extract_vector_context
Extract relevant semantic passages from large documents for a given query, returning only useful chunks within a specified token budget.
Instructions
⚡ 100M Token Vector Reasoning & Hierarchical Semantic Chunker Engine. Extracts relevant semantic chunks from large documents/attachments.
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": {
"query": "<query>",
"full_text": "<full_text>"
},
"name": "extract_vector_context"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query or topic | |
| filename | No | Source document filename | |
| full_text | Yes | Full document text to chunk and rank | |
| max_tokens | No | Maximum token budget |