Skip to content

Commit 8a7ce8e

Browse files
gcf-owl-bot[bot]gcf-owl-bot[bot]
authored
feat: Add EmbedContent method v1beta1 (#6833)
* feat: Add EmbedContent method v1beta1 PiperOrigin-RevId: 822273804 Source-Link: googleapis/googleapis@bb4016f Source-Link: googleapis/googleapis-gen@9e09a79 Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWFpcGxhdGZvcm0vLk93bEJvdC55YW1sIiwiaCI6IjllMDlhNzkzNzcyNGU1MTcyYjFkZGEyOTE4NGQ4MzMzMzYwMjE5NTEifQ== * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md --------- Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
1 parent 7f614ac commit 8a7ce8e

50 files changed

Lines changed: 2926 additions & 1 deletion

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎packages/google-cloud-aiplatform/README.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -693,6 +693,7 @@ Samples are in the [`samples/`][homepage_samples] directory. Each sample's `READ
693693
| count tokens | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.count_tokens.js) |
694694
| direct predict | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.direct_predict.js) |
695695
| direct raw predict | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.direct_raw_predict.js) |
696+
| embed content | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.embed_content.js) |
696697
| explain | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.explain.js) |
697698
| generate content | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.generate_content.js) |
698699
| predict | [source code](https://github.com/googleapis/google-cloud-node/blob/main/packages/google-cloud-aiplatform/samples/generated/v1beta1/prediction_service.predict.js) |

‎packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/prediction_service.proto‎

Lines changed: 89 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -25,6 +25,7 @@ import "google/cloud/aiplatform/v1beta1/content.proto";
2525
import "google/cloud/aiplatform/v1beta1/explanation.proto";
2626
import "google/cloud/aiplatform/v1beta1/tool.proto";
2727
import "google/cloud/aiplatform/v1beta1/types.proto";
28+
import "google/cloud/aiplatform/v1beta1/usage_metadata.proto";
2829
import "google/protobuf/struct.proto";
2930
import "google/protobuf/timestamp.proto";
3031

@@ -239,6 +240,15 @@ service PredictionService {
239240
};
240241
option (google.api.method_signature) = "endpoint,http_body";
241242
}
243+
244+
// Embed content with multimodal inputs.
245+
rpc EmbedContent(EmbedContentRequest) returns (EmbedContentResponse) {
246+
option (google.api.http) = {
247+
post: "/v1beta1/{model=projects/*/locations/*/publishers/*/models/*}:embedContent"
248+
body: "*"
249+
};
250+
option (google.api.method_signature) = "model,content";
251+
}
242252
}
243253

244254
// Request message for
@@ -950,3 +960,82 @@ message GenerateVideoResponse {
950960
// Returns rai failure reasons if any.
951961
repeated string rai_media_filtered_reasons = 3;
952962
}
963+
964+
// Request message for
965+
// [PredictionService.EmbedContent][google.cloud.aiplatform.v1beta1.PredictionService.EmbedContent].
966+
message EmbedContentRequest {
967+
// Represents a downstream task the embeddings will be used for.
968+
enum EmbeddingTaskType {
969+
// Unset value, which will default to one of the other enum values.
970+
UNSPECIFIED = 0;
971+
972+
// Specifies the given text is a query in a search/retrieval setting.
973+
RETRIEVAL_QUERY = 2;
974+
975+
// Specifies the given text is a document from the corpus being searched.
976+
RETRIEVAL_DOCUMENT = 3;
977+
978+
// Specifies the given text will be used for STS.
979+
SEMANTIC_SIMILARITY = 4;
980+
981+
// Specifies that the given text will be classified.
982+
CLASSIFICATION = 5;
983+
984+
// Specifies that the embeddings will be used for clustering.
985+
CLUSTERING = 6;
986+
987+
// Specifies that the embeddings will be used for question answering.
988+
QUESTION_ANSWERING = 7;
989+
990+
// Specifies that the embeddings will be used for fact verification.
991+
FACT_VERIFICATION = 8;
992+
993+
// Specifies that the embeddings will be used for code retrieval.
994+
CODE_RETRIEVAL_QUERY = 9;
995+
}
996+
997+
// Required. The name of the publisher model requested to serve the
998+
// prediction. Format:
999+
// `projects/{project}/locations/{location}/publishers/*/models/*`
1000+
optional string model = 1 [(google.api.resource_reference) = {
1001+
type: "aiplatform.googleapis.com/Endpoint"
1002+
}];
1003+
1004+
// Required. Input content to be embedded. Required.
1005+
optional Content content = 2;
1006+
1007+
// Optional. An optional title for the text.
1008+
optional string title = 4 [(google.api.field_behavior) = OPTIONAL];
1009+
1010+
// Optional. The task type of the embedding.
1011+
optional EmbeddingTaskType task_type = 5
1012+
[(google.api.field_behavior) = OPTIONAL];
1013+
1014+
// Optional. Optional reduced dimension for the output embedding. If set,
1015+
// excessive values in the output embedding are truncated from the end.
1016+
optional int32 output_dimensionality = 6
1017+
[(google.api.field_behavior) = OPTIONAL];
1018+
1019+
// Optional. Whether to silently truncate the input content if it's longer
1020+
// than the maximum sequence length.
1021+
optional bool auto_truncate = 7 [(google.api.field_behavior) = OPTIONAL];
1022+
}
1023+
1024+
// Response message for
1025+
// [PredictionService.EmbedContent][google.cloud.aiplatform.v1beta1.PredictionService.EmbedContent].
1026+
message EmbedContentResponse {
1027+
// A list of floats representing an embedding.
1028+
message Embedding {
1029+
// Embedding vector values.
1030+
repeated float values = 1;
1031+
}
1032+
1033+
// The embedding generated from the input content.
1034+
Embedding embedding = 1;
1035+
1036+
// Metadata about the response(s).
1037+
UsageMetadata usage_metadata = 2;
1038+
1039+
// Whether the input content was truncated before generating the embedding.
1040+
bool truncated = 4;
1041+
}

