# Amazon Textract

AWS machine learning service for extracting text, handwriting, layout elements, and structured data from documents.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Announcing Amazon Textract Insights: Verifiable generative AI for documents

DevFeed: [Announcing Amazon Textract Insights: Verifiable generative AI for documents](<https://devfeed.tech/articles/announcing-amazon-textract-insights-verifiable-generative-ai-for-documents-146682.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/announcing-amazon-textract-insights-verifiable-generative-ai-for-documents/>)

Author: Keith Mascarenhas

Published: 2026-11-20T20:22:00Z

Content type: release

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [amazon-textract](<https://devfeed.tech/tags/amazon-textract.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [confidence-score](<https://devfeed.tech/tags/confidence-score.md>), [general-availability](<https://devfeed.tech/tags/general-availability.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

Amazon Textract Insights provides document field extraction through one asynchronous API request: define fields in a JSON Schema blueprint with natural language descriptions, then submit a document or mixed packet from S3. With splitting enabled, it separates packets of up to 3,000 pages, matches subdocuments to blueprints, and returns explicit or inferred values with confidence scores and page and bounding-box grounding. Public blueprints cover common forms; custom blueprints support business-specific documents. This offers a managed alternative to assembling an OCR, splitting, classification, model, and review pipeline, while grounding and confidence support audit and review decisions. The source recommends tuning confidence thresholds on representative documents. Inputs are PDF, PNG, JPEG, or TIFF; supported languages are English, French, German, Italian, Portuguese, and Spanish. Pricing is per page with no minimum commitment. Insights is not yet available in the newly added Tokyo and Zurich Regions; inference requests are routed to compute within the originating geography.

### Source excerpt

Announcing the general availability of Amazon Textract Insights, a new generative AI feature of Amazon Textract. Describe the fields you need in natural language, submit a document or a mixed packet, and receive structured results with a confidence score and page-level grounding for each value, with no model training required.

## Unsiloed nabs $7.5M to turn scanned documents into structured data for AI agents

DevFeed: [Unsiloed nabs $7.5M to turn scanned documents into structured data for AI agents](<https://devfeed.tech/articles/unsiloed-nabs-7-5m-to-turn-scanned-documents-into-structured-data-for-ai-agents-140862.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/18/unsiloed-nabs-7-5m-to-turn-scanned-documents-into-structured-data-for-ai-agents/>)

Author: Kyt Dotson

Published: 2026-11-18T16:00:40Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [document ai](<https://devfeed.tech/topics/document-ai.md>), [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [Serialization protocols](<https://devfeed.tech/topics/serialization-protocols.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-startup-funding](<https://devfeed.tech/tags/ai-startup-funding.md>), [aman-mishra](<https://devfeed.tech/tags/aman-mishra.md>), [apps](<https://devfeed.tech/tags/apps.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [funding](<https://devfeed.tech/tags/funding.md>), [news](<https://devfeed.tech/tags/news.md>), [pdfs](<https://devfeed.tech/tags/pdfs.md>), [scanning](<https://devfeed.tech/tags/scanning.md>), [startup-funding](<https://devfeed.tech/tags/startup-funding.md>), [structured-data](<https://devfeed.tech/tags/structured-data.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [unsiloed](<https://devfeed.tech/tags/unsiloed.md>)

### AI overview

Unsiloed says its visual-first parser converts PDFs, forms, presentations, Word files and images into Markdown or JSON while preserving layout, tables, sections and relationships between content. Unlike OCR, which the article describes as extracting text without recognizing layout or graphics, Unsiloed combines computer vision algorithms with dual-stream vision models that process text and visual structure together. Developers can provide schemas to extract fields, classify or split documents, and update text and images while retaining formatting. The company reports an 88.0 score on olmOCR-Bench, compared with 81.9 for Claude Opus 4.7, 84.6 for GPT 5.5 and 77.7 for Gemini 3 Pro, and says it ranked first among 19 systems. It supports private cloud, on-premises and air-gapped deployment. The excerpt reports a $7.5 million seed round led by Felicis.

