This commit is contained in:
19
docs/snippets/python/utils/image_extraction.md
Normal file
19
docs/snippets/python/utils/image_extraction.md
Normal file
@@ -0,0 +1,19 @@
|
||||
```python title="Python"
|
||||
import asyncio
|
||||
from kreuzberg import ExtractionConfig, ImageExtractionConfig, extract_file
|
||||
|
||||
async def main() -> None:
|
||||
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 = await extract_file("document.pdf", config=config)
|
||||
print(f"Extracted: {result.content[:100]}")
|
||||
|
||||
asyncio.run(main())
|
||||
```
|
||||
Reference in New Issue
Block a user