enhance: add NewSegmentWithLoadInfo API to support segment self-managed loading (#45061)

This commit introduces the foundation for enabling segments to manage
their own loading process by passing load information during segment
creation.

Changes:

C++ Layer:
- Add NewSegmentWithLoadInfo() C API to create segments with serialized
load info
- Add SetLoadInfo() method to SegmentInterface for storing load
information
- Refactor segment creation logic into shared CreateSegment() helper
function
- Add comprehensive documentation for the new API

Go Layer:
- Extend CreateCSegmentRequest to support optional LoadInfo field
- Update segment creation in querynode to pass SegmentLoadInfo when
available
- Add ConvertToSegcoreSegmentLoadInfo() and helper converters for proto
translation

Proto Definitions:
- Add segcorepb.SegmentLoadInfo message with essential loading metadata
- Add supporting messages: Binlog, FieldBinlog, FieldIndexInfo,
TextIndexStats, JsonKeyStats
- Remove dependency on data_coord.proto by creating segcore-specific
definitions

Testing:
- Add comprehensive unit tests for proto conversion functions
- Test edge cases including nil inputs, empty data, and nil array/map
elements

This is the first step toward issue #45060 - enabling segments to
autonomously manage their loading process, which will:
- Clarify responsibilities between Go and C++ layers
- Reduce cross-language call overhead
- Enable precise resource management at the C++ level
- Support better integration with caching layer
- Enable proactive schema evolution handling

Related to #45060

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>

internal/core/src/segcore/SegmentInterface.h

@@ -197,6 +197,9 @@ class SegmentInterface {
     // currently it's used to sync field data list with updated schema.
     virtual void
     FinishLoad() = 0;
+
+    virtual void
+    SetLoadInfo(const milvus::proto::segcore::SegmentLoadInfo& load_info) = 0;
 };
 
 // internal API for DSL calculation
@@ -381,6 +384,12 @@ class SegmentInternalInterface : public SegmentInterface {
                          FieldId field_id,
                          const std::string& nested_path) const override;
 
+    virtual void
+    SetLoadInfo(
+        const milvus::proto::segcore::SegmentLoadInfo& load_info) override {
+        load_info_ = load_info;
+    }
+
  public:
     // `query_offsets` is not null only for vector array (embedding list) search
     // where it denotes the number of vectors in each embedding list. The length
@@ -599,6 +608,8 @@ class SegmentInternalInterface : public SegmentInterface {
     // mutex protecting rw options on schema_
     std::shared_mutex sch_mutex_;
 
+    milvus::proto::segcore::SegmentLoadInfo load_info_;
+
     mutable std::shared_mutex mutex_;
     // fieldID -> std::pair<num_rows, avg_size>
     std::unordered_map<FieldId, std::pair<int64_t, int64_t>>

internal/core/src/segcore/segment_c.cpp

@@ -14,6 +14,8 @@
 #include <memory>
 #include <limits>
 
+#include "common/EasyAssert.h"
+#include "common/common_type_c.h"
 #include "pb/cgo_msg.pb.h"
 #include "pb/index_cgo_msg.pb.h"
 
@@ -27,6 +29,7 @@
 #include "log/Log.h"
 #include "mmap/Types.h"
 #include "monitor/scope_metric.h"
+#include "pb/segcore.pb.h"
 #include "segcore/Collection.h"
 #include "segcore/SegcoreConfig.h"
 #include "segcore/SegmentGrowingImpl.h"
@@ -45,6 +48,48 @@
 #include "common/GeometryCache.h"
 
