To perform batch inference with Bedrock, you need to upload files to S3. This process can be cumbersome and duplicative in nature because you need to transform your data into model specific formats. With Portkey, you can upload the file in OpenAI format and portkey will handle transforming the file into the format required by Bedrock on the fly! This is the most efficient way to
  • Test your data with different foundation models
  • Perform A/B testing with different foundation models
  • Perform batch inference with different foundation models

​
Uploading Files

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@PROVIDER",   
    provider="bedrock",
    aws_region="YOUR_AWS_REGION",
    aws_s3_bucket="YOUR_AWS_S3_BUCKET",
    aws_s3_object_key="YOUR_AWS_S3_OBJECT_KEY",
    aws_bedrock_model="YOUR_AWS_BEDROCK_MODEL",
    amz_server_side_encryption: "ENCRYPTION_TYPE", # [optional] default is aws:kms
    amz_server_side_encryption_aws_kms_key_id: "KMS_KEY_ID" # [optional] use this only if you want to use a KMS key to encrypt the file at rest
)

upload_file_response = portkey.files.create(
  purpose="batch",
  file=open("file.pdf", "rb")
)

print(upload_file_response)

​
Get File

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@PROVIDER",   
    aws_region="YOUR_AWS_REGION",
)

file = portkey.files.retrieve(file_id="file_id")

print(file)

​
Get File Content

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@PROVIDER",   
    aws_region="YOUR_AWS_REGION",
)

file_content = portkey.files.content(file_id="file_id")

print(file_content)
The following endpoints are NOT supported for Bedrock for security reasons:
  • GET /v1/files
  • DELETE /v1/files/{file_id}