This commit is contained in:
17
docs/snippets/python/ocr/image_extraction.md
Normal file
17
docs/snippets/python/ocr/image_extraction.md
Normal file
@@ -0,0 +1,17 @@
|
||||
```python title="Python"
|
||||
from kreuzberg import extract_file_sync, ExtractionConfig, ImageExtractionConfig
|
||||
|
||||
config: ExtractionConfig = ExtractionConfig(
|
||||
images=ImageExtractionConfig(
|
||||
extract_images=True,
|
||||
target_dpi=200,
|
||||
max_image_dimension=2048,
|
||||
inject_placeholders=True, # set to False to extract images without markdown references
|
||||
auto_adjust_dpi=True,
|
||||
)
|
||||
)
|
||||
|
||||
result = extract_file_sync("document.pdf", config=config)
|
||||
|
||||
print(f"Content length: {len(result.content)} characters")
|
||||
```
|
||||
Reference in New Issue
Block a user