Create utils.py

utils.py

@@ -0,0 +1,19 @@
+from sentence_transformers import SentenceTransformer
+import faiss
+import pandas as pd
+import numpy as np
+
+def load_dataset(path):
+    return pd.read_csv(path)
+
+def embed_questions(df, model_name="all-MiniLM-L6-v2"):
+    model = SentenceTransformer(model_name)
+    embeddings = model.encode(df["question"].tolist(), show_progress_bar=True)
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(np.array(embeddings))
+    return model, index, embeddings
+
+def retrieve_context(query, model, index, df, k=3):
+    query_vec = model.encode([query])
+    D, I = index.search(query_vec, k)
+    return "\n".join(df["answer"].iloc[i] for i in I[0])