Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cyborg.co/llms.txt

Use this file to discover all available pages before exploring further.

​
VectorItem

Represents a single vector with its associated data. 
type VectorItem struct {
    Id       string                 `json:"id"`                // Unique identifier
    Vector   []float32              `json:"vector,omitempty"`  // Vector data
    Contents NullableContents       `json:"contents,omitempty"` // Optional text content  
    Metadata map[string]interface{} `json:"metadata,omitempty"` // Optional metadata
}

​
Fields

FieldTypeDescription
IdstringUnique identifier for the vector (required)
Vector[]float32The vector data as float32 slice
ContentsNullableContentsOptional text content associated with the vector
Metadatamap[string]interface{}Optional key-value pairs for filtering and retrieval

​
CreateIndexParams

Parameters for creating a new encrypted vector index. 
type CreateIndexParams struct {
    IndexName      string     `json:"index_name"`            // Unique identifier for the index
    IndexKey       []byte     `json:"index_key"`             // 32-byte encryption key
    IndexConfig    IndexModel `json:"index_config,omitempty"` // Index configuration
    Metric         *string    `json:"metric,omitempty"`       // Distance metric
    EmbeddingModel *string    `json:"embedding_model,omitempty"` // Associated embedding model
}

​
Fields

FieldTypeRequiredDescription
IndexNamestringYesUnique identifier for the index
IndexKey[]byteYes32-byte encryption key (use GenerateKey() to create)
IndexConfigIndexModelNoIndex configuration (IVFFlat, IVFPQ, or IVFSQ)
Metric*stringNoDistance metric (“euclidean”, “squared_euclidean”, “cosine”)
EmbeddingModel*stringNoName of embedding model to associate

​
Index Configuration Types

​
IndexModel Interface

All index configuration types implement this interface. 
type IndexModel interface {
    ToIndexConfig() *internal.IndexConfig
}

​
IVFSQ Configuration

Create an IVFSQ (Scalar Quantization) index configuration that compresses each dimension independently. 
func IndexIVFSQ(dimension int32, sqBits int32) *indexIVFSQ

​
Parameters

ParameterTypeDescription
dimensionint32The dimensionality of vectors that will be stored
sqBitsint32Number of bits per dimension for scalar quantization (default: 16)

​
IVFFlat Configuration

Create an IVFFlat (Inverted File Flat) index configuration for higher accuracy. 
func IndexIVFFlat(dimension int32) *indexIVFFlat

​
Parameters

ParameterTypeDescription
dimensionint32The dimensionality of vectors that will be stored

​
IVFPQ Configuration

Create an IVFPQ (Inverted File with Product Quantization) index configuration for memory efficiency. 
func IndexIVFPQ(dimension int32, pqDim int32, pqBits int32) *indexIVFPQ

​
Parameters

ParameterTypeDescription
dimensionint32The dimensionality of vectors that will be stored
pqDimint32Product quantization dimension (typically dimension/8 or dimension/16)
pqBitsint32Bits per PQ code (typically 8, higher = more accurate but larger)

​
Response Types

​
QueryResponse

Response from similarity search operations. 
type QueryResponse = internal.QueryResponse
Contains search results with similar vectors and their metadata.

​
QueryResultItem

A single result from a similarity search query. 
type QueryResultItem = internal.QueryResultItem
Represents one matching vector with its similarity score and metadata.

​
GetResponse

Response from Get operations containing retrieved vectors. 
type GetResponse = internal.GetResponseModel

​
ListIDsResponse

Response from ListIDs operations. 
type ListIDsResponse = internal.ListIDsResponse
Contains the list of vector IDs in the index.