### Source excerpt

Document-scanning firm Unsiloed Inc. today announced it has raised $7.5 million in seed funding to turn PDFs and other complex documents into structured, readable data for artificial intelligence agents. Participants in the round, led by Felicis, included Y Combinator, Orange Collective, Uncorrelated Ventures, Aarthi Ramamurthy and Beth Turner. A variety of documents arrive in formats [...] The post Unsiloed nabs $7.5M to turn scanned documents into structured data for AI agents appeared first on SiliconANGLE.

## Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

DevFeed: [Dharma Field Extractor: Any Document In, Structured Fields in JSON Out](<https://devfeed.tech/articles/dharma-field-extractor-any-document-in-structured-fields-in-json-out-118022.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/Dharma-AI/dharma-field-extractor>)

Author: Gabriel Pimenta de Freitas Cardoso; Paulo Henrique de Medeiros Araujo; Bruno Duarte; Francisco de Almeida Rocha Alves

Published: 2026-11-04T17:50:10Z

Content type: release

Language: en

Sources: [Hugging Face](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [document ai](<https://devfeed.tech/topics/document-ai.md>), [JSON](<https://devfeed.tech/topics/json.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [benchmark overfitting machine learning](<https://devfeed.tech/topics/benchmark-overfitting-machine-learning.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2019](<https://devfeed.tech/tags/2019.md>), [2020](<https://devfeed.tech/tags/2020.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [cost](<https://devfeed.tech/tags/cost.md>), [court](<https://devfeed.tech/tags/court.md>), [field](<https://devfeed.tech/tags/field.md>), [fields](<https://devfeed.tech/tags/fields.md>), [forms](<https://devfeed.tech/tags/forms.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [ids](<https://devfeed.tech/tags/ids.md>), [json](<https://devfeed.tech/tags/json.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [range](<https://devfeed.tech/tags/range.md>), [structured](<https://devfeed.tech/tags/structured.md>), [type](<https://devfeed.tech/tags/type.md>), [wide](<https://devfeed.tech/tags/wide.md>)

### AI overview

Dharma Field Extractor converts document images into typed JSON, either by finding fields without a schema or filling an exact user-provided schema; missing requested values are returned as null. The article says one model handles multiple document types without per-type fine-tuning. In the authors' 546-document, three-scenario benchmark, it scored 0.834, above four tested frontier configurations (0.741-0.816). They report costs 6-147 times lower, but compare API list-price estimates with self-hosted GPU time on one L40S, not a sales price; deployment cost depends on hardware, volume, and latency. SROIE and FUNSD were held out from training. These are the article's reported results and do not establish performance beyond its benchmark.

### Source excerpt

*A 2-billion-parameter model that extracts exactly the fields you ask for, from any document type, outperforming every frontier LLM we tested, at a fraction of the cost.* In April, we released DharmaOCR-LITE, a model specialized for OCR across a wide range of documents, from contracts and court filings to invoices, IDs and forms.

## Your RAG Pipeline Dies on Real Documents: Here's Why

DevFeed: [Your RAG Pipeline Dies on Real Documents: Here's Why](<https://devfeed.tech/articles/your-rag-pipeline-dies-on-real-documents-here-s-why-64495.md>)

Original publisher: [Read original article](<https://hackernoon.com/your-rag-pipeline-dies-on-real-documents-heres-why?source=rss>)

Author: Paolo Perrone

Published: 2026-10-03T17:00:06Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-rag](<https://devfeed.tech/tags/agentic-rag.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [better](<https://devfeed.tech/tags/better.md>), [block](<https://devfeed.tech/tags/block.md>), [coding](<https://devfeed.tech/tags/coding.md>), [context](<https://devfeed.tech/tags/context.md>), [cost](<https://devfeed.tech/tags/cost.md>), [csv](<https://devfeed.tech/tags/csv.md>), [data](<https://devfeed.tech/tags/data.md>), [demo](<https://devfeed.tech/tags/demo.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [detection](<https://devfeed.tech/tags/detection.md>), [edit-distance](<https://devfeed.tech/tags/edit-distance.md>), [pdf](<https://devfeed.tech/tags/pdf.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rag-architecture](<https://devfeed.tech/tags/rag-architecture.md>), [rag-chunking-strategies](<https://devfeed.tech/tags/rag-chunking-strategies.md>), [rag-evaluation](<https://devfeed.tech/tags/rag-evaluation.md>), [rag-optimization](<https://devfeed.tech/tags/rag-optimization.md>), [rag-pipelines](<https://devfeed.tech/tags/rag-pipelines.md>), [rag-systems](<https://devfeed.tech/tags/rag-systems.md>), [what-is-rag](<https://devfeed.tech/tags/what-is-rag.md>)

