Upload src/labdaps/ingestion/embedder.py with huggingface_hub

src/labdaps/ingestion/embedder.py

@@ -0,0 +1,26 @@
+from src.labdaps.config import EMBEDDING_MODEL, EMBED_QUERY_PREFIX, EMBED_PASSAGE_PREFIX
+
+
+class Embedder:
+    def __init__(self):
+        from sentence_transformers import SentenceTransformer
+        print(f"[INFO] Carregando modelo de embeddings: {EMBEDDING_MODEL}")
+        self._model = SentenceTransformer(EMBEDDING_MODEL)
+        print("[INFO] Modelo carregado.")
+
+    def embed_passages(self, texts: list[str], batch_size: int = 32) -> list[list[float]]:
+        prefixed = [f"{EMBED_PASSAGE_PREFIX}{t}" for t in texts]
+        vecs = self._model.encode(
+            prefixed,
+            batch_size=batch_size,
+            normalize_embeddings=True,
+            show_progress_bar=True,
+        )
+        return vecs.tolist()
+
+    def embed_query(self, query: str) -> list[float]:
+        vec = self._model.encode(
+            f"{EMBED_QUERY_PREFIX}{query}",
+            normalize_embeddings=True,
+        )
+        return vec.tolist()