 //////////////////////////////    common interfaces    //////////////////////////////
+
+/**
+ * @brief Create a segment from a collection.
+ * @param col The collection to create the segment from.
+ * @param seg_type The type of segment to create.
+ * @param segment_id The ID of the segment to create.
+ * @param is_sorted_by_pk Whether the data in the sealed segment is sorted by primary key.
+ * @return A unique pointer to a SegmentInterface object.
+ */
+std::unique_ptr<milvus::segcore::SegmentInterface>
+CreateSegment(milvus::segcore::Collection* col,
+              SegmentType seg_type,
+              int64_t segment_id,
+              bool is_sorted_by_pk) {
+    std::unique_ptr<milvus::segcore::SegmentInterface> segment;
+    switch (seg_type) {
+        case Growing: {
+            auto seg = milvus::segcore::CreateGrowingSegment(
+                col->get_schema(),
+                col->get_index_meta(),
+                segment_id,
+                milvus::segcore::SegcoreConfig::default_config());
+            segment = std::move(seg);
+            break;
+        }
+        case Sealed:
+        case Indexing:
+            segment = milvus::segcore::CreateSealedSegment(
+                col->get_schema(),
+                col->get_index_meta(),
+                segment_id,
+                milvus::segcore::SegcoreConfig::default_config(),
+                is_sorted_by_pk);
+            break;
+
+        default:
+            ThrowInfo(
+                milvus::UnexpectedError, "invalid segment type: {}", seg_type);
+    }
+    return segment;
+}
+
 CStatus
 NewSegment(CCollection collection,
            SegmentType seg_type,
@@ -56,33 +101,37 @@ NewSegment(CCollection collection,
     try {
         auto col = static_cast<milvus::segcore::Collection*>(collection);
 
-        std::unique_ptr<milvus::segcore::SegmentInterface> segment;
-        switch (seg_type) {
-            case Growing: {
-                auto seg = milvus::segcore::CreateGrowingSegment(
-                    col->get_schema(),
-                    col->get_index_meta(),
-                    segment_id,
-                    milvus::segcore::SegcoreConfig::default_config());
-                segment = std::move(seg);
-                break;
-            }
-            case Sealed:
-            case Indexing:
-                segment = milvus::segcore::CreateSealedSegment(
-                    col->get_schema(),
-                    col->get_index_meta(),
-                    segment_id,
-                    milvus::segcore::SegcoreConfig::default_config(),
-                    is_sorted_by_pk);
-                break;
+        auto segment =
+            CreateSegment(col, seg_type, segment_id, is_sorted_by_pk);
 
-            default:
-                ThrowInfo(milvus::UnexpectedError,
-                          "invalid segment type: {}",
-                          seg_type);
-        }
+        *newSegment = segment.release();
+        return milvus::SuccessCStatus();
+    } catch (std::exception& e) {
+        return milvus::FailureCStatus(&e);
+    }
+}
 
+CStatus
+NewSegmentWithLoadInfo(CCollection collection,
+                       SegmentType seg_type,
+                       int64_t segment_id,
+                       CSegmentInterface* newSegment,
+                       bool is_sorted_by_pk,
+                       const uint8_t* load_info_blob,
+                       const int64_t load_info_length) {
+    SCOPE_CGO_CALL_METRIC();
+
+    try {
+        AssertInfo(load_info_blob, "load info is null");
+        milvus::proto::segcore::SegmentLoadInfo load_info;
+        auto suc = load_info.ParseFromArray(load_info_blob, load_info_length);
+        AssertInfo(suc, "unmarshal load info failed");
+
+        auto col = static_cast<milvus::segcore::Collection*>(collection);
+
+        auto segment =
+            CreateSegment(col, seg_type, segment_id, is_sorted_by_pk);
+        segment->SetLoadInfo(load_info);
         *newSegment = segment.release();
         return milvus::SuccessCStatus();
     } catch (std::exception& e) {

internal/core/src/segcore/segment_c.h

@@ -36,6 +36,27 @@ NewSegment(CCollection collection,
            CSegmentInterface* newSegment,
            bool is_sorted_by_pk);
 
+// Create a new segment with pre-loaded segment information.
+// This function creates a segment and initializes it with serialized load info,
+// which can include precomputed metadata, statistics, or configuration data.
+//
+// @param collection: The collection that this segment belongs to
+// @param seg_type: Type of the segment (growing, sealed, etc.)
+// @param segment_id: Unique identifier for this segment
+// @param newSegment: Output parameter for the created segment interface
+// @param is_sorted_by_pk: Whether the segment data is sorted by primary key
+// @param load_info_blob: Serialized load information blob
+// @param load_info_length: Length of the load_info_blob in bytes
+// @return CStatus indicating success or failure
+CStatus
+NewSegmentWithLoadInfo(CCollection collection,
+                       SegmentType seg_type,
+                       int64_t segment_id,
+                       CSegmentInterface* newSegment,
+                       bool is_sorted_by_pk,
+                       const uint8_t* load_info_blob,
+                       const int64_t load_info_length);
+
 void
 DeleteSegment(CSegmentInterface c_segment);
 

