Robility OCR Extractor
Robility OCR Extractor is an intelligent document processing component that extracts text and structured information from images, scanned documents, and PDF files. Rather than relying on traditional pixel-based OCR, it uses an OpenAI-compatible vision endpoint — allowing it to interpret document layout, context, and content with greater accuracy than conventional OCR engines.
The component is compatible with modern vision-serving platforms, including: vLLM, SGLang and Text Generation Inference (TGI). This makes it easy to run against self-hosted or third-party vision-language models without changing the integration logic.
Parameters
| Parameter | Description |
|---|---|
| File* |
Enter the file path of the image or PDF file from which you want to extract content.
Supported file formats are .jpg, .jpeg, .png, .tif, .tiff, and .pdf.
Note: To obtain the file path, use a component from the File System category and retrieve the file path from its output. Copy the file path and enter it in the File field. |
| Output Type |
Specifies the format of the extracted result.
Supported formats are Text, JSON, and HTML. |
| Timeout (Seconds) | Specifies the maximum time, in seconds, the component waits for the OCR request to complete before timing out. Default: 30 seconds. |
| API Key | Specifies the API key used to authenticate with the OpenAI-compatible vision endpoint. |
| Retry Count | Specifies the number of times the component retries the OCR request when an execution attempt fails. Default: 1. |
| Delay Between Retries (Seconds) | Specifies the time, in seconds, to wait between consecutive retry attempts. Default: 1 second. |
| Delay Before Execution (Seconds) | Specifies the time, in seconds, to wait before the component starts processing the input file. Default: 0 seconds. |
| Delay After Execution (Seconds) | Specifies the time, in seconds, to wait after the component finishes processing. Default: 0 seconds. |
| Continue on Error |
Determines the behavior when an unrecoverable error occurs.
|
Outputs
| Output | Description |
|---|---|
| Message | Returns the extracted OCR result in the selected output format. |
| JSON | Returns the extracted document content and structured information as JSON data. |