​
Fields

FieldTypeDescription
Ids[]stringList of all vector ID strings in the index
Countint32Total number of IDs in the index

​
TrainParams

Parameters for training an encrypted vector index. 
type TrainParams struct {
    BatchSize  *int32   `json:"batch_size,omitempty"`  // Number of vectors per training batch
    MaxIters   *int32   `json:"max_iters,omitempty"`   // Maximum training iterations  
    Tolerance  *float64 `json:"tolerance,omitempty"`   // Convergence tolerance
    MaxMemory  *int32   `json:"max_memory,omitempty"`  // Maximum memory usage in MB
    NLists     *int32   `json:"n_lists,omitempty"`     // Number of IVF clusters
}

​
Fields

FieldTypeDescription
BatchSize*int32Number of vectors processed per training batch (default: 2048)
MaxIters*int32Maximum training iterations (default: 100)
Tolerance*float64Convergence tolerance for training (default: 1e-6)
MaxMemory*int32Maximum memory usage in MB, 0 = no limit (default: 0)
NLists*int32Number of IVF clusters, 0 = auto-determine (default: 0)

​
UpsertInput Interface

Sealed interface implemented by types that can be passed to Upsert. 
type UpsertInput interface {
    isUpsertInput()
}
Valid implementations: VectorItems, BinaryUpsertParams

​
QueryInput Interface

Sealed interface implemented by types that can be passed to Query. 
type QueryInput interface {
    isQueryInput()
}
Valid implementations: QueryParams, BinaryQueryParams

​
VectorItems

A slice of VectorItem that implements UpsertInput for type-safe upsert operations. 
type VectorItems []VectorItem

​
BinaryUpsertParams

Parameters for binary format vector upserts. More efficient than VectorItems for large batches. 
type BinaryUpsertParams struct {
    IDs      []string
    Vectors  [][]float32
    Metadata []map[string]interface{}
    Contents []string
}

​
Fields

FieldTypeRequiredDescription
IDs[]stringYesUnique identifiers for each vector
Vectors[][]float32YesVector data, shape [n_vectors][dimension]
Metadata[]map[string]interface{}NoOptional metadata for each vector (length must match IDs if provided)
Contents[]stringNoOptional content strings for each vector (length must match IDs if provided)

​
BinaryQueryParams

Parameters for binary format similarity search. More efficient than QueryParams for large batch queries. 
type BinaryQueryParams struct {
    QueryVectors [][]float32
    TopK         int32
    NProbes      *int32
    Greedy       *bool
    Filters      map[string]interface{}
    Include      []string
}

​
Fields

FieldTypeRequiredDescription
QueryVectors[][]float32YesQuery vectors, shape [n_queries][dimension]
TopKint32NoNumber of nearest neighbors to return (default: 100)
NProbes*int32NoNumber of IVF lists to probe
Greedy*boolNoEnable greedy search mode
Filtersmap[string]interface{}NoMetadata filters to apply
Include[]stringNoFields to include in response. Defaults to [] (only id is returned)

​
QueryParams

Parameters for similarity search queries. Supports single vector, batch, and content-based queries. 
type QueryParams struct {
    QueryVector       []float32              `json:"query_vector,omitempty"`
    BatchQueryVectors [][]float32            `json:"query_vectors,omitempty"`
    QueryContents     *string                `json:"query_contents,omitempty"`
    TopK              int32                  `json:"top_k"`
    NProbes           *int32                 `json:"n_probes,omitempty"`
    Greedy            *bool                  `json:"greedy,omitempty"`
    Filters           map[string]interface{} `json:"filters,omitempty"`
    Include           []string               `json:"include"`
}

​
Fields

FieldTypeRequiredDescription
QueryVector[]float32NoSingle query vector for similarity search
BatchQueryVectors[][]float32NoMultiple query vectors for batch search
QueryContents*stringNoText content for semantic search
TopKint32NoNumber of nearest neighbors to return
NProbes*int32NoNumber of clusters to probe for search
Greedy*boolNoUse greedy search algorithm
Filtersmap[string]interface{}NoMetadata filters to apply
Include[]stringNoFields to include in results: "metadata", "distance", "vector", "contents". Defaults to [] (only id is returned)