## Query Vectors `client.VectorStores.Query(ctx, vectorStoreName, body) (*VectorStoreQueryResponse, error)` **post** `/v5/vector-stores/{vector_store_name}/query` Query documents using similarity search with optional reranking. Primary endpoint for semantic search, question-answering, and RAG (Retrieval-Augmented Generation) applications. Returns documents ranked by relevance to the query text with similarity scores. **Query Types:** - `semantic` (default): Approximate nearest-neighbor search using HNSW over cosine similarity of document embeddings. Optimal for question-answering, conceptual search, and finding semantically related content without requiring exact keyword matches. - `lexical`: Keyword-based text search (BM25 algorithm). Optimal for exact phrase matching, proper nouns, and scenarios where keyword presence is more important than semantic similarity. - `hybrid`: Combines semantic and lexical approaches with weighted scoring. Provides maximum recall by identifying documents matching either semantically or lexically. **Metadata Filtering:** Narrow the search scope by applying metadata filters (e.g., search only documents where `category: "technical"`). Only indexed fields can be used for filtering. Filters are applied before similarity search for optimal efficiency. **Reranking (Advanced):** Optionally enhance result quality using a cross-encoder reranking model. The reranker rescores the initial results using a more sophisticated model that evaluates the complete query-document pair (not solely embeddings). This adds 100-500ms latency but significantly improves precision for high-stakes applications. **Reranking Strategy:** Set `top_k` higher than the desired final count (e.g., 50) to retrieve more candidates from the initial search. Then configure `rerank_top_n` to the desired final count (e.g., 10) to return only the most relevant documents after reranking. This two-stage approach maximizes both recall and precision. **Performance Metrics:** The response includes detailed timing breakdowns (embedding generation time, index query time, reranking time) to facilitate search pipeline optimization and latency analysis. **Similarity Scores:** Each result includes a `score` field indicating relevance. Higher scores indicate greater relevance. Score ranges and semantics vary by query type (semantic scores use cosine similarity, lexical scores use BM25, hybrid scores combine both approaches). ### Parameters - `vectorStoreName string` The name of the vector store - `body VectorStoreQueryParams` - `Content param.Field[TextContent]` Text content for documents. - `Filter param.Field[map[string, any]]` Metadata filter expression - `IncludeVectors param.Field[bool]` Include embedding vectors in response - `QueryType param.Field[VectorStoreQueryParamsQueryType]` Query type: semantic, lexical, or hybrid - `const VectorStoreQueryParamsQueryTypeSemantic VectorStoreQueryParamsQueryType = "semantic"` - `const VectorStoreQueryParamsQueryTypeLexical VectorStoreQueryParamsQueryType = "lexical"` - `const VectorStoreQueryParamsQueryTypeHybrid VectorStoreQueryParamsQueryType = "hybrid"` - `Rerank param.Field[bool]` [Deprecated: use rerank_config] Enable reranking of search results - `RerankConfig param.Field[VectorStoreQueryParamsRerankConfig]` Reranking configuration. Presence enables reranking; omit to disable. Pass an empty object ({}) to enable reranking with system defaults. - `Instruction string` Custom instruction for the reranking model (e.g., 'Given a medical question, retrieve relevant clinical passages'). Only applies to instruction-following rerankers like Qwen3. - `Model string` Reranking model to use (uses system default if not specified). Supported values depend on the selected provider: Launch cross-encoder names (e.g. 'cross-encoder/ms-marco-MiniLM-L-12-v2'), Vertex semantic-ranker names (e.g. 'semantic-ranker-default-004') when provider='vertex', or any model id the inference proxy serves when provider='proxy'. - `Provider string` Reranking provider to use. When omitted, the deployment default is used ('launch', or 'proxy' on ray-serve deployments configured for the OpenAI-compatible inference proxy). Set explicitly (e.g. 