distill_file
Converts local PDF, Word, Excel, PowerPoint, ODF, and image files into token-lean Markdown for LLM use, paging large documents and reporting token savings.
Instructions
Convert a document (PDF, DOCX, PPTX, XLSX, ODF, image) to token-lean Markdown; large documents come back in pages
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": {
"path": "<path>"
},
"name": "distill_file"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute path, or relative to the server's working directory | |
| lingua | No | Compress further with LLMLingua-2 when installed | |
| offset | No | Line to start from, for documents too large to return at once; use the nextOffset from the previous call | |
| boosters | No | Boosters to apply: dedupe, media, tables, ws |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| note | No | ||
| lines | Yes | ||
| pages | Yes | ||
| tokens | Yes | ||
| savings | No | ||
| markdown | Yes | ||
| truncated | No | ||
| nextOffset | No | ||
| continuation | No |