Update knowledge_base.py

knowledge_base.py

@@ -11,4 +11,24 @@ def create_faiss_index(texts):
     index = faiss.IndexFlatL2(dimension)
     index.add(embeddings)
 
-    return index, texts
+    return index, texts
+
+    def search_faiss(faiss_index, stored_texts, query, top_k=3):
+    """
+    Search the FAISS index for the most relevant texts based on the query.
+    """
+    from sentence_transformers import SentenceTransformer
+
+    # Load the same model used for indexing
+    model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+    # Encode the query into an embedding
+    query_embedding = model.encode([query])
+
+    # Search the FAISS index
+    distances, indices = faiss_index.search(query_embedding, top_k)
+
+    # Retrieve the corresponding texts
+    results = [stored_texts[i] for i in indices[0] if i < len(stored_texts)]
+
+    return results