You can change a workflow’s preconfigured strategy only through Custom workflow settings.
- VLM: For the highest-quality transformation of these file types:
.bmp
,.gif
,.heic
,.jpeg
,.jpg
,.pdf
,.png
,.tiff
, and.webp
. - High Res: For all other supported file types, and for the generation of bounding box coordinates.
- Fast: For text-only documents.
.pdf
files, the Auto partitioning strategy routes these files’ pages
on a page-by-page basis, as follows:
- A page is routed to Fast when it contains only embedded text and no images or tables are detected.
- All other kinds of pages are routed to VLM or High Res, depending on the complexity of a page’s content. Unstructured constantly optimizes its proprietary algorithm for routing to VLM or High Res in these cases.
Images and tables in PDF files
The differences between the various partitioning strategies can be more clearly demonstrated by the ways each of these strategies handle images and tables within PDF files. For example, the Fast partitioning strategy skips processing images altogether in PDF files:







Handwriting and multilanguage characters in PDF files
The differences between the various partitioning strategies can be more clearly demonstrated by the ways each of these strategies handle handwriting and multilanguage characters within PDF files. For example, the Fast partitioning strategy skips processing handwriting altogether in PDF files. The Fast strategy processes multilanguage characters in PDF files with limited output, depending on the language. In the following example, Japanese hiragana characters are processed as text, but the output can be very difficult to work with:




Supported languages
Fast partitioning accepts any text inputs, though automatic language detection of those inputs is restricted to langdetect. High Res partitioning leverages Tesseract OCR. For the list of languages that Tesseract supports, see: Languages/Scripts supported in different versions of Tesseract. Language support for VLM depends on the model used. The list of supported languages for a particular model is maintained by that model’s provider. For the list of languages that each model supports, see the following, where provided:-
Anthropic
- Claude 3.5 Sonnet: Arabic, Bengali, Chinese (Simplified), English, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese (Brazil), Spanish, Swahili, and Yoruba are mentioned. (Source)
-
OpenAI
- GPT-4o: Arabic, Chinese, English, French, German, Gujarati, Hindi, Italian, Japanese, Korean, Marathi, Persian, Portuguese, Russian, Spanish, Tamil, Telugu, Turkish, Urdu, and Vietnamese are mentioned. (Source)
-
Amazon Bedrock
- Claude 3.5 Sonnet: “English, Spanish, Japanese, and multiple other languages” (Source)
- Claude 3 Opus: “English, Spanish, Japanese, and multiple other languages” (Source)
- Claude 3 Haiku: “English, Spanish, Japanese, and multiple other languages” (Source)
- Claude 3 Sonnet: “English, Spanish, Japanese, and multiple other languages” (Source)
- Amazon Nova Pro: “200+ languages” (Source)
- Amazon Nova Lite: “200+ languages” (Source)
- Meta Llama 3.2 90B Instruct: “English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai” (Source)
- Meta Llama 3.2 11B Instruct: “English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai” (Source)