internal/querynodev2/segments/segment.go

@@ -370,6 +370,7 @@ func NewSegment(ctx context.Context,
 			SegmentID:   loadInfo.GetSegmentID(),
 			SegmentType: segmentType,
 			IsSorted:    loadInfo.GetIsSorted(),
+			LoadInfo:    loadInfo,
 		})
 		return nil, err
 	}).Await(); err != nil {

internal/util/segcore/segment.go

@@ -23,6 +23,9 @@ import (
 	"github.com/milvus-io/milvus-proto/go-api/v2/commonpb"
 	"github.com/milvus-io/milvus/internal/storage"
 	"github.com/milvus-io/milvus/internal/util/cgo"
+	"github.com/milvus-io/milvus/pkg/v2/proto/datapb"
+	"github.com/milvus-io/milvus/pkg/v2/proto/querypb"
+	"github.com/milvus-io/milvus/pkg/v2/proto/segcorepb"
 	"github.com/milvus-io/milvus/pkg/v2/util/merr"
 )
 
@@ -42,6 +45,7 @@ type CreateCSegmentRequest struct {
 	SegmentID   int64
 	SegmentType SegmentType
 	IsSorted    bool
+	LoadInfo    *querypb.SegmentLoadInfo
 }
 
 func (req *CreateCSegmentRequest) getCSegmentType() C.SegmentType {
@@ -60,7 +64,17 @@ func (req *CreateCSegmentRequest) getCSegmentType() C.SegmentType {
 // CreateCSegment creates a segment from a CreateCSegmentRequest.
 func CreateCSegment(req *CreateCSegmentRequest) (CSegment, error) {
 	var ptr C.CSegmentInterface
-	status := C.NewSegment(req.Collection.rawPointer(), req.getCSegmentType(), C.int64_t(req.SegmentID), &ptr, C.bool(req.IsSorted))
+	var status C.CStatus
+	if req.LoadInfo != nil {
+		loadInfoBlob, err := proto.Marshal(req.LoadInfo)
+		if err != nil {
+			return nil, err
+		}
+
+		status = C.NewSegmentWithLoadInfo(req.Collection.rawPointer(), req.getCSegmentType(), C.int64_t(req.SegmentID), &ptr, C.bool(req.IsSorted), (*C.uint8_t)(unsafe.Pointer(&loadInfoBlob[0])), C.int64_t(len(loadInfoBlob)))
+	} else {
+		status = C.NewSegment(req.Collection.rawPointer(), req.getCSegmentType(), C.int64_t(req.SegmentID), &ptr, C.bool(req.IsSorted))
+	}
 	if err := ConsumeCStatusIntoError(&status); err != nil {
 		return nil, err
 	}
@@ -317,3 +331,160 @@ func (s *cSegmentImpl) DropJSONIndex(ctx context.Context, fieldID int64, nestedP
 func (s *cSegmentImpl) Release() {
 	C.DeleteSegment(s.ptr)
 }
+
+// ConvertToSegcoreSegmentLoadInfo converts querypb.SegmentLoadInfo to segcorepb.SegmentLoadInfo.
+// This function is needed because segcorepb.SegmentLoadInfo is a simplified version that doesn't
+// depend on data_coord.proto and excludes fields like start_position, delta_position, and level.
+func ConvertToSegcoreSegmentLoadInfo(src *querypb.SegmentLoadInfo) *segcorepb.SegmentLoadInfo {
+	if src == nil {
+		return nil
+	}
+
+	return &segcorepb.SegmentLoadInfo{
+		SegmentID:        src.GetSegmentID(),
+		PartitionID:      src.GetPartitionID(),
+		CollectionID:     src.GetCollectionID(),
+		DbID:             src.GetDbID(),
+		FlushTime:        src.GetFlushTime(),
+		BinlogPaths:      convertFieldBinlogs(src.GetBinlogPaths()),
+		NumOfRows:        src.GetNumOfRows(),
+		Statslogs:        convertFieldBinlogs(src.GetStatslogs()),
+		Deltalogs:        convertFieldBinlogs(src.GetDeltalogs()),
+		CompactionFrom:   src.GetCompactionFrom(),
+		IndexInfos:       convertFieldIndexInfos(src.GetIndexInfos()),
+		SegmentSize:      src.GetSegmentSize(),
+		InsertChannel:    src.GetInsertChannel(),
+		ReadableVersion:  src.GetReadableVersion(),
+		StorageVersion:   src.GetStorageVersion(),
+		IsSorted:         src.GetIsSorted(),
+		TextStatsLogs:    convertTextIndexStats(src.GetTextStatsLogs()),
+		Bm25Logs:         convertFieldBinlogs(src.GetBm25Logs()),
+		JsonKeyStatsLogs: convertJSONKeyStats(src.GetJsonKeyStatsLogs()),
+		Priority:         src.GetPriority(),
+	}
+}
+
+// convertFieldBinlogs converts datapb.FieldBinlog to segcorepb.FieldBinlog.
+func convertFieldBinlogs(src []*datapb.FieldBinlog) []*segcorepb.FieldBinlog {
+	if src == nil {
+		return nil
+	}
+
+	result := make([]*segcorepb.FieldBinlog, 0, len(src))
+	for _, fb := range src {
+		if fb == nil {
+			continue
+		}
+
+		result = append(result, &segcorepb.FieldBinlog{
+			FieldID:     fb.GetFieldID(),
+			Binlogs:     convertBinlogs(fb.GetBinlogs()),
+			ChildFields: fb.GetChildFields(),
+		})
+	}
+	return result
+}
+
+// convertBinlogs converts datapb.Binlog to segcorepb.Binlog.
+func convertBinlogs(src []*datapb.Binlog) []*segcorepb.Binlog {
+	if src == nil {
+		return nil
+	}
+
+	result := make([]*segcorepb.Binlog, 0, len(src))
+	for _, b := range src {
+		if b == nil {
+			continue
+		}
+
+		result = append(result, &segcorepb.Binlog{
+			EntriesNum:    b.GetEntriesNum(),
+			TimestampFrom: b.GetTimestampFrom(),
+			TimestampTo:   b.GetTimestampTo(),
+			LogPath:       b.GetLogPath(),
+			LogSize:       b.GetLogSize(),
+			LogID:         b.GetLogID(),
+			MemorySize:    b.GetMemorySize(),
+		})
+	}
+	return result
+}
+
+// convertFieldIndexInfos converts querypb.FieldIndexInfo to segcorepb.FieldIndexInfo.
+func convertFieldIndexInfos(src []*querypb.FieldIndexInfo) []*segcorepb.FieldIndexInfo {
+	if src == nil {
+		return nil
+	}
+
+	result := make([]*segcorepb.FieldIndexInfo, 0, len(src))
+	for _, fii := range src {
+		if fii == nil {
+			continue
+		}
+
+		result = append(result, &segcorepb.FieldIndexInfo{
+			FieldID:             fii.GetFieldID(),
+			EnableIndex:         fii.GetEnableIndex(),
+			IndexName:           fii.GetIndexName(),
+			IndexID:             fii.GetIndexID(),
+			BuildID:             fii.GetBuildID(),
+			IndexParams:         fii.GetIndexParams(),
+			IndexFilePaths:      fii.GetIndexFilePaths(),
+			IndexSize:           fii.GetIndexSize(),
+			IndexVersion:        fii.GetIndexVersion(),
+			NumRows:             fii.GetNumRows(),
+			CurrentIndexVersion: fii.GetCurrentIndexVersion(),
+			IndexStoreVersion:   fii.GetIndexStoreVersion(),
+		})
+	}
+	return result
+}
+
+// convertTextIndexStats converts datapb.TextIndexStats to segcorepb.TextIndexStats.
+func convertTextIndexStats(src map[int64]*datapb.TextIndexStats) map[int64]*segcorepb.TextIndexStats {
+	if src == nil {
+		return nil
+	}
+
+	result := make(map[int64]*segcorepb.TextIndexStats, len(src))
+	for k, v := range src {
+		if v == nil {
+			continue
+		}
+
+		result[k] = &segcorepb.TextIndexStats{
+			FieldID:    v.GetFieldID(),
+			Version:    v.GetVersion(),
+			Files:      v.GetFiles(),
+			LogSize:    v.GetLogSize(),
+			MemorySize: v.GetMemorySize(),
+			BuildID:    v.GetBuildID(),
+		}
+	}
+	return result
+}
+
+// convertJSONKeyStats converts datapb.JsonKeyStats to segcorepb.JsonKeyStats.
+func convertJSONKeyStats(src map[int64]*datapb.JsonKeyStats) map[int64]*segcorepb.JsonKeyStats {
+	if src == nil {
+		return nil
+	}
+
+	result := make(map[int64]*segcorepb.JsonKeyStats, len(src))
+	for k, v := range src {
+		if v == nil {
+			continue
+		}
+
+		result[k] = &segcorepb.JsonKeyStats{
+			FieldID:                v.GetFieldID(),
+			Version:                v.GetVersion(),
+			Files:                  v.GetFiles(),
+			LogSize:                v.GetLogSize(),
+			MemorySize:             v.GetMemorySize(),
+			BuildID:                v.GetBuildID(),
+			JsonKeyStatsDataFormat: v.GetJsonKeyStatsDataFormat(),
+		}
+	}
+	return result
+}

internal/util/segcore/segment_test.go

@@ -8,12 +8,15 @@ import (
 	"github.com/stretchr/testify/assert"
 	"google.golang.org/protobuf/proto"
 
+	"github.com/milvus-io/milvus-proto/go-api/v2/commonpb"
 	"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
 	"github.com/milvus-io/milvus/internal/mocks/util/mock_segcore"
 	"github.com/milvus-io/milvus/internal/storage"
 	"github.com/milvus-io/milvus/internal/util/initcore"
 	"github.com/milvus-io/milvus/internal/util/segcore"
+	"github.com/milvus-io/milvus/pkg/v2/proto/datapb"
 	"github.com/milvus-io/milvus/pkg/v2/proto/planpb"
+	"github.com/milvus-io/milvus/pkg/v2/proto/querypb"
 	"github.com/milvus-io/milvus/pkg/v2/proto/segcorepb"
 	"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
 	"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
@@ -139,3 +142,260 @@ func assertEqualCount(
 	assert.NotNil(t, retrieveResult2)
 	retrieveResult2.Release()
 }
+
+func TestConvertToSegcoreSegmentLoadInfo(t *testing.T) {
+	t.Run("nil input", func(t *testing.T) {
+		result := segcore.ConvertToSegcoreSegmentLoadInfo(nil)
+		assert.Nil(t, result)
+	})
+
+	t.Run("empty input", func(t *testing.T) {
+		src := &querypb.SegmentLoadInfo{}
+		result := segcore.ConvertToSegcoreSegmentLoadInfo(src)
+		assert.NotNil(t, result)
+		assert.Equal(t, int64(0), result.SegmentID)
+		assert.Equal(t, int64(0), result.PartitionID)
+		assert.Equal(t, int64(0), result.CollectionID)
+	})
+
+	t.Run("full conversion", func(t *testing.T) {
+		// Create source querypb.SegmentLoadInfo with all fields populated
+		src := &querypb.SegmentLoadInfo{
+			SegmentID:    1001,
+			PartitionID:  2001,
+			CollectionID: 3001,
+			DbID:         4001,
+			FlushTime:    5001,
+			BinlogPaths: []*datapb.FieldBinlog{
+				{
+					FieldID: 100,
+					Binlogs: []*datapb.Binlog{
+						{
+							EntriesNum:    10,
+							TimestampFrom: 1000,
+							TimestampTo:   2000,
+							LogPath:       "/path/to/binlog",
+							LogSize:       1024,
+							LogID:         9001,
+							MemorySize:    2048,
+						},
+					},
+					ChildFields: []int64{101, 102},
+				},
+			},
+			NumOfRows: 1000,
+			Statslogs: []*datapb.FieldBinlog{
+				{
+					FieldID: 200,
+					Binlogs: []*datapb.Binlog{
+						{
+							EntriesNum:    5,
+							TimestampFrom: 1500,
+							TimestampTo:   2500,
+							LogPath:       "/path/to/statslog",
+							LogSize:       512,
+							LogID:         9002,
+							MemorySize:    1024,
+						},
+					},
+				},
+			},
+			Deltalogs: []*datapb.FieldBinlog{
+				{
+					FieldID: 300,
+					Binlogs: []*datapb.Binlog{
+						{
+							EntriesNum:    3,
+							TimestampFrom: 2000,
+							TimestampTo:   3000,
+							LogPath:       "/path/to/deltalog",
+							LogSize:       256,
+							LogID:         9003,
+							MemorySize:    512,
+						},
+					},
+				},
+			},
+			CompactionFrom: []int64{8001, 8002},
+			IndexInfos: []*querypb.FieldIndexInfo{
+				{
+					FieldID:             100,
+					EnableIndex:         true,
+					IndexName:           "test_index",
+					IndexID:             7001,
+					BuildID:             7002,
+					IndexParams:         []*commonpb.KeyValuePair{{Key: "index_type", Value: "HNSW"}},
+					IndexFilePaths:      []string{"/path/to/index"},
+					IndexSize:           4096,
+					IndexVersion:        1,
+					NumRows:             1000,
+					CurrentIndexVersion: 2,
+					IndexStoreVersion:   3,
+				},
+			},
+			SegmentSize:     8192,
+			InsertChannel:   "insert_channel_1",
+			ReadableVersion: 6001,
+			StorageVersion:  7001,
+			IsSorted:        true,
+			TextStatsLogs: map[int64]*datapb.TextIndexStats{
