load_document
Parse a Markdown file into heading-bounded chunks, embed and index them for semantic search, replacing prior chunks for the same path so AI agents can retrieve relevant sections.
Instructions
Parse a markdown file into heading-bounded chunks, embed each chunk, and index them for semantic search. Replaces existing chunks for the same path on reload. Requires [embeddings] in config.toml.
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": "load_document"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute or repo-relative path to the markdown file. | |
| project | No | Optional project tag. Chunks tagged with a project can be bulk-deleted via delete_project. |