src/utils.py

import faiss
import numpy as np
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("all-MiniLM-L6-v2")

def get_embeddings(texts):
    return model.encode(texts, convert_to_numpy=True)

def build_index(embeddings):
    dim = embeddings.shape[1]
    index = faiss.IndexFlatIP(dim)
    faiