Page History

...

ISSUE: #6299

PRs: #6570 #6598 #6671 #7102

Keywords: Query / Search / Vector

...

Motivation

In Milvus 2.0rc1, operations like query do  does not support return vector field in output. Proxy will check If query request's output fields , if find their data types contain float vector or binary vector, proxy error proxy will error out.

This is for the consideration of memory consumption,because  because vector field with big dimension will occupy hundreds of times of memory comparing with scalar

field. So generally load_collection or load_partitionpartition only load scalar fields' raw data into memory. Vector fields' raw data is loaded into memory only in 3 cases:

1. steaming streaming segment
2. vector field's index type is FLAT
3. vector field's index has not been created

If Only if vector's raw data has been loaded into memory, query has already supported to  can return vector field in output.

But query need this capability to return vector's raw data, for example tester can use this to check the correctness of inserted data.

Currently search also does not support return vector field in output, but we don't plan to enhance search in this project. If users need to get the vector data after

search returns ID, they can call query to get it.

If there is real requirement from users to let search return vector in output, we can achieve this in SDK level.

Design Details

Query supporting vector field in output can be divided into 2 steps:

1. in load segment stage, create VectorFieldInfo for vector fields, and save it into segment struct
2. in the end of query stage, 
   1. load vector field's data if needed
   2. get vector data, fill in query result

• Add new field VectorFieldInfo into segment struct to return vector field related information  

...

// For vector output fields, load raw data from fieldBinlog if needed,
// get vector raw data via result.Offset from *VectorfieldInfo, then
// fill vector raw data into result
func (q *queryCollection) fillVectorFieldsData(segment *Segment, result *segcorepb.RetrieveResults) error

We also enhanced query to support wildcard in output fields.

• "*" - means all scalar fields
• "%" - means all vector fields

For example, A/B are scalar fields, C/D are vector fields, duplicated fields are automatically removed.

• output_fields=["*"] ==> [A,B]
• output_fields=["%"] ==> [C,D]
• output_fields=["*","%"] ==> [A,B,C,D]
• output_fields=["*",A] ==> [A,B]
• output_fields=["*",C] ==> [A,B,C]

Original vector data storage public interface and struct

Public Interfaces```go
type FileManager interface {
GetFile(path string) . It may be discussed and changed in future.

type ChunkManager interface {
	GetPath(key string) (string, error)

...

	Write(key string, content []byte) error

...

	Exist(

...

key string) bool
	Read(key string) ([]byte, error)
	ReadAt(key string, p []byte, off int64) (n int, err error)
}

ReadFile(path string) []byte
}
```A VectorFileManager implements FileManager interface and add a method to download vector file from remote and deserialize its content, finally save pure vector to local storage.```go

type

...

 VectorChunkManager struct {
	localChunkManager  ChunkManager
	remoteChunkManager ChunkManager
}

func NewVectorChunkManager(localChunkManager ChunkManager, remoteChunkManager ChunkManager) *VectorChunkManager

localChunkManager {
localFileManager FileManager
remoteFileManager FileManager
insertCodec *InsertCodec
}
```localFileManager is responsible to local file manager. And can be implements with golang os library. The path of local chunk manager is config in milvus.yaml with key storage.path.
remoteFileManager remoteChunkManager is responsible for cloud storage or remote server storage, and will be implemented with minio client now.

When the offset of vector is obtained, we can get origin vector data from local vector data file.

Get the vector the ID through the following process：

1.Get segment's id size in each binlog and vector file names when load_segment. The binlogs file will be sorted by file name's last id to guarantee the order is increasing. Suppose we get sizes are 300, 300, 400, 500.

2.Get the id offset in segment in C layer. Suppose we get an offset 700.

3.We can know the vector we want to get is in 3rd vector files. for 300+300 <700<300+300+400

4.Get the 3rd file in to memory and deserialize out pure vector. Save the vector to local storage. Release the memory usage.

5.Mmap the file to memory, and get the data of offset 100. The data length differs data type and dim.

Test Plan

Do query / search (with vector field in output fields) in all kinds of combinations of following scenarios, check the correctness of result.

...