query_document
Find relevant indexed document chunks by embedding a query and ranking results by cosine similarity, enabling retrieval-augmented answers over project knowledge.
Instructions
Semantic search over indexed document chunks. Embeds the query context and returns the most similar chunks ordered by cosine similarity. 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": {
"context": "<context>"
},
"name": "query_document"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum results (0 = no limit). | |
| context | Yes | Query text to embed and search. | |
| project | No | Restrict search to chunks tagged with this project. |