Skip to content

Commit 2233d36

Browse files
Merge branch 'main' into DDOC-1453-iframe-for-chromium
2 parents b6e1998 + 43daed7 commit 2233d36

File tree

2 files changed

+31
-2
lines changed

2 files changed

+31
-2
lines changed

content/guides/box-ai/ai-tutorials/extract-metadata-structured.md

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -20,6 +20,30 @@ and get the result in the form of key-value pairs.
2020
As input, you can either create a structure using the `fields` parameter, or use an already defined metadata template.
2121
To learn more about creating templates, see [Creating metadata templates in the Admin Console][templates-console] or use the [metadata template API][templates-api].
2222

23+
## Supported file formats
24+
25+
The endpoint supports the following file formats:
26+
27+
- PDF
28+
- TIFF
29+
- PNG
30+
- JPEG
31+
32+
Box AI automatically applies optical character recognition (OCR) when processing image files (TIFF, PNG, JPEG) and scanned documents. This eliminates the need to convert images to PDF before extraction, saving time and simplifying your integration.
33+
34+
## Supported languages
35+
36+
Box AI can extract metadata from documents in the following languages:
37+
<!--alex ignore-->
38+
- English
39+
- Japanese
40+
- Chinese
41+
- Korean
42+
<!--alex enable-->
43+
- Cyrillic-based languages (such as Russian, Ukrainian, Bulgarian, and Serbian)
44+
45+
No additional configuration is required to use different languages or image formats. Box AI automatically detects the language and applies OCR when needed.
46+
2347
## Before you start
2448

2549
Make sure you followed the steps listed in [getting started with Box AI][prereq] to create a platform app and authenticate.

content/guides/box-ai/ai-tutorials/extract-metadata.md

Lines changed: 7 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -14,9 +14,13 @@ alias_paths:
1414

1515
# Extract metadata from file (freeform)
1616

17-
Box AI API allows you to query a document or image and extract metadata based on a provided prompt.
17+
Box AI API allows you to query a document and extract metadata based on a provided prompt.
1818
**Freeform** means that the prompt can include a stringified version of formats such as JSON or XML, or even plain text.
1919

20+
<Message type="notice">
21+
The **Extract metadata (freeform)** endpoint doesn't support OCR. To extract metadata from image files (TIFF, PNG, JPEG) or documents in languages other than English, use the [Extract metadata (structured)][structured-endpoint] endpoint.
22+
</Message>
23+
2024
## Before you start
2125

2226
Make sure you followed the steps listed in [getting started with Box AI][prereq] to create a platform app and authenticate.
@@ -151,4 +155,5 @@ The response includes the `fields` present in the file, along with their values:
151155
[agent]: e://get_ai_agent_default
152156
[model-param]: r://ai_agent_text_gen#param_basic_gen_model
153157
[prompt-param]: r://ai_agent_text_gen#param_basic_gen_prompt_template
154-
[overrides]: g://box-ai/ai-agents/ai-agent-overrides
158+
[overrides]: g://box-ai/ai-agents/ai-agent-overrides
159+
[structured-endpoint]: g://box-ai/ai-tutorials/extract-metadata-structured

0 commit comments

Comments
 (0)