This commit is contained in:
34
docs/snippets/python/advanced/combining_all_features.md
Normal file
34
docs/snippets/python/advanced/combining_all_features.md
Normal file
@@ -0,0 +1,34 @@
|
||||
```python title="Python"
|
||||
import asyncio
|
||||
from kreuzberg import (
|
||||
extract_file,
|
||||
ExtractionConfig,
|
||||
ChunkingConfig,
|
||||
EmbeddingConfig,
|
||||
EmbeddingModelType,
|
||||
LanguageDetectionConfig,
|
||||
TokenReductionConfig,
|
||||
)
|
||||
|
||||
async def main() -> None:
|
||||
config: ExtractionConfig = ExtractionConfig(
|
||||
enable_quality_processing=True,
|
||||
language_detection=LanguageDetectionConfig(enabled=True),
|
||||
token_reduction=TokenReductionConfig(mode="moderate"),
|
||||
chunking=ChunkingConfig(
|
||||
max_chars=512,
|
||||
max_overlap=50,
|
||||
embedding=EmbeddingConfig(
|
||||
model=EmbeddingModelType.preset("balanced"), normalize=True
|
||||
),
|
||||
),
|
||||
)
|
||||
result = await extract_file("document.pdf", config=config)
|
||||
quality = result.quality_score or 0
|
||||
print(f"Quality: {quality:.2f}")
|
||||
print(f"Languages: {result.detected_languages}")
|
||||
if result.chunks:
|
||||
print(f"Chunks: {len(result.chunks)}")
|
||||
|
||||
asyncio.run(main())
|
||||
```
|
||||
Reference in New Issue
Block a user