Create get_embedding_function.py

get_embedding_function.py

@@ -0,0 +1,20 @@
+from sentence_transformers import SentenceTransformer
+
+def get_embedding_function():
+    # Load the local embedding model
+    model = SentenceTransformer('all-MiniLM-L6-v2')  # You can choose another model from Hugging Face
+
+    # Create an embedding function with `embed_documents` and `embed_query`
+    class EmbeddingsWrapper:
+        def embed_documents(self, texts):
+            """Embed a list of documents (texts)."""
+            embeddings = model.encode(texts, convert_to_tensor=False)
+            # Convert to list to avoid ambiguity with array truth values
+            return [embedding.tolist() if hasattr(embedding, "tolist") else embedding for embedding in embeddings]
+
+        def embed_query(self, text):
+            """Embed a single query."""
+            embedding = model.encode([text], convert_to_tensor=False)[0]
+            return embedding.tolist() if hasattr(embedding, "tolist") else embedding
+
+    return EmbeddingsWrapper()