qdrant_search
Perform semantic vector search across code and documentation to find similar snippets or symbols, with optional filters for language, chunk type, and symbol name.
Instructions
Search for similar code or documentation using semantic search.
This tool performs vector search in Qdrant to find relevant code snippets
or documentation based on semantic similarity to the query.
Use optional filters to narrow down results:
- chunk_type: Find only specific code constructs (function_def, class_def, etc.)
- symbol_name: Find exact symbol by name (e.g., 'get_user', 'MyClass')
- language: Find only files of a specific language
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>",
"collection": "<collection>"
},
"name": "qdrant_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results | |
| query | Yes | Search query text | |
| language | No | Filter by programming language (e.g., 'python', 'go', 'javascript') | |
| chunk_type | No | Filter by chunk type (e.g., 'function_def', 'class_def', 'document') | |
| collection | Yes | Collection name to search in (use project-specific name to isolate data) | |
| symbol_name | No | Filter by exact symbol name (function, class, variable name) | |
| score_threshold | No | Minimum score threshold |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |