mirror of
https://gitee.com/milvus-io/milvus.git
synced 2026-01-07 19:31:51 +08:00
https://github.com/milvus-io/milvus/issues/42589 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Semantic Highlighting Feature **Core Invariant**: Semantic highlighting operates on a per-field basis with independent text processing through an external Zilliz highlight provider. The implementation maintains field ID to field name mapping and correlates highlight results back to original field outputs. **What is Added**: This PR introduces semantic highlighting capability for search results alongside the existing lexical highlighting. The feature consists of: - New `SemanticHighlight` orchestrator that validates queries/input fields against collection schema, instantiates a Zilliz-based provider, and batches text processing across multiple queries - New `SemanticHighlighter` proxy wrapper implementing the `Highlighter` interface for search pipeline integration - New `semanticHighlightOperator` that processes search results by delegating per-field text processing to the provider and attaching correlated `HighlightResult` data to search outputs - New gRPC service definition (`HighlightService`) and `ZillizClient.Highlight()` method for external provider communication **No Data Loss or Regression**: The change is purely additive without modifying existing logic: - Lexical highlighting path remains unchanged (separate switch case in `createHighlightTask`) - New `HighlightResults` field is only populated when semantic highlighting is explicitly requested via `HighlightType_Semantic` enum value - Gracefully handles missing fields by returning explicit errors rather than silent failures - Pipeline operator integration follows existing patterns and only processes when semantic highlighter is instantiated **Why This Design**: Semantic highlighting is routed through the same pipeline operator pattern as lexical highlighting, ensuring consistent integration into search workflows. The per-field model allows flexible highlighting across different text columns and batch processing ensures efficient handling of multiple queries with configurable provider constraints. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: junjie.jiang <junjie.jiang@zilliz.com>
92 lines
1.8 KiB
Protocol Buffer
92 lines
1.8 KiB
Protocol Buffer
syntax = "proto3";
|
|
|
|
package milvus.proto.modelservice;
|
|
option go_package="github.com/milvus-io/milvus/pkg/v2/proto/modelservicepb";
|
|
|
|
service TextEmbeddingService {
|
|
rpc Embedding(TextEmbeddingRequest) returns (TextEmbeddingResponse);
|
|
}
|
|
|
|
service RerankService {
|
|
rpc Rerank(TextRerankRequest) returns (TextRerankResponse);
|
|
}
|
|
|
|
service HighlightService {
|
|
rpc Highlight(HighlightRequest) returns (HighlightResponse);
|
|
}
|
|
|
|
message Status {
|
|
int32 code = 1;
|
|
string msg = 2;
|
|
}
|
|
|
|
message DenseVector {
|
|
enum DType {
|
|
DTYPE_UNSPECIFIED = 0;
|
|
DTYPE_FLOAT = 1;
|
|
DTYPE_INT8 = 2;
|
|
}
|
|
|
|
DType dtype = 1;
|
|
bytes data = 2;
|
|
int32 dim = 3; // Optional
|
|
}
|
|
|
|
message SparseVector {
|
|
repeated int32 indices = 1;
|
|
repeated float values = 2;
|
|
}
|
|
|
|
message MultiVector {
|
|
repeated DenseVector token_vectors = 1;
|
|
int32 dim = 2; // Optional
|
|
}
|
|
|
|
message TextEmbeddingRequest {
|
|
string model = 1;
|
|
repeated string texts = 2;
|
|
map<string, string> params = 3;
|
|
}
|
|
|
|
message EmbeddingResult {
|
|
DenseVector dense = 1;
|
|
SparseVector sparse = 2;
|
|
MultiVector multi_vector = 3;
|
|
}
|
|
|
|
message TextEmbeddingResponse {
|
|
Status status = 1;
|
|
map<string, string> extra_info = 2;
|
|
repeated EmbeddingResult results = 3;
|
|
}
|
|
|
|
message TextRerankRequest {
|
|
string model = 1;
|
|
string query = 2;
|
|
repeated string documents = 3;
|
|
map<string, string> params = 4;
|
|
}
|
|
|
|
message TextRerankResponse {
|
|
Status status = 1;
|
|
map<string, string> extra_info = 2;
|
|
repeated float scores = 3;
|
|
}
|
|
|
|
message HighlightRequest {
|
|
string model = 1;
|
|
string query = 2;
|
|
repeated string documents = 3;
|
|
map<string, string> params = 4;
|
|
}
|
|
|
|
message HighlightResult {
|
|
repeated string sentences = 1;
|
|
}
|
|
|
|
message HighlightResponse {
|
|
Status status = 1;
|
|
map<string, string> extra_info = 2;
|
|
repeated HighlightResult results = 3;
|
|
}
|