Pipeline Configuration

Customize your document processing workflow

Processing Steps

OCR Processing

Enable optical character recognition for image-based documents

Text Extraction

Extract and clean text from documents

Chunking Strategy

Split documents into manageable chunks for processing

Metadata Extraction

Extract document metadata (author, date, etc.)

AI Models

Model used to convert text into vector embeddings

Model used for text generation and analysis

Save Configuration

Save your pipeline configuration for future use

Document Types

Select which document types this pipeline should process