### AI overview

PDFs often preserve text positions without the structure needed for reliable retrieval. Flattened tables, scrambled reading order, scans, and missing visual context can produce plausible but incorrect RAG answers without raising errors. The article explains how document-understanding parsers combine layout detection, reading-order recovery, table reconstruction, OCR, and language models, while noting their cost, accuracy limits, and downstream tradeoffs. It recommends comparing raw parser output on difficult documents from your own corpus.

### Source excerpt

RAG fails on PDFs because a PDF stores glyph positions, not document structure. Tables flatten, reading order scrambles, and no error is ever raised.

## Automating Amazon Textract adapter lifecycle management across accounts

DevFeed: [Automating Amazon Textract adapter lifecycle management across accounts](<https://devfeed.tech/articles/automating-amazon-textract-adapter-lifecycle-management-across-accounts-61386.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/automating-amazon-textract-adapter-lifecycle-management-across-accounts/>)

Author: Bhavya Sruthi Sode

Published: 2026-09-28T15:49:04Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [adapter pattern](<https://devfeed.tech/topics/adapter-pattern.md>), [Terraform](<https://devfeed.tech/topics/terraform.md>)

Tags: [amazon-textract](<https://devfeed.tech/tags/amazon-textract.md>), [aws-cloudformation](<https://devfeed.tech/tags/aws-cloudformation.md>), [cloudformation](<https://devfeed.tech/tags/cloudformation.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [iam](<https://devfeed.tech/tags/iam.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [least-privilege](<https://devfeed.tech/tags/least-privilege.md>), [security](<https://devfeed.tech/tags/security.md>), [terraform](<https://devfeed.tech/tags/terraform.md>), [vpc](<https://devfeed.tech/tags/vpc.md>)

### AI overview

This tutorial describes production lifecycle management for Amazon Textract adapters across AWS accounts. It covers infrastructure templates, cross-account promotion, adapter ID management through Systems Manager Parameter Store, pre-classification routing, and security configurations. The described process aims to update production adapter references without application redeployment.

### Source excerpt

Learn how to operationalize Amazon Textract Custom Queries adapters for production: infrastructure as code with AWS CloudFormation and Terraform, a cross-account adapter promotion process, a pre-classification routing pattern for multiple form versions, and production security controls such as VPC endpoints, encryption, and least-privilege IAM.

## jina-ocr-v1: One OCR model for layout, tables, math and 100+ languages

DevFeed: [jina-ocr-v1: One OCR model for layout, tables, math and 100+ languages](<https://devfeed.tech/articles/jina-ocr-v1-one-ocr-model-for-layout-tables-math-and-100-languages-78870.md>)

Original publisher: [Read original article](<https://www.elastic.co/search-labs/blog/ocr-model-jina-ocr-v1-document-parsing>)

Author: Scott Martens

Published: 2026-09-17T00:00:00Z

Content type: article

Language: en

Sources: [Elasticsearch Labs](<https://devfeed.tech/sources/elasticsearch-labs.md>)

Topics: [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [api](<https://devfeed.tech/tags/api.md>), [jina-ai](<https://devfeed.tech/tags/jina-ai.md>), [layout](<https://devfeed.tech/tags/layout.md>), [model](<https://devfeed.tech/tags/model.md>), [ocr](<https://devfeed.tech/tags/ocr.md>)

### AI overview

The article describes jina-ocr-v1, an end-to-end document parser that converts scans, photographs, slides, and handwriting in more than 100 languages into structured text. It covers its layout-aware output, table and math extraction, handwriting recognition, performance comparisons, model architecture, input constraints, and API and local access options.

### Source excerpt

jina-ocr-v1 scores 83.4 on olmOCR-bench with 570 million active parameters, the highest of any OCR model under 600 million, and it outscores GPT-5.2 on OmniDocBench.

## Build AI-powered file classification with AWS Transfer Family

DevFeed: [Build AI-powered file classification with AWS Transfer Family](<https://devfeed.tech/articles/build-ai-powered-file-classification-with-aws-transfer-family-49888.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/storage/build-ai-powered-file-classification-with-aws-transfer-family/>)

Author: Erasmo Fabio Acrani

Published: 2026-09-11T19:56:57Z

Content type: tutorial

Language: en

Sources: [AWS Storage Blog](<https://devfeed.tech/sources/aws-storage-blog.md>)

Topics: [file](<https://devfeed.tech/topics/file.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>), [Amazon Simple Queue Service (SQS)](<https://devfeed.tech/topics/amazon-simple-queue-service-sqs.md>), [event driven](<https://devfeed.tech/topics/event-driven.md>), [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-eventbridge](<https://devfeed.tech/tags/amazon-eventbridge.md>), [amazon-simple-notification-service-sns](<https://devfeed.tech/tags/amazon-simple-notification-service-sns.md>), [amazon-simple-queue-service-sqs](<https://devfeed.tech/tags/amazon-simple-queue-service-sqs.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [amazon-sqs](<https://devfeed.tech/tags/amazon-sqs.md>), [amazon-textract](<https://devfeed.tech/tags/amazon-textract.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [aws-transfer-family](<https://devfeed.tech/tags/aws-transfer-family.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [file](<https://devfeed.tech/tags/file.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [regular-expressions](<https://devfeed.tech/tags/regular-expressions.md>), [sftp](<https://devfeed.tech/tags/sftp.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

This tutorial explains how to replace fragile filename-based routing with content-aware file classification. It combines AWS Transfer Family, Amazon Bedrock with Amazon Nova Lite, Amazon Textract, Amazon EventBridge, and Amazon SQS to ingest files over SFTP, classify their contents, and route them to downstream systems.

### Source excerpt

Organizations that receive files from external partners through SFTP face a persistent operational challenge: routing each file to the correct downstream system. Invoices, contracts, images, CSVs, and reports all arrive in a single landing zone, and each requires a different destination. The traditional approach--pattern-matching on file names with regular expressions--is inherently fragile. It relies on [...]

## How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock

DevFeed: [How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock](<https://devfeed.tech/articles/how-clario-technology-detects-phi-pii-in-dicom-images-using-amazon-bedrock-4645.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/how-clario-automates-phi-pii-detection-in-dicom-images-using-amazon-bedrock/>)

Author: Alex Boudreau

Published: 2026-08-19T14:29:31Z

Content type: article

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Medical imaging](<https://devfeed.tech/topics/medical-imaging.md>), [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-textract](<https://devfeed.tech/tags/amazon-textract.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [data](<https://devfeed.tech/tags/data.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [images](<https://devfeed.tech/tags/images.md>), [medical-imaging](<https://devfeed.tech/tags/medical-imaging.md>), [pii](<https://devfeed.tech/tags/pii.md>), [technology](<https://devfeed.tech/tags/technology.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Clario uses Amazon Bedrock and Amazon Textract to automate the detection of PHI and PII in DICOM image slices from clinical trials, including information stored in metadata and text embedded in image pixels.

### Source excerpt

Clario, part of Thermo Fisher Scientific, uses Amazon Bedrock and Amazon Textract to automatically detect protected health information (PHI) and personally identifiable information (PII) across thousands of DICOM image slices in clinical trials, covering both metadata tags and text burned into the image pixels.

## Technical Tuesday: Should you process your enterprise documents with LLMs?

DevFeed: [Technical Tuesday: Should you process your enterprise documents with LLMs?](<https://devfeed.tech/articles/technical-tuesday-should-you-process-your-enterprise-documents-with-llms-79375.md>)

Original publisher: [Read original article](<https://www.uipath.com/blog/product-and-updates/technical-tuesday-process-enterprise-docs-with-llms>)

Author: George Barnett - Blog

Published: 2025-07-29T00:00:00Z

Content type: article

Language: en

Sources: [UiPath RSS Feed](<https://devfeed.tech/sources/uipath-rss-feed.md>)

Topics: [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [text-classification](<https://devfeed.tech/topics/text-classification.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [vectorization techniques](<https://devfeed.tech/topics/vectorization-techniques.md>)

Tags: [document-processing](<https://devfeed.tech/tags/document-processing.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [features](<https://devfeed.tech/tags/features.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [llms](<https://devfeed.tech/tags/llms.md>), [product-and-updates](<https://devfeed.tech/tags/product-and-updates.md>), [uipath](<https://devfeed.tech/tags/uipath.md>)

### AI overview

UiPath describes research showing why large language models alone may not reliably handle enterprise document processing at scale. The article discusses issues with table extraction, schema consistency, attribution, confidence scores and validation, and outlines UiPath IXP's approach of combining specialized models with pre- and post-processing. It also summarizes mixed results from few-shot prompting, including stronger results for short documents and targeted table fixes, but weaker results on longer documents.

