅ Users can input Firecrawl API keys through RAGFlow's configuration interface - ✅ Successfully scrapes content from provided URLs and imports into RAGFlow's document store - ✅ Handles common edge cases (rate limits, failed requests, malformed content) - ✅ Includes basic documentation and README updates - ✅ Code follows RAGFlow's existing patterns and coding standards ### �� Related Issue https://github.com/firecrawl/firecrawl/issues/2167 --------- Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
16 lines
476 B
Python
16 lines
476 B
Python
"""
|
|
Firecrawl Plugin for RAGFlow
|
|
|
|
This plugin integrates Firecrawl's web scraping capabilities into RAGFlow,
|
|
allowing users to import web content directly into their RAG workflows.
|
|
"""
|
|
|
|
__version__ = "1.0.0"
|
|
__author__ = "Firecrawl Team"
|
|
__description__ = "Firecrawl integration for RAGFlow - Web content scraping and import"
|
|
|
|
from firecrawl_connector import FirecrawlConnector
|
|
from firecrawl_config import FirecrawlConfig
|
|
|
|
__all__ = ["FirecrawlConnector", "FirecrawlConfig"]
|