+				400: {
+					FieldID:    400,
+					Version:    1,
+					Files:      []string{"/path/to/text/stats1", "/path/to/text/stats2"},
+					LogSize:    2048,
+					MemorySize: 4096,
+					BuildID:    9101,
+				},
+			},
+			Bm25Logs: []*datapb.FieldBinlog{
+				{
+					FieldID: 500,
+					Binlogs: []*datapb.Binlog{
+						{
+							EntriesNum:    7,
+							TimestampFrom: 3000,
+							TimestampTo:   4000,
+							LogPath:       "/path/to/bm25log",
+							LogSize:       768,
+							LogID:         9004,
+							MemorySize:    1536,
+						},
+					},
+				},
+			},
+			JsonKeyStatsLogs: map[int64]*datapb.JsonKeyStats{
+				600: {
+					FieldID:                600,
+					Version:                2,
+					Files:                  []string{"/path/to/json/stats"},
+					LogSize:                1024,
+					MemorySize:             2048,
+					BuildID:                9201,
+					JsonKeyStatsDataFormat: 1,
+				},
+			},
+			Priority: commonpb.LoadPriority_HIGH,
+		}
+
+		// Convert to segcorepb.SegmentLoadInfo
+		result := segcore.ConvertToSegcoreSegmentLoadInfo(src)
+
+		// Validate basic fields
+		assert.NotNil(t, result)
+		assert.Equal(t, src.SegmentID, result.SegmentID)
+		assert.Equal(t, src.PartitionID, result.PartitionID)
+		assert.Equal(t, src.CollectionID, result.CollectionID)
+		assert.Equal(t, src.DbID, result.DbID)
+		assert.Equal(t, src.FlushTime, result.FlushTime)
+		assert.Equal(t, src.NumOfRows, result.NumOfRows)
+		assert.Equal(t, src.SegmentSize, result.SegmentSize)
+		assert.Equal(t, src.InsertChannel, result.InsertChannel)
+		assert.Equal(t, src.ReadableVersion, result.ReadableVersion)
+		assert.Equal(t, src.StorageVersion, result.StorageVersion)
+		assert.Equal(t, src.IsSorted, result.IsSorted)
+		assert.Equal(t, src.Priority, result.Priority)
+		assert.Equal(t, src.CompactionFrom, result.CompactionFrom)
+
+		// Validate BinlogPaths conversion
+		assert.Equal(t, len(src.BinlogPaths), len(result.BinlogPaths))
+		assert.Equal(t, src.BinlogPaths[0].FieldID, result.BinlogPaths[0].FieldID)
+		assert.Equal(t, len(src.BinlogPaths[0].Binlogs), len(result.BinlogPaths[0].Binlogs))
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].EntriesNum, result.BinlogPaths[0].Binlogs[0].EntriesNum)
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].TimestampFrom, result.BinlogPaths[0].Binlogs[0].TimestampFrom)
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].TimestampTo, result.BinlogPaths[0].Binlogs[0].TimestampTo)
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].LogPath, result.BinlogPaths[0].Binlogs[0].LogPath)
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].LogSize, result.BinlogPaths[0].Binlogs[0].LogSize)
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].LogID, result.BinlogPaths[0].Binlogs[0].LogID)
+		assert.Equal(t, src.BinlogPaths[0].Binlogs[0].MemorySize, result.BinlogPaths[0].Binlogs[0].MemorySize)
+		assert.Equal(t, src.BinlogPaths[0].ChildFields, result.BinlogPaths[0].ChildFields)
+
+		// Validate Statslogs conversion
+		assert.Equal(t, len(src.Statslogs), len(result.Statslogs))
+		assert.Equal(t, src.Statslogs[0].FieldID, result.Statslogs[0].FieldID)
+
+		// Validate Deltalogs conversion
+		assert.Equal(t, len(src.Deltalogs), len(result.Deltalogs))
+		assert.Equal(t, src.Deltalogs[0].FieldID, result.Deltalogs[0].FieldID)
+
+		// Validate IndexInfos conversion
+		assert.Equal(t, len(src.IndexInfos), len(result.IndexInfos))
+		assert.Equal(t, src.IndexInfos[0].FieldID, result.IndexInfos[0].FieldID)
+		assert.Equal(t, src.IndexInfos[0].EnableIndex, result.IndexInfos[0].EnableIndex)
