ByteDance with Eachlabs
ByteDance's new video model, OmniHuman, is available on Eachlabs →
Eachlabs | AI Workflows for app builders

PDF to Text Generator

pdf-to-text

PDF to Text is an AI model that provides the text of a PDF from a URL.

CPU Small 10GB
Fast Inference
REST API
Try in ConsoleAPI DocsExamples

Model Information

Response Time~31 sec
StatusActive
Version
0.0.1
Updated9 days ago
API Reference
View Full Documentation

Prerequisites

  • Create an API Key from the Eachlabs Console
  • Install the required dependencies for your chosen language (e.g., requests for Python)

API Integration Steps

1. Create a Prediction

Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.

import requests
import time


API_KEY = "YOUR_API_KEY"  # Replace with your API key
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json"
}


def create_prediction():
    response = requests.post(
        "https://api.eachlabs.ai/v1/prediction/",
        headers=HEADERS,
        json={
            "model": "pdf-to-text",
            "version": "0.0.1",
            "input": {
  "url": "your url here"
}
        }
    )
    prediction = response.json()
    
    if prediction["status"] != "success":
        raise Exception(f"Prediction failed: {prediction}")
    
    return prediction["predictionID"]

2. Get Prediction Result

Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.

def get_prediction(prediction_id):
    while True:
        result = requests.get(
            f"https://api.eachlabs.ai/v1/prediction/{prediction_id}",
            headers=HEADERS
        ).json()
        
        if result["status"] == "success":
            return result
        elif result["status"] == "error":
            raise Exception(f"Prediction failed: {result}")
        
        time.sleep(1)  # Wait before polling again

3. Complete Example

Here's a complete example that puts it all together, including error handling and result processing. This shows how to create a prediction and wait for the result in a production environment.

try:
    # Create prediction
    prediction_id = create_prediction()
    print(f"Prediction created: {prediction_id}")
    
    # Get result
    result = get_prediction(prediction_id)
    print(f"Output URL: {result['output']}")
    print(f"Processing time: {result['metrics']['predict_time']}s")
except Exception as e:
    print(f"Error: {e}")

Additional Information

  • The API uses a two-step process: create prediction and poll for results
  • Response time: ~31 seconds
  • Rate limit: 60 requests/minute
  • Concurrent requests: 10 maximum
  • Use long-polling to check prediction status until completion

Overview

The PDF to Text Generator is designed to extract textual content from PDF files using Optical Character Recognition (OCR). By providing the URL of a PDF, PDF to Text Generator downloads the file, processes each page to recognize text, and outputs the extracted content. This facilitates the conversion of non-editable PDFs into accessible and editable text formats.

Technical Specifications

Processing Workflow:

  1. Download: Fetches the PDF from the provided URL.
  2. Conversion: Transforms each page of the PDF into an image format suitable for OCR processing.
  3. Text Extraction: Applies Tesseract OCR to each image to extract textual content.
  4. Output: Compiles the extracted text and provides it as the final output.

Key Considerations

URL Accessibility: The provided URL must be publicly accessible. URLs requiring authentication or located behind firewalls will not be accessible to PDF to Text Generator.

File Size and Length: Large PDFs or documents with numerous pages may result in longer processing times. It's advisable to test with smaller documents initially to gauge performance.

Tips & Tricks

Optimizing Input for Better Results:

  • High-Quality Scans: Use PDFs with a resolution of at least 300 DPI to improve OCR accuracy.
  • Preprocessing: If possible, preprocess PDFs to enhance clarity by removing noise, adjusting contrast, and correcting skewed text.
  • Language Specification: Specify the correct language in Tesseract settings to improve recognition accuracy for non-English texts.

Handling Complex Layouts:

  • Tables and Columns: Be aware that complex layouts with tables or multiple columns may not be accurately interpreted. Post-processing of the extracted text might be necessary to organize such content appropriately.

Error Handling:

  • Invalid URLs: Implement checks to validate the URL before processing to ensure it points to a valid PDF.
  • Timeouts: Set appropriate timeout settings for downloading large PDFs to prevent the process from hanging indefinitely.

Capabilities

Text Extraction: Converts textual content from PDFs into editable text, facilitating further processing or analysis.

Scalability: Suitable for batch processing of multiple PDFs, allowing for automation in workflows that require text extraction from numerous documents.

What can I use for?

Data Extraction: Retrieve textual information from reports, invoices, or academic papers stored in PDF format for data analysis or record-keeping.

Content Digitization: Convert scanned documents into editable text, aiding in digital archiving and content management.

Searchability Enhancement: Transform image-based PDFs into searchable text, improving the ability to locate specific information within large documents.

Things to be aware of

Different Languages: Experiment with PDFs in various languages to assess PDF to Text Generator's multilingual OCR capabilities.

Diverse Document Types: Use a variety of PDF documents, such as forms, reports, and scanned images, to understand PDF to Text Generator's versatility and identify any limitations in different contexts.

Limitations

Image-Only PDFs: PDFs that consist solely of images without embedded text rely entirely on OCR, which may not always accurately capture all textual content, especially if the images are of low quality.

Complex Formatting:  may struggle with PDFs that have intricate formatting, such as multiple columns, embedded tables, or non-standard fonts, leading to less accurate text extraction.


Output Format: Text