Create rag_helper.py

rag_helper.py

@@ -0,0 +1,20 @@
+from sentence_transformers import SentenceTransformer
+import faiss
+import os
+
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+def build_knowledge_base(path="data/medical_guides"):
+    texts = []
+    for fname in os.listdir(path):
+        with open(os.path.join(path, fname), "r") as f:
+            texts.append(f.read())
+    embeddings = model.encode(texts)
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(embeddings)
+    return index, texts, os.listdir(path)
+
+def get_medical_guidance(query, index, texts):
+    query_vec = model.encode([query])
+    D, I = index.search(query_vec, k=1)
+    return texts[I[0][0]]