added scaffold struct for the prj

kg_ocr/embeddings/__init__.py

@@ -0,0 +1,3 @@
+from .indexer import create_and_index, query_embedding
+
+__all__ = ["create_and_index", "query_embedding"]

kg_ocr/embeddings/config_loader.py

@@ -0,0 +1 @@
+# in future prefer a config, especially for graph traversal

kg_ocr/embeddings/indexer.py

@@ -0,0 +1,23 @@
+from txtai.embeddings import Embeddings
+
+
+def create_and_index(
+    data: list[str], model: str = "sentence-transformers/all-MiniLM-L6-v2"
+) -> Embeddings:
+    """Create and index embeddings from text."""
+    embeddings = Embeddings({
+        "path": model,
+        "content": True,
+        "hybrid": True,
+        "scoring": "bm25",
+    })
+    embeddings.index(data)
+    return embeddings
+
+
+def query_embedding(
+    embeddings: Embeddings, query: str, limit: int = 100
+) -> list[str]:
+    """Search embeddings and return matching texts."""
+    results = embeddings.search(query, limit)
+    return [r["text"] for r in results]