Generate embeddings for Images, Videos and Text

import(
"context"
"encoding/json"
"fmt"
"io"
"time"
aiplatform"cloud.google.com/go/aiplatform/apiv1beta1"
aiplatformpb"cloud.google.com/go/aiplatform/apiv1beta1/aiplatformpb"
"google.golang.org/api/option"
"google.golang.org/protobuf/encoding/protojson"
"google.golang.org/protobuf/types/known/structpb"
)
// generateForImageTextAndVideo shows how to use the multimodal model to generate embeddings for
// image, text and video data.
funcgenerateForImageTextAndVideo(wio.Writer,project,locationstring)error{
// location = "us-central1"
// The default context timeout may be not enough to process a video input.
ctx,cancel:=context.WithTimeout(context.Background(),15*time.Second)
defercancel()
apiEndpoint:=fmt.Sprintf("%s-aiplatform.googleapis.com:443",location)
client,err:=aiplatform.NewPredictionClient (ctx,option.WithEndpoint(apiEndpoint))
iferr!=nil{
returnfmt.Errorf("failed to construct API client: %w",err)
}
deferclient.Close()
model:="multimodalembedding@001"
endpoint:=fmt.Sprintf("projects/%s/locations/%s/publishers/google/models/%s",project,location,model)
// This is the input to the model's prediction call. For schema, see:
// https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/multimodal-embeddings-api#request_body
instance,err:=structpb.NewValue(map[string]any{
"text":"Domestic cats in natural conditions",
"image":map[string]any{
// Image and video inputs can be provided either as a Google Cloud Storage URI or as
// base64-encoded bytes using the "bytesBase64Encoded" field.
"gcsUri":"gs://cloud-samples-data/generative-ai/image/320px-Felis_catus-cat_on_snow.jpg",
},
"video":map[string]any{
"gcsUri":"gs://cloud-samples-data/video/cat.mp4",
},
})
iferr!=nil{
returnfmt.Errorf("failed to construct request payload: %w",err)
}
req:=&aiplatformpb.PredictRequest{
Endpoint:endpoint,
// The model supports only 1 instance per request.
Instances:[]*structpb.Value{instance},
}
resp,err:=client.Predict(ctx,req)
iferr!=nil{
returnfmt.Errorf("failed to generate embeddings: %w",err)
}
instanceEmbeddingsJson,err:=protojson.Marshal(resp.GetPredictions()[0])
iferr!=nil{
returnfmt.Errorf("failed to convert protobuf value to JSON: %w",err)
}
// For response schema, see:
// https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/multimodal-embeddings-api#response-body
varinstanceEmbeddingsstruct{
ImageEmbeddings[]float32`json:"imageEmbedding"`
TextEmbeddings[]float32`json:"textEmbedding"`
VideoEmbeddings[]struct{
Embedding[]float32`json:"embedding"`
StartOffsetSecfloat64`json:"startOffsetSec"`
EndOffsetSecfloat64`json:"endOffsetSec"`
}`json:"videoEmbeddings"`
}
iferr:=json.Unmarshal(instanceEmbeddingsJson,&instanceEmbeddings);err!=nil{
returnfmt.Errorf("failed to unmarshal JSON: %w",err)
}
imageEmbedding:=instanceEmbeddings.ImageEmbeddings
textEmbedding:=instanceEmbeddings.TextEmbeddings
// Get the embedding for our single video segment (`.videoEmbeddings` object has one entry per
// each processed segment).
videoEmbedding:=instanceEmbeddings.VideoEmbeddings[0].Embedding
fmt.Fprintf(w,"Image embedding (length=%d): %v\n",len(imageEmbedding),imageEmbedding)
fmt.Fprintf(w,"Text embedding (length=%d): %v\n",len(textEmbedding),textEmbedding)
fmt.Fprintf(w,"Video embedding (length=%d): %v\n",len(videoEmbedding),videoEmbedding)
// Example response:
// Image embedding (length=1408): [-0.01558477 0.0258355 0.016342038 ... ]
// Text embedding (length=1408): [-0.005894961 0.008349559 0.015355394 ... ]
// Video embedding (length=1408): [-0.018867437 0.013997682 0.0012682161 ... ]
returnnil
}

importvertexai
fromvertexai.vision_modelsimport Image , MultiModalEmbeddingModel , Video
fromvertexai.vision_modelsimport VideoSegmentConfig
# TODO(developer): Update & uncomment line below
# PROJECT_ID = "your-project-id"
vertexai .init(project=PROJECT_ID, location="us-central1")
model = MultiModalEmbeddingModel .from_pretrained ("multimodalembedding@001")
image = Image .load_from_file (
 "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"
)
video = Video .load_from_file (
 "gs://cloud-samples-data/vertex-ai-vision/highway_vehicles.mp4"
)
embeddings = model.get_embeddings (
 image=image,
 video=video,
 video_segment_config=VideoSegmentConfig(end_offset_sec=1),
 contextual_text="Cars on Highway",
)
print(f"Image Embedding: {embeddings.image_embedding}")
# Video Embeddings are segmented based on the video_segment_config.
print("Video Embeddings:")
for video_embedding in embeddings.video_embeddings:
 print(
 f"Video Segment: {video_embedding.start_offset_sec} - {video_embedding.end_offset_sec}"
 )
 print(f"Embedding: {video_embedding.embedding}")
print(f"Text Embedding: {embeddings.text_embedding}")
# Example response:
# Image Embedding: [-0.0123144267, 0.0727186054, 0.000201397663, ...]
# Video Embeddings:
# Video Segment: 0.0 - 1.0
# Embedding: [-0.0206376351, 0.0345234685, ...]
# Text Embedding: [-0.0207006838, -0.00251058186, ...]