‎packages/google-cloud-aiplatform/protos/google/cloud/aiplatform/v1beta1/usage_metadata.proto‎

Lines changed: 96 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,96 @@
1+
// Copyright 2025 Google LLC
2+
//
3+
// Licensed under the Apache License, Version 2.0 (the "License");
4+
// you may not use this file except in compliance with the License.
5+
// You may obtain a copy of the License at
6+
//
7+
// http://www.apache.org/licenses/LICENSE-2.0
8+
//
9+
// Unless required by applicable law or agreed to in writing, software
10+
// distributed under the License is distributed on an "AS IS" BASIS,
11+
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
// See the License for the specific language governing permissions and
13+
// limitations under the License.
14+
15+
syntax = "proto3";
16+
17+
package google.cloud.aiplatform.v1beta1;
18+
19+
import "google/api/field_behavior.proto";
20+
import "google/cloud/aiplatform/v1beta1/content.proto";
21+
22+
option csharp_namespace = "Google.Cloud.AIPlatform.V1Beta1";
23+
option go_package = "cloud.google.com/go/aiplatform/apiv1beta1/aiplatformpb;aiplatformpb";
24+
option java_multiple_files = true;
25+
option java_outer_classname = "UsageMetadataProto";
26+
option java_package = "com.google.cloud.aiplatform.v1beta1";
27+
option php_namespace = "Google\\Cloud\\AIPlatform\\V1beta1";
28+
option ruby_package = "Google::Cloud::AIPlatform::V1beta1";
29+
30+
// Usage metadata about the content generation request and response.
31+
// This message provides a detailed breakdown of token usage and other
32+
// relevant metrics.
33+
message UsageMetadata {
34+
// The type of traffic that this request was processed with, indicating which
35+
// quota gets consumed.
36+
enum TrafficType {
37+
// Unspecified request traffic type.
38+
TRAFFIC_TYPE_UNSPECIFIED = 0;
39+
40+
// Type for Pay-As-You-Go traffic.
41+
ON_DEMAND = 1;
42+
43+
// Type for Provisioned Throughput traffic.
44+
PROVISIONED_THROUGHPUT = 2;
45+
}
46+
47+
// The total number of tokens in the prompt. This includes any text, images,
48+
// or other media provided in the request. When `cached_content` is set,
49+
// this also includes the number of tokens in the cached content.
50+
int32 prompt_token_count = 1;
51+
52+
// The total number of tokens in the generated candidates.
53+
int32 candidates_token_count = 2;
54+
55+
// The total number of tokens for the entire request. This is the sum of
56+
// `prompt_token_count`, `candidates_token_count`,
57+
// `tool_use_prompt_token_count`, and `thoughts_token_count`.
58+
int32 total_token_count = 3;
59+
60+
// Output only. The number of tokens in the results from tool executions,
61+
// which are provided back to the model as input, if applicable.
62+
int32 tool_use_prompt_token_count = 13
63+
[(google.api.field_behavior) = OUTPUT_ONLY];
64+
65+
// Output only. The number of tokens that were part of the model's generated
66+
// "thoughts" output, if applicable.
67+
int32 thoughts_token_count = 14 [(google.api.field_behavior) = OUTPUT_ONLY];
68+
69+
// Output only. The number of tokens in the cached content that was used for
70+
// this request.
71+
int32 cached_content_token_count = 5
72+
[(google.api.field_behavior) = OUTPUT_ONLY];
73+
74+
// Output only. A detailed breakdown of the token count for each modality in
75+
// the prompt.
76+
repeated ModalityTokenCount prompt_tokens_details = 9
77+
[(google.api.field_behavior) = OUTPUT_ONLY];
78+
79+
// Output only. A detailed breakdown of the token count for each modality in
80+
// the cached content.
81+
repeated ModalityTokenCount cache_tokens_details = 10
82+
[(google.api.field_behavior) = OUTPUT_ONLY];
83+
84+
// Output only. A detailed breakdown of the token count for each modality in
85+
// the generated candidates.
86+
repeated ModalityTokenCount candidates_tokens_details = 11
87+
[(google.api.field_behavior) = OUTPUT_ONLY];
88+
89+
// Output only. A detailed breakdown by modality of the token counts from the
90+
// results of tool executions, which are provided back to the model as input.
91+
repeated ModalityTokenCount tool_use_prompt_tokens_details = 12
92+
[(google.api.field_behavior) = OUTPUT_ONLY];
93+
94+
// Output only. The traffic type for this request.
95+
TrafficType traffic_type = 8 [(google.api.field_behavior) = OUTPUT_ONLY];
96+
}

0 commit comments

Comments
 (0)