All Content tagged with Amazon Textract
Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents.
Content language: English
Filter content
Select tags to filter
Sort by
Sort by most recent
378 results
I've crated a Textact Dataset, and, it walks me thru the queries I've created with responses for each document, but, is this the only purpose of creating a dataset, to train on queries? What about th...
2
answers
0
votes
47
views
asked 2 months ago
We are using multiple Amazon Textract Custom Adapters for document processing and need to copy them between AWS accounts as part of our environment promotion process (Dev > QA > Staging > Production)....
1
answers
0
votes
34
views
asked 3 months ago
I recently created a new AWS account and am experiencing an issue where certain services (such as Amazon Textract and AWS App Runner) cannot be accessed.
When I attempt to open these services in the ...
1
answers
-2
votes
128
views
asked 3 months ago
We are planning a centralized AI Hub account that hosts multiple Textract Custom Adapter versions, one per environment:
- Adapter version for Dev → tagged environment=dev, project=doc-reader
- Adapte...
2
answers
0
votes
47
views
asked 3 months ago
We are using Amazon Textract Custom Adapters for document processing in a financial institution. We have a centralized AI Hub AWS account that hosts all Textract adapters. The AI services only exist i...
1
answers
0
votes
73
views
asked 3 months ago
We have a centralized AI Hub AWS account that hosts all our Amazon Textract Custom Adapters. The AI services only live in this Hub account they are not replicated in other environments.
Our other env...
1
answers
0
votes
62
views
asked 3 months ago
We are implementing Amazon Textract Custom Adapters and Amazon Bedrock Data Automation (BDA) with optimized blueprints for document processing across different environments: Dev, Staging, and Producti...
1
answers
1
votes
66
views
asked 3 months ago
I'm using Python's `ThreadPoolExecutor` to process pages concurrently with Textract. My code looks like this:
```python
def _process_page(args: tuple, client, loader_type_name: str) -> tuple[int, str...
1
answers
0
votes
47
views
asked 3 months ago
Hello all,
I want to build a demo web application using only AWS services where I can upload a set of PDFs and using Amazon Textract, I can extract the content in the pdfs and show them in the UI its...
1
answers
0
votes
132
views
asked 6 months ago
Hi everyone,
I’m working on extracting readable text (Chinese/English) from PDFs that contain both digital and image-based text. I used AWS Bedrock with models including Claude 3.5 Sonnet, Haiku, Ama...
3
answers
0
votes
208
views
asked 7 months ago
Hi, my account is verified and active, but AWS Textract is asking me to complete registration. Please check and enable access for AI/ML services.
2
answers
0
votes
117
views
asked 7 months ago
Hello,
I’ve attached an image and the corresponding table extracted by AWS Textract. As you can see, the table rows are somewhat collateral — meaning that multiple pieces of information are grouped i...
1
answers
0
votes
155
views
asked 7 months ago