'vertex') to route to a specific provider on a deployment that has more than one configured. Requesting a provider that is not configured on the deployment returns a 400. - `const VectorStoreQueryParamsRerankConfigProviderLaunch VectorStoreQueryParamsRerankConfigProvider = "launch"` - `const VectorStoreQueryParamsRerankConfigProviderVertex VectorStoreQueryParamsRerankConfigProvider = "vertex"` - `const VectorStoreQueryParamsRerankConfigProviderProxy VectorStoreQueryParamsRerankConfigProvider = "proxy"` - `TopN int64` Number of results to keep after reranking (defaults to top_k) - `Type string` Reranking configuration type. Currently only 'base' is supported. - `const VectorStoreQueryParamsRerankConfigTypeBase VectorStoreQueryParamsRerankConfigType = "base"` - `RerankInstruction param.Field[string]` [Deprecated: use rerank_config.instruction] Custom instruction for reranker - `RerankModel param.Field[string]` [Deprecated: use rerank_config.model] Reranking model to use - `RerankTopN param.Field[int64]` [Deprecated: use rerank_config.top_n] Number of results after reranking - `TopK param.Field[int64]` Number of search results to return ### Returns - `type VectorStoreQueryResponse struct{…}` Response for query operation. - `Metadata VectorStoreQueryResponseMetadata` Query execution metadata - `SearchType string` Type of search performed (semantic, lexical, hybrid) - `TotalQueryTimeMs int64` Total end-to-end query execution time in milliseconds - `EmbeddingConfig EmbeddingConfigUnion` Embedding configuration used for query vectorization. None for lexical queries on model-less stores. - `type EmbeddingConfigModelsAPI struct{…}` - `ModelDeploymentID string` The ID of the deployment of the created model in the Models API V3. - `Type ModelsAPI` The type of the embedding configuration. - `const ModelsAPIModelsAPI ModelsAPI = "models_api"` - `type EmbeddingConfigBase struct{…}` - `EmbeddingModel EmbeddingModelName` The name of the base embedding model to use. Either a known base model (EmbeddingModelName) or, in ray-serve deployments with NATIVE_OPENAI_EMBEDDING_GATEWAY enabled, any model id served by the OpenAI-compatible inference proxy (e.g. 'nomic-embed-text-v1.5'). For fully custom deployments, use type 'models_api' with a model_deployment_id. - `type EmbeddingModelName string` - `const EmbeddingModelNameSentenceTransformersAllMiniLmL12V2 EmbeddingModelName = "sentence-transformers/all-MiniLM-L12-v2"` - `const EmbeddingModelNameSentenceTransformersMultiQaDistilbertCosV1 EmbeddingModelName = "sentence-transformers/multi-qa-distilbert-cos-v1"` - `const EmbeddingModelNameOpenAITextEmbeddingAda002 EmbeddingModelName = "openai/text-embedding-ada-002"` - `const EmbeddingModelNameOpenAITextEmbedding3Small EmbeddingModelName = "openai/text-embedding-3-small"` - `const EmbeddingModelNameOpenAITextEmbedding3Large EmbeddingModelName = "openai/text-embedding-3-large"` - `const EmbeddingModelNameEmbedEnglishV3_0 EmbeddingModelName = "embed-english-v3.0"` - `const EmbeddingModelNameEmbedEnglishLightV3_0 EmbeddingModelName = "embed-english-light-v3.0"` - `const EmbeddingModelNameEmbedMultilingualV3_0 EmbeddingModelName = "embed-multilingual-v3.0"` - `const EmbeddingModelNameGeminiTextEmbedding005 EmbeddingModelName = "gemini/text-embedding-005"` - `const EmbeddingModelNameGeminiTextMultilingualEmbedding002 EmbeddingModelName = "gemini/text-multilingual-embedding-002"` - `const EmbeddingModelNameGeminiGeminiEmbedding001 EmbeddingModelName = "gemini/gemini-embedding-001"` - `string` - `Type EmbeddingConfigBaseType` The type of the embedding configuration. - `const EmbeddingConfigBaseTypeBase EmbeddingConfigBaseType = "base"` - `EmbeddingTimeMs int64` Time spent generating embeddings in milliseconds (None for lexical queries) - `IndexQueryTimeMs int64` Time spent querying the vector index (OpenSearch) in milliseconds - `RerankingModel string` Reranking model used (None if reranking not enabled) - `RerankingTimeMs int64` Time spent reranking results in milliseconds (None if reranking not enabled) - `Vectors []VectorStoreQueryResponseVector` Array of matching documents - `ID string` Document ID - `Score float64` Similarity score indicating relevance - `Content TextContent` Text content for documents. - `Text string` Text content to be embedded - `Type TextContentType` Content type identifier - `const TextContentTypeText TextContentType = "text"` - `Metadata map[string, any]` Key-value metadata - `Vector []float64` Embedding vector (if requested) ### Example ```go package main import ( "context" "fmt" "github.com/scaleapi/sgp-dev-go" "github.com/scaleapi/sgp-dev-go/option" ) func main() { client := sgpdev.NewClient( option.WithAPIKey("My API Key"), option.WithAccountID("My Account ID"), ) response, err := client.VectorStores.Query( context.TODO(), "vector_store_name", sgpdev.VectorStoreQueryParams{ Content: sgpdev.TextContentParam{ Text: "text", }, }, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", response.Metadata) } ``` #### Response ```json { "metadata": { "search_type": "search_type", "total_query_time_ms": 0, "embedding_config": { "model_deployment_id": "model_deployment_id", "type": "models_api" }, "embedding_time_ms": 0, "index_query_time_ms": 0, "reranking_model": "reranking_model", "reranking_time_ms": 0 }, "vectors": [ { "id": "id", "score": 0, "content": { "text": "text", "type": "text" }, "metadata": { "foo": "bar" }, "vector": [ 0 ] } ] } ```