Nomad changes

docs/snippets/python/llm/structured_extraction.md

@@ -0,0 +1,27 @@
+```python title="Python"
+import asyncio
+from kreuzberg import extract_file, ExtractionConfig, StructuredExtractionConfig, LlmConfig
+
+async def main() -> None:
+    config = ExtractionConfig(
+        structured_extraction=StructuredExtractionConfig(
+            schema={
+                "type": "object",
+                "properties": {
+                    "title": {"type": "string"},
+                    "authors": {"type": "array", "items": {"type": "string"}},
+                    "date": {"type": "string"},
+                },
+                "required": ["title", "authors", "date"],
+                "additionalProperties": False,
+            },
+            llm=LlmConfig(model="openai/gpt-4o-mini"),
+            strict=True,
+        ),
+    )
+    result = await extract_file("paper.pdf", config=config)
+    print(result.structured_output)
+    # {"title": "...", "authors": ["..."], "date": "..."}
+
+asyncio.run(main())
+```

docs/snippets/python/llm/vlm_embeddings.md

@@ -0,0 +1,16 @@
+```python title="Python"
+import asyncio
+from kreuzberg import embed, EmbeddingConfig, EmbeddingModelType, LlmConfig
+
+async def main() -> None:
+    config = EmbeddingConfig(
+        model=EmbeddingModelType.llm(
+            LlmConfig(model="openai/text-embedding-3-small")
+        ),
+        normalize=True,
+    )
+    embeddings = await embed(["Hello world"], config=config)
+    print(len(embeddings[0]))  # 1536
+
+asyncio.run(main())
+```

docs/snippets/python/llm/vlm_ocr.md

@@ -0,0 +1,17 @@
+```python title="Python"
+import asyncio
+from kreuzberg import extract_file, ExtractionConfig, OcrConfig, LlmConfig
+
+async def main() -> None:
+    config = ExtractionConfig(
+        force_ocr=True,
+        ocr=OcrConfig(
+            backend="vlm",
+            vlm_config=LlmConfig(model="openai/gpt-4o-mini"),
+        ),
+    )
+    result = await extract_file("scan.pdf", config=config)
+    print(result.content)
+
+asyncio.run(main())
+```