+		assert.Equal(t, src.IndexInfos[0].IndexName, result.IndexInfos[0].IndexName)
+		assert.Equal(t, src.IndexInfos[0].IndexID, result.IndexInfos[0].IndexID)
+		assert.Equal(t, src.IndexInfos[0].BuildID, result.IndexInfos[0].BuildID)
+		assert.Equal(t, len(src.IndexInfos[0].IndexParams), len(result.IndexInfos[0].IndexParams))
+		assert.Equal(t, src.IndexInfos[0].IndexFilePaths, result.IndexInfos[0].IndexFilePaths)
+		assert.Equal(t, src.IndexInfos[0].IndexSize, result.IndexInfos[0].IndexSize)
+		assert.Equal(t, src.IndexInfos[0].IndexVersion, result.IndexInfos[0].IndexVersion)
+		assert.Equal(t, src.IndexInfos[0].NumRows, result.IndexInfos[0].NumRows)
+		assert.Equal(t, src.IndexInfos[0].CurrentIndexVersion, result.IndexInfos[0].CurrentIndexVersion)
+		assert.Equal(t, src.IndexInfos[0].IndexStoreVersion, result.IndexInfos[0].IndexStoreVersion)
+
+		// Validate TextStatsLogs conversion
+		assert.Equal(t, len(src.TextStatsLogs), len(result.TextStatsLogs))
+		textStats := result.TextStatsLogs[400]
+		assert.NotNil(t, textStats)
+		assert.Equal(t, src.TextStatsLogs[400].FieldID, textStats.FieldID)
+		assert.Equal(t, src.TextStatsLogs[400].Version, textStats.Version)
+		assert.Equal(t, src.TextStatsLogs[400].Files, textStats.Files)
+		assert.Equal(t, src.TextStatsLogs[400].LogSize, textStats.LogSize)
+		assert.Equal(t, src.TextStatsLogs[400].MemorySize, textStats.MemorySize)
+		assert.Equal(t, src.TextStatsLogs[400].BuildID, textStats.BuildID)
+
+		// Validate Bm25Logs conversion
+		assert.Equal(t, len(src.Bm25Logs), len(result.Bm25Logs))
+		assert.Equal(t, src.Bm25Logs[0].FieldID, result.Bm25Logs[0].FieldID)
+
+		// Validate JsonKeyStatsLogs conversion
+		assert.Equal(t, len(src.JsonKeyStatsLogs), len(result.JsonKeyStatsLogs))
+		jsonStats := result.JsonKeyStatsLogs[600]
+		assert.NotNil(t, jsonStats)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].FieldID, jsonStats.FieldID)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].Version, jsonStats.Version)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].Files, jsonStats.Files)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].LogSize, jsonStats.LogSize)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].MemorySize, jsonStats.MemorySize)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].BuildID, jsonStats.BuildID)
+		assert.Equal(t, src.JsonKeyStatsLogs[600].JsonKeyStatsDataFormat, jsonStats.JsonKeyStatsDataFormat)
+	})
+
+	t.Run("nil elements in arrays and maps", func(t *testing.T) {
+		src := &querypb.SegmentLoadInfo{
+			SegmentID: 1001,
+			BinlogPaths: []*datapb.FieldBinlog{
+				nil, // nil element should be skipped
+				{FieldID: 100},
+			},
+			Statslogs: []*datapb.FieldBinlog{
+				nil,
+			},
+			IndexInfos: []*querypb.FieldIndexInfo{
+				nil,
+				{FieldID: 200},
+			},
+			TextStatsLogs: map[int64]*datapb.TextIndexStats{
+				100: nil, // nil value should be skipped
+				200: {FieldID: 200},
+			},
+			JsonKeyStatsLogs: map[int64]*datapb.JsonKeyStats{
+				300: nil,
+				400: {FieldID: 400},
+			},
+		}
+
+		result := segcore.ConvertToSegcoreSegmentLoadInfo(src)
+
+		assert.NotNil(t, result)
+		assert.Equal(t, 1, len(result.BinlogPaths))
+		assert.Equal(t, int64(100), result.BinlogPaths[0].FieldID)
+		assert.Equal(t, 0, len(result.Statslogs))
+		assert.Equal(t, 1, len(result.IndexInfos))
+		assert.Equal(t, int64(200), result.IndexInfos[0].FieldID)
+		assert.Equal(t, 1, len(result.TextStatsLogs))
+		assert.NotNil(t, result.TextStatsLogs[200])
+		assert.Equal(t, 1, len(result.JsonKeyStatsLogs))
+		assert.NotNil(t, result.JsonKeyStatsLogs[400])
+	})
+}

