Nomad changes
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s

This commit is contained in:
Henrik Jess Nielsen
2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions

View File

@@ -0,0 +1,39 @@
```python title="Python"
import asyncio
from kreuzberg import (
ExtractionConfig,
ChunkingConfig,
EmbeddingConfig,
EmbeddingModelType,
extract_file,
)
async def main() -> None:
config: ExtractionConfig = ExtractionConfig(
chunking=ChunkingConfig(
max_characters=500,
overlap=50,
embedding=EmbeddingConfig(
model=EmbeddingModelType({"type": "preset", "name": "balanced"}),
normalize=True,
),
)
)
result = await extract_file("research_paper.pdf", config=config)
for chunk in result.chunks or []:
print(
f"Chunk {chunk.metadata.chunk_index + 1}/{chunk.metadata.total_chunks}"
)
print(
f"Position: {chunk.metadata.byte_start}-{chunk.metadata.byte_end}"
)
print(f"Content: {chunk.content[:100]}...")
if chunk.embedding is not None:
print(f"Embedding: {len(chunk.embedding)} dimensions")
asyncio.run(main())
```