generate_document_processing_pipeline
Generates document pipelines for parsing, chunking (recursive/semantic), and embedding generation across PDF, Markdown, and CSV files.
Instructions
Generates document parsing, chunking (recursive character, semantic chunking), and embedding generation pipelines for PDF, Markdown, and CSV files.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"document_type": "<document_type>"
},
"name": "generate_document_processing_pipeline"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| chunk_size | No | Target chunk character size (default: 1000) | |
| document_type | Yes | Type of input documents to ingest |