pkg/proto/segcore.proto

@@ -5,6 +5,41 @@ option go_package = "github.com/milvus-io/milvus/pkg/v2/proto/segcorepb";
 import "schema.proto";
 import "common.proto";
 
+message Binlog {
+  int64 entries_num = 1;
+  uint64 timestamp_from = 2;
+  uint64 timestamp_to = 3;
+  string log_path = 4;
+  int64 log_size = 5;
+  int64 logID = 6;
+  int64 memory_size = 7;
+}
+
+message FieldBinlog {
+  int64 fieldID = 1;
+  repeated Binlog binlogs = 2;
+  repeated int64 child_fields = 3;
+}
+
+message TextIndexStats {
+  int64 fieldID = 1;
+  int64 version = 2;
+  repeated string files = 3;
+  int64 log_size = 4;
+  int64 memory_size = 5;
+  int64 buildID = 6;
+}
+
+message JsonKeyStats {
+  int64 fieldID = 1;
+  int64 version = 2;
+  repeated string files = 3;
+  int64 log_size = 4;
+  int64 memory_size = 5;
+  int64 buildID = 6;
+  int64 json_key_stats_data_format = 7;
+}
+
 message RetrieveResults {
   schema.IDs ids = 1;
   repeated int64 offset = 2;
@@ -46,3 +81,41 @@ message CollectionIndexMeta {
   int64 maxIndexRowCount = 1;
   repeated FieldIndexMeta index_metas = 2;
 }
+
+message FieldIndexInfo {
+  int64 fieldID = 1;
+  bool enable_index = 2 [deprecated = true];
+  string index_name = 3;
+  int64 indexID = 4;
+  int64 buildID = 5;
+  repeated common.KeyValuePair index_params = 6;
+  repeated string index_file_paths = 7;
+  int64 index_size = 8;
+  int64 index_version = 9;
+  int64 num_rows = 10;
+  int32 current_index_version = 11;
+  int64 index_store_version = 12;
+}
+
+message SegmentLoadInfo {
+  int64 segmentID = 1;
+  int64 partitionID = 2;
+  int64 collectionID = 3;
+  int64 dbID = 4;
+  int64 flush_time = 5;
+  repeated FieldBinlog binlog_paths = 6;
+  int64 num_of_rows = 7;
+  repeated FieldBinlog statslogs = 8;
+  repeated FieldBinlog deltalogs = 9;
+  repeated int64 compactionFrom = 10;  // segmentIDs compacted from
+  repeated FieldIndexInfo index_infos = 11;
+  int64 segment_size = 12 [deprecated = true];
+  string insert_channel = 13;
+  int64 readableVersion = 14;
+  int64 storageVersion = 15;
+  bool is_sorted = 16;
+  map<int64, TextIndexStats> textStatsLogs = 17;
+  repeated FieldBinlog bm25logs = 18;
+  map<int64, JsonKeyStats> jsonKeyStatsLogs = 19;
+  common.LoadPriority priority = 20;
+}