Help us improve the AWS re:Post Knowledge Center by sharing your feedback in a brief survey. Your input can influence how we create and update our content to better support your AWS journey.
Questions 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 questions
Select tags to filter
Sort by
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
377 results
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
26
views
asked a month 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
106
views
asked a month 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...
1
answers
0
votes
40
views
asked a month 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
45
views
asked a month 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
51
views
asked a month 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
49
views
asked a month 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
36
views
asked a month 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
107
views
asked 4 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
162
views
asked 5 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
92
views
asked 5 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
135
views
asked 5 months ago
I'm extracting tables from financial statement PDFs (like 10-Ks) Textract has a feature which allows for extracting them in markdown format.
However, some of the tables don't have headers. For exampl...
1
answers
0
votes
85
views
asked 5 months ago