Qdrant Vector Search Tool
qdrant_searchSearch a Qdrant vector database using natural language, filters, or DSL queries. Retrieve semantically similar results with relevance scores.
Instructions
Search through Qdrant vector database using natural language queries, filters, point IDs, or DSL filter notation. Supports semantic search, service-specific filtering, analytics queries, recommendation-style example search, direct point lookup, and advanced DSL queries. When filter_dsl is provided, routes to the DSL executor for precise filter-based search. Returns structured search results with relevance scores and metadata.
Parameterized DSL Grammar: symbol{param1=value1, param2=value2}
Values can be:
Strings: "hello"
Numbers: 42, 3.14
Booleans: true, false
Null: null
Nested symbols: symbol{...}
Lists: [item1, item2, ...]
Key filter symbols (used in 'dsl' param): D_5 = DatetimeRange ʄ = FieldCondition ƒ = Filter F_6 = FilterSelector ℏ = HasIdCondition I_2 = IsEmptyCondition I_0 = IsNullCondition ɱ = MatchAny ṁ = MatchText M_0 = MatchTextAny ☆ = MatchValue ř = Range
Advanced query symbols (used in 'query_dsl'/'prefetch_dsl' params): (Types without Unicode symbols use full class names as identifiers) Å = AcornSearchParams C_14 = ContextExamplePair ¢ = ContextPair C_0 = ContextQuery D_6 = DiscoverInput D_2 = DiscoverQuery D_4 = DiscoverRequest D_21 = DiscoverRequestBatch ℱ = Fusion φ = FusionQuery ø = OrderBy ɵ = OrderByQuery ¶ = Prefetch ʔ = QuantizationSearchParams R_12 = RecommendGroupsRequest R_2 = RecommendInput R_4 = RecommendQuery R_5 = RecommendRequest R_18 = RecommendRequestBatch R_10 = RecommendStrategy ♦ = SearchParams
Examples: ƒ{must=[ʄ{key="tool_name", match=☆{value="search"}}]} (filter by tool_name), ƒ{must=[ʄ{key="tool_name", match=ɱ{any=["send_dynamic_card", "send_gmail_message"]}}]} (match any of multiple values).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return (1-100) | |
| query | Yes | Search query string (natural language, filters, or semantic text for DSL mode) | |
| dry_run | No | If True with filter_dsl, parse+build without executing | |
| query_dsl | No | Optional advanced query DSL (RecommendQuery, FusionQuery, OrderByQuery) | |
| collection | No | Optional Qdrant collection name to search. If not provided, uses the server's default collection. | |
| filter_dsl | No | Optional DSL filter string (e.g., 'ƒ{must=[...]}') | |
| prefetch_dsl | No | Optional multi-stage Prefetch DSL | |
| score_threshold | No | Minimum similarity score (0.0-1.0) | |
| user_google_email | No | Use 'me' or 'myself' for auto-resolution to authenticated user, or provide specific email address. If None, uses current authenticated user (auto-injected by middleware). | |
| negative_point_ids | No | Optional list of point IDs to use as negative examples | |
| positive_point_ids | No | Optional list of point IDs to use as positive examples |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | Error message if search failed | |
| query | Yes | The search query used | |
| results | Yes | Search results | |
| dsl_input | No | DSL filter string when using DSL search mode | |
| query_type | Yes | Type of query (semantic, service_history, dsl, etc.) | |
| search_vector | No | Named vector used for search (e.g., 'components', 'inputs', 'relationships') | |
| total_results | Yes | Number of results found | |
| collection_name | Yes | Qdrant collection name | |
| built_filter_repr | No | Debug repr of built filter object | |
| processing_time_ms | Yes | Time taken to process the search |