FilesExpand file tree

 main

/

batch_example.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

60 lines (49 loc) · 2.12 KB

 main

/

batch_example.py

Copy path

Top

File metadata and controls

• Code
• Blame

60 lines (49 loc) · 2.12 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

# Copyright 2024 Google LLC

#

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

#

# https://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

import os

from google.cloud.aiplatform import BatchPredictionJob

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")

def embed_text_batch(OUTPUT_URI: str) -> BatchPredictionJob:

"""Example of how to generate embeddings from text using batch processing.

Read more: https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/batch-prediction-genai-embeddings

"""

# [START generativeaionvertexai_embedding_batch]

import vertexai

from vertexai.preview import language_models

# TODO(developer): Update & uncomment line below

# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

input_uri = (

"gs://cloud-samples-data/generative-ai/embeddings/embeddings_input.jsonl"

)

# Format: `"gs://your-bucket-unique-name/directory/` or `bq://project_name.llm_dataset`

output_uri = OUTPUT_URI

textembedding_model = language_models.TextEmbeddingModel.from_pretrained(

"textembedding-gecko@003"

)

batch_prediction_job = textembedding_model.batch_predict(

dataset=[input_uri],

destination_uri_prefix=output_uri,

)

print(batch_prediction_job.display_name)

print(batch_prediction_job.resource_name)

print(batch_prediction_job.state)

# Example response:

# BatchPredictionJob 2024-09-10 15:47:51.336391

# projects/1234567890/locations/us-central1/batchPredictionJobs/123456789012345

# JobState.JOB_STATE_SUCCEEDED

# [END generativeaionvertexai_embedding_batch]

return batch_prediction_job

if __name__ == "__main__":

embed_text_batch()