### Source excerpt

Discover why LLMs alone aren't enough for enterprise document processing. Learn about UiPath research findings and multi-model approach for better accuracy.

## PDF Text Extraction Is Hard Even for AWS Textract

DevFeed: [PDF Text Extraction Is Hard Even for AWS Textract](<https://devfeed.tech/articles/pdf-text-extraction-is-hard-even-for-aws-textract-28124.md>)

Original publisher: [Read original article](<http://fuzzyblog.io/blog/aws/2020/03/05/pdf-text-extraction-is-hard-even-for-aws-textract.html>)

Author: Fuzzygroup

Published: 2020-03-05T00:00:00Z

Content type: article

Language: en

Sources: [Scott Johnson](<https://devfeed.tech/sources/scott-johnson.md>)

Topics: [Amazon Textract](<https://devfeed.tech/topics/amazon-textract.md>)

Tags: [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-textract](<https://devfeed.tech/tags/amazon-textract.md>), [api](<https://devfeed.tech/tags/api.md>), [aws](<https://devfeed.tech/tags/aws.md>), [csv](<https://devfeed.tech/tags/csv.md>), [email](<https://devfeed.tech/tags/email.md>), [json](<https://devfeed.tech/tags/json.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [medium](<https://devfeed.tech/tags/medium.md>), [pdf](<https://devfeed.tech/tags/pdf.md>), [pdf-processing](<https://devfeed.tech/tags/pdf-processing.md>), [python](<https://devfeed.tech/tags/python.md>), [resume](<https://devfeed.tech/tags/resume.md>), [text](<https://devfeed.tech/tags/text.md>)

### AI overview

In a small resume sample, a prior PDF extraction approach found about 70% of email addresses; AWS Textract reduced the failure rate from roughly 30% to 10% but still missed some addresses. The author describes Textract returning geometry-linked text blocks in apiResponse.json, semantic fields in keyValues.csv, and full document text in rawText.txt. The semantic fields were often unhelpful for resume contact details, while the structured JSON seemed suitable for searching text with regular expressions or examining the first lines for contact information. Despite imperfect extraction, the author found Textract easier to run than Python with NLTK, with less garbled text and results that were easy to manipulate.

### Source excerpt

I have always found that serendipity plays a large role in my technical life. For example I recently ran into a great article and discussion thread on PDF Text Extraction: Article Discussion Thread The thrust of this article amounts to "PDF Processing Is Hard and Here's Why" (tldr - PDF isn't a document format as much as a layout format and how things are laid out generally bears little relationship to their structure as "document elements"). Now lately I've been involved in some resume processing lately and this made me say: Hm... Can I extract just the email addresses programmatically from this stack of resumes? I found that following the techniques in this Medium article, I was able to extract roughly 70% of the email addresses from a small sample. And while 70% isn't bad, I suspected that better should be possible. And that led me to the AWS Textract service. Unfortunately what I found was that even the "machine learning" powered Textract service: Amazon Textract overcomes these challenges by using machine learning to instantly "read" virtually any type of document to accurately extract text and data without the need for any manual effort or custom code. failed to get email addresses reliably out of simple PDF resumes (note - my overall review on Textract is still generally positive; see Conclusion below). The failure rate was better - roughly 10% instead of 30% but it still failed. What I did find fascinating, however, is how AWS Textract works under the hood. There appear to be three results from the Textract API call: apiResponse.json keyValues.csv rawText.txt These three results have different functions: a set of bounding boxes with text elements right down to geometry a set of semantic fields that they found in the document (I generally found this pretty useless; for a resume I would have expected things like contact info to be key values; instead it was a graduation date) the full text of the document Here's an example of the apiResponse.json which was the m