vector: VectorService gRPC contract (P1) (#12101)

* vector: VectorService protobuf contract

The shared RPC boundary between the Go S3 gateway and the Rust vector
engine from the vector design doc: CreateIndex/DropIndex, Put/Get/
List/Delete/Query vectors. A Table reference carries the Lance table id
and an optional pinned version, matching the snapshot discipline queries
are required to keep.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* vector: generated Go stubs for vector.proto

protoc output via weed/pb/Makefile.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* vector: carry return_data through QueryVectors

S3 Vectors QueryVectors honours returnData, but the contract had no
way to ask for or carry vector data in a query response, so the
gateway would need a second GetVectors round-trip per query. Add
return_data to the request and data to QueryResult now, while the
contract is still new.

* vector: pin metadata numbers to double precision in the contract

Metadata arrives as JSON, where numbers carry double precision; say
so on the field so neither side promises integer fidelity past 2^53.

* vector: clarify the query filter is raw Lance SQL over one metadata column

The doc said 'metadata columns' but the table stores all metadata in a
single JSON column named metadata; the gateway translates S3 Vectors
filter expressions onto it.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Chris LuandDevin authored and GitHub committed 2026-10-26 13:26:11 -07:00
1 parent 6b379badbb
commit d771a91571
4 files changed
+1701

No files matched your search

+1
View File
@@ -17,6 +17,7 @@ gen:
protoc mq_broker.proto --go_out=./mq_pb --go-grpc_out=./mq_pb --go_opt=paths=source_relative --go-grpc_opt=paths=source_relative
protoc mq_schema.proto --go_out=./schema_pb --go-grpc_out=./schema_pb --go_opt=paths=source_relative --go-grpc_opt=paths=source_relative
protoc mq_agent.proto --go_out=./mq_agent_pb --go-grpc_out=./mq_agent_pb --go_opt=paths=source_relative --go-grpc_opt=paths=source_relative
protoc vector.proto --go_out=./vector_pb --go-grpc_out=./vector_pb --go_opt=paths=source_relative --go-grpc_opt=paths=source_relative
protoc worker.proto --go_out=./worker_pb --go-grpc_out=./worker_pb --go_opt=paths=source_relative --go-grpc_opt=paths=source_relative
mkdir -p ./plugin_pb
protoc plugin.proto --go_out=./plugin_pb --go-grpc_out=./plugin_pb --go_opt=paths=source_relative --go-grpc_opt=paths=source_relative
+127
View File
@@ -0,0 +1,127 @@
syntax = "proto3";
package vector_pb;
option go_package = "github.com/seaweedfs/seaweedfs/weed/pb/vector_pb";
import "google/protobuf/struct.proto";
// The shared contract between the Go S3 gateway and the vector query engine.
// The public S3 Vectors API stays an AWS contract; this RPC is the internal
// boundary the design doc gives both editions.
service VectorService {
rpc CreateIndex(CreateIndexRequest) returns (CreateIndexResponse);
rpc DropIndex(DropIndexRequest) returns (DropIndexResponse);
rpc PutVectors(PutVectorsRequest) returns (PutVectorsResponse);
rpc GetVectors(GetVectorsRequest) returns (GetVectorsResponse);
rpc DeleteVectors(DeleteVectorsRequest) returns (DeleteVectorsResponse);
rpc ListVectors(ListVectorsRequest) returns (ListVectorsResponse);
rpc QueryVectors(QueryVectorsRequest) returns (QueryVectorsResponse);
}
enum DistanceMetric {
DISTANCE_METRIC_UNSPECIFIED = 0;
L2 = 1;
COSINE = 2;
DOT_PRODUCT = 3;
}
// Table addresses a Lance table through the namespace: the id parts as the
// namespace catalog joins them.
message Table {
repeated string id = 1;
// Dataset version to pin reads to; 0 means latest.
uint64 version = 2;
}
message CreateIndexRequest {
Table table = 1;
uint32 dimension = 2;
DistanceMetric distance_metric = 3;
repeated string non_filterable_metadata_keys = 4;
}
message CreateIndexResponse {
uint64 version = 1;
}
message DropIndexRequest {
Table table = 1;
}
message DropIndexResponse {}
message Vector {
string key = 1;
repeated float data = 2;
// JSON-typed metadata: numbers carry double precision, as on the wire.
google.protobuf.Struct metadata = 3;
}
message PutVectorsRequest {
Table table = 1;
repeated Vector vectors = 2;
}
message PutVectorsResponse {
uint64 version = 1;
}
message GetVectorsRequest {
Table table = 1;
repeated string keys = 2;
bool return_data = 3;
bool return_metadata = 4;
}
message GetVectorsResponse {
repeated Vector vectors = 1;
}
message DeleteVectorsRequest {
Table table = 1;
repeated string keys = 2;
}
message DeleteVectorsResponse {
uint64 version = 1;
}
message ListVectorsRequest {
Table table = 1;
uint32 max_results = 2;
string next_token = 3;
bool return_data = 4;
bool return_metadata = 5;
}
message ListVectorsResponse {
repeated Vector vectors = 1;
string next_token = 2;
}
message QueryVectorsRequest {
Table table = 1;
repeated float query_vector = 2;
uint32 top_k = 3;
// Lance SQL filter; empty means unfiltered. Metadata is one JSON
// `metadata` column, so the gateway translates S3 Vectors filter
// expressions onto it before they land here.
string filter = 4;
// Lance's post-filter escape hatch; off prefilters, matching S3 Vectors.
bool postfilter = 5;
bool return_metadata = 6;
bool return_distance = 7;
bool return_data = 8;
}
message QueryResult {
string key = 1;
float distance = 2;
google.protobuf.Struct metadata = 3;
repeated float data = 4;
}
message QueryVectorsResponse {
repeated QueryResult vectors = 1;
}
File diff suppressed because it is too large. Load diff
+357
View File
@@ -0,0 +1,357 @@
// Code generated by protoc-gen-go-grpc. DO NOT EDIT.
// versions:
// - protoc-gen-go-grpc v1.6.2
// - protoc v3.21.12
// source: vector.proto
package vector_pb
import (
context "context"
grpc "google.golang.org/grpc"
codes "google.golang.org/grpc/codes"
status "google.golang.org/grpc/status"
)
// This is a compile-time assertion to ensure that this generated file
// is compatible with the grpc package it is being compiled against.
// Requires gRPC-Go v1.64.0 or later.
const _ = grpc.SupportPackageIsVersion9
const (
VectorService_CreateIndex_FullMethodName = "/vector_pb.VectorService/CreateIndex"
VectorService_DropIndex_FullMethodName = "/vector_pb.VectorService/DropIndex"
VectorService_PutVectors_FullMethodName = "/vector_pb.VectorService/PutVectors"
VectorService_GetVectors_FullMethodName = "/vector_pb.VectorService/GetVectors"
VectorService_DeleteVectors_FullMethodName = "/vector_pb.VectorService/DeleteVectors"
VectorService_ListVectors_FullMethodName = "/vector_pb.VectorService/ListVectors"
VectorService_QueryVectors_FullMethodName = "/vector_pb.VectorService/QueryVectors"
)
// VectorServiceClient is the client API for VectorService service.
//
// For semantics around ctx use and closing/ending streaming RPCs, please refer to https://pkg.go.dev/google.golang.org/grpc/?tab=doc#ClientConn.NewStream.
//
// The shared contract between the Go S3 gateway and the vector query engine.
// The public S3 Vectors API stays an AWS contract; this RPC is the internal
// boundary the design doc gives both editions.
type VectorServiceClient interface {
CreateIndex(ctx context.Context, in *CreateIndexRequest, opts ...grpc.CallOption) (*CreateIndexResponse, error)
DropIndex(ctx context.Context, in *DropIndexRequest, opts ...grpc.CallOption) (*DropIndexResponse, error)
PutVectors(ctx context.Context, in *PutVectorsRequest, opts ...grpc.CallOption) (*PutVectorsResponse, error)
GetVectors(ctx context.Context, in *GetVectorsRequest, opts ...grpc.CallOption) (*GetVectorsResponse, error)
DeleteVectors(ctx context.Context, in *DeleteVectorsRequest, opts ...grpc.CallOption) (*DeleteVectorsResponse, error)
ListVectors(ctx context.Context, in *ListVectorsRequest, opts ...grpc.CallOption) (*ListVectorsResponse, error)
QueryVectors(ctx context.Context, in *QueryVectorsRequest, opts ...grpc.CallOption) (*QueryVectorsResponse, error)
}
type vectorServiceClient struct {
cc grpc.ClientConnInterface
}
func NewVectorServiceClient(cc grpc.ClientConnInterface) VectorServiceClient {
return &vectorServiceClient{cc}
}
func (c *vectorServiceClient) CreateIndex(ctx context.Context, in *CreateIndexRequest, opts ...grpc.CallOption) (*CreateIndexResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(CreateIndexResponse)
err := c.cc.Invoke(ctx, VectorService_CreateIndex_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
func (c *vectorServiceClient) DropIndex(ctx context.Context, in *DropIndexRequest, opts ...grpc.CallOption) (*DropIndexResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(DropIndexResponse)
err := c.cc.Invoke(ctx, VectorService_DropIndex_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
func (c *vectorServiceClient) PutVectors(ctx context.Context, in *PutVectorsRequest, opts ...grpc.CallOption) (*PutVectorsResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(PutVectorsResponse)
err := c.cc.Invoke(ctx, VectorService_PutVectors_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
func (c *vectorServiceClient) GetVectors(ctx context.Context, in *GetVectorsRequest, opts ...grpc.CallOption) (*GetVectorsResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(GetVectorsResponse)
err := c.cc.Invoke(ctx, VectorService_GetVectors_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
func (c *vectorServiceClient) DeleteVectors(ctx context.Context, in *DeleteVectorsRequest, opts ...grpc.CallOption) (*DeleteVectorsResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(DeleteVectorsResponse)
err := c.cc.Invoke(ctx, VectorService_DeleteVectors_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
func (c *vectorServiceClient) ListVectors(ctx context.Context, in *ListVectorsRequest, opts ...grpc.CallOption) (*ListVectorsResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(ListVectorsResponse)
err := c.cc.Invoke(ctx, VectorService_ListVectors_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
func (c *vectorServiceClient) QueryVectors(ctx context.Context, in *QueryVectorsRequest, opts ...grpc.CallOption) (*QueryVectorsResponse, error) {
cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
out := new(QueryVectorsResponse)
err := c.cc.Invoke(ctx, VectorService_QueryVectors_FullMethodName, in, out, cOpts...)
if err != nil {
return nil, err
}
return out, nil
}
// VectorServiceServer is the server API for VectorService service.
// All implementations must embed UnimplementedVectorServiceServer
// for forward compatibility.
//
// The shared contract between the Go S3 gateway and the vector query engine.
// The public S3 Vectors API stays an AWS contract; this RPC is the internal
// boundary the design doc gives both editions.
type VectorServiceServer interface {
CreateIndex(context.Context, *CreateIndexRequest) (*CreateIndexResponse, error)
DropIndex(context.Context, *DropIndexRequest) (*DropIndexResponse, error)
PutVectors(context.Context, *PutVectorsRequest) (*PutVectorsResponse, error)
GetVectors(context.Context, *GetVectorsRequest) (*GetVectorsResponse, error)
DeleteVectors(context.Context, *DeleteVectorsRequest) (*DeleteVectorsResponse, error)
ListVectors(context.Context, *ListVectorsRequest) (*ListVectorsResponse, error)
QueryVectors(context.Context, *QueryVectorsRequest) (*QueryVectorsResponse, error)
mustEmbedUnimplementedVectorServiceServer()
}
// UnimplementedVectorServiceServer must be embedded to have
// forward compatible implementations.
//
// NOTE: this should be embedded by value instead of pointer to avoid a nil
// pointer dereference when methods are called.
type UnimplementedVectorServiceServer struct{}
func (UnimplementedVectorServiceServer) CreateIndex(context.Context, *CreateIndexRequest) (*CreateIndexResponse, error) {
return nil, status.Error(codes.Unimplemented, "method CreateIndex not implemented")
}
func (UnimplementedVectorServiceServer) DropIndex(context.Context, *DropIndexRequest) (*DropIndexResponse, error) {
return nil, status.Error(codes.Unimplemented, "method DropIndex not implemented")
}
func (UnimplementedVectorServiceServer) PutVectors(context.Context, *PutVectorsRequest) (*PutVectorsResponse, error) {
return nil, status.Error(codes.Unimplemented, "method PutVectors not implemented")
}
func (UnimplementedVectorServiceServer) GetVectors(context.Context, *GetVectorsRequest) (*GetVectorsResponse, error) {
return nil, status.Error(codes.Unimplemented, "method GetVectors not implemented")
}
func (UnimplementedVectorServiceServer) DeleteVectors(context.Context, *DeleteVectorsRequest) (*DeleteVectorsResponse, error) {
return nil, status.Error(codes.Unimplemented, "method DeleteVectors not implemented")
}
func (UnimplementedVectorServiceServer) ListVectors(context.Context, *ListVectorsRequest) (*ListVectorsResponse, error) {
return nil, status.Error(codes.Unimplemented, "method ListVectors not implemented")
}
func (UnimplementedVectorServiceServer) QueryVectors(context.Context, *QueryVectorsRequest) (*QueryVectorsResponse, error) {
return nil, status.Error(codes.Unimplemented, "method QueryVectors not implemented")
}
func (UnimplementedVectorServiceServer) mustEmbedUnimplementedVectorServiceServer() {}
func (UnimplementedVectorServiceServer) testEmbeddedByValue() {}
// UnsafeVectorServiceServer may be embedded to opt out of forward compatibility for this service.
// Use of this interface is not recommended, as added methods to VectorServiceServer will
// result in compilation errors.
type UnsafeVectorServiceServer interface {
mustEmbedUnimplementedVectorServiceServer()
}
func RegisterVectorServiceServer(s grpc.ServiceRegistrar, srv VectorServiceServer) {
// If the following call panics, it indicates UnimplementedVectorServiceServer was
// embedded by pointer and is nil. This will cause panics if an
// unimplemented method is ever invoked, so we test this at initialization
// time to prevent it from happening at runtime later due to I/O.
if t, ok := srv.(interface{ testEmbeddedByValue() }); ok {
t.testEmbeddedByValue()
}
s.RegisterService(&VectorService_ServiceDesc, srv)
}
func _VectorService_CreateIndex_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(CreateIndexRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).CreateIndex(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_CreateIndex_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).CreateIndex(ctx, req.(*CreateIndexRequest))
}
return interceptor(ctx, in, info, handler)
}
func _VectorService_DropIndex_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(DropIndexRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).DropIndex(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_DropIndex_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).DropIndex(ctx, req.(*DropIndexRequest))
}
return interceptor(ctx, in, info, handler)
}
func _VectorService_PutVectors_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(PutVectorsRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).PutVectors(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_PutVectors_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).PutVectors(ctx, req.(*PutVectorsRequest))
}
return interceptor(ctx, in, info, handler)
}
func _VectorService_GetVectors_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(GetVectorsRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).GetVectors(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_GetVectors_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).GetVectors(ctx, req.(*GetVectorsRequest))
}
return interceptor(ctx, in, info, handler)
}
func _VectorService_DeleteVectors_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(DeleteVectorsRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).DeleteVectors(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_DeleteVectors_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).DeleteVectors(ctx, req.(*DeleteVectorsRequest))
}
return interceptor(ctx, in, info, handler)
}
func _VectorService_ListVectors_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(ListVectorsRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).ListVectors(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_ListVectors_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).ListVectors(ctx, req.(*ListVectorsRequest))
}
return interceptor(ctx, in, info, handler)
}
func _VectorService_QueryVectors_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
in := new(QueryVectorsRequest)
if err := dec(in); err != nil {
return nil, err
}
if interceptor == nil {
return srv.(VectorServiceServer).QueryVectors(ctx, in)
}
info := &grpc.UnaryServerInfo{
Server: srv,
FullMethod: VectorService_QueryVectors_FullMethodName,
}
handler := func(ctx context.Context, req interface{}) (interface{}, error) {
return srv.(VectorServiceServer).QueryVectors(ctx, req.(*QueryVectorsRequest))
}
return interceptor(ctx, in, info, handler)
}
// VectorService_ServiceDesc is the grpc.ServiceDesc for VectorService service.
// It's only intended for direct use with grpc.RegisterService,
// and not to be introspected or modified (even as a copy)
var VectorService_ServiceDesc = grpc.ServiceDesc{
ServiceName: "vector_pb.VectorService",
HandlerType: (*VectorServiceServer)(nil),
Methods: []grpc.MethodDesc{
{
MethodName: "CreateIndex",
Handler: _VectorService_CreateIndex_Handler,
},
{
MethodName: "DropIndex",
Handler: _VectorService_DropIndex_Handler,
},
{
MethodName: "PutVectors",
Handler: _VectorService_PutVectors_Handler,
},
{
MethodName: "GetVectors",
Handler: _VectorService_GetVectors_Handler,
},
{
MethodName: "DeleteVectors",
Handler: _VectorService_DeleteVectors_Handler,
},
{
MethodName: "ListVectors",
Handler: _VectorService_ListVectors_Handler,
},
{
MethodName: "QueryVectors",
Handler: _VectorService_QueryVectors_Handler,
},
},
Streams: []grpc.StreamDesc{},
Metadata: "vector.proto",
}