[Python] processing pdf documents using bedrock runtime

I am trying to use AWS Bedrock Runtime for document understanding:

(model:amazon.nova-premier-v1:0)

Here is my current code:

def process():
with open("file.pdf", "rb") as f:
document_bytes = f.read()
bedrock_client = boto3.client("bedrock-runtime", "us-east-1")
response = bedrock_client.converse(
modelId=MODEL_ID,
messages=[
{
"role": "user",
"content": [
{
"text": "explain this document",
"document": {
"format": "pdf",
"name": "file",
"source": {
"bytes": document_bytes,
},
},
},
],
},
],
)

print(response)

return response


Here is the error I am encountering:

botocore.exceptions.ParamValidationError: Parameter validation failed:
Invalid number of parameters set for tagged union structure messages[0].content[0]. Can only set one of the following keys: text, image, document, video, toolUse, toolResult, guardContent, cachePoint, reasoningContent.


The code works fine if I remove the messages[0].content[0].document

but according to the error message 'document' is part of the tagged union.

I looked at the Docs, the example shows that 'document' can be used this way.

The example on the docs is similar to what I wrote. Can someone explain why is it still throwing this error.

Continue reading...