vus-sdk-java.2.4.7.source-code.schema.proto Maven / Gradle / Ivy

Go to download
syntax = "proto3";
package milvus.proto.schema;

option go_package = "github.com/milvus-io/milvus-proto/go-api/v2/schemapb";

option java_multiple_files = true;
option java_package = "io.milvus.grpc";
option java_outer_classname = "SchemaProto";
option java_generate_equals_and_hash = true;

option csharp_namespace = "Milvus.Client.Grpc";

import "common.proto";
import "google/protobuf/descriptor.proto";

/**
 * @brief Field data type
 */
enum DataType {
  None = 0;
  Bool = 1;
  Int8 = 2;
  Int16 = 3;
  Int32 = 4;
  Int64 = 5;

  Float = 10;
  Double = 11;

  String = 20;
  VarChar = 21; // variable-length strings with a specified maximum length
  Array = 22;
  JSON = 23;

  BinaryVector = 100;
  FloatVector = 101;
  Float16Vector = 102;
  BFloat16Vector = 103;
  SparseFloatVector = 104;
}

enum FieldState {
  FieldCreated = 0;
  FieldCreating = 1;
  FieldDropping = 2;
  FieldDropped = 3;
}

/**
 * @brief Field schema
 */
message FieldSchema {
  int64 fieldID = 1;
  string name = 2;
  bool is_primary_key = 3;
  string description = 4;
  DataType data_type = 5;
  repeated common.KeyValuePair type_params = 6;
  repeated common.KeyValuePair index_params = 7;
  bool autoID = 8;
  FieldState state = 9; // To keep compatible with older version, the default
                        // state is `Created`.
  DataType element_type = 10; // For array type, the element type is stored here
  ValueField default_value = 11; // default_value only support scalars except array and json for now
  bool is_dynamic = 12; // mark whether this field is the dynamic field
  bool is_partition_key = 13; // enable logic partitions
  bool is_clustering_key = 14;
}

/**
 * @brief Collection schema
 */
message CollectionSchema {
  string name = 1;
  string description = 2;
  bool autoID = 3 [deprecated=true]; // deprecated later, keep compatible with c++ part now
  repeated FieldSchema fields = 4;
  bool enable_dynamic_field = 5; // mark whether this table has the dynamic field function enabled.
  repeated common.KeyValuePair properties = 6;
}

message BoolArray { repeated bool data = 1; }

message IntArray { repeated int32 data = 1; }

message LongArray { repeated int64 data = 1; }

message FloatArray { repeated float data = 1; }

message DoubleArray { repeated double data = 1; }

// For special fields such as bigdecimal, array...
message BytesArray { repeated bytes data = 1; }

message StringArray { repeated string data = 1; }

message ArrayArray {
  repeated ScalarField data = 1;
  DataType element_type = 2;
}

message JSONArray { repeated bytes data = 1; }

message ValueField {
  oneof data {
    bool bool_data = 1;
    int32 int_data = 2;
    int64 long_data = 3;
    float float_data = 4;
    double double_data = 5;
    string string_data = 6;
    bytes bytes_data = 7;
  }
}

message ScalarField {
  oneof data {
    BoolArray bool_data = 1;
    IntArray int_data = 2;
    LongArray long_data = 3;
    FloatArray float_data = 4;
    DoubleArray double_data = 5;
    StringArray string_data = 6;
    BytesArray bytes_data = 7;
    ArrayArray array_data = 8;
    JSONArray json_data = 9;
  }
}

// beta, api may change
message SparseFloatArray {
  repeated bytes contents = 1;
  // dim is the max dimension of the current batch of vectors
  int64 dim = 2;
}

message VectorField {
  // For sparse vector, dim is the max dimension of the current batch of vectors
  int64 dim = 1;
  oneof data {
    FloatArray float_vector = 2;
    bytes binary_vector = 3;
    bytes float16_vector = 4;
    bytes bfloat16_vector = 5;
    SparseFloatArray sparse_float_vector = 6;
  }
}

message FieldData {
  DataType type = 1;
  string field_name = 2;
  oneof field {
    ScalarField scalars = 3;
    VectorField vectors = 4;
  }
  int64 field_id = 5;
  bool is_dynamic = 6;
}

message IDs {
  oneof id_field {
    LongArray int_id = 1;
    StringArray str_id = 2;
  }
}

message SearchResultData {
  int64 num_queries = 1;
  int64 top_k = 2;
  repeated FieldData fields_data = 3;
  repeated float scores = 4;
  IDs ids = 5;
  repeated int64 topks = 6;
  repeated string output_fields = 7;
  FieldData group_by_field_value = 8;
  int64 all_search_count = 9;
  repeated float distances = 10;
}

// vector field clustering info
message VectorClusteringInfo {
  // for multi vectors
  string field = 1;
  schema.VectorField centroid = 2;
}

// Scalar field clustering info
// todo more definitions: min/max, etc
message ScalarClusteringInfo {
  string field = 1;
}

// clustering distribution info of a certain data unit, it can be segment, partition, etc.
message ClusteringInfo {
  repeated VectorClusteringInfo vector_clustering_infos = 1;
  repeated ScalarClusteringInfo scalar_clustering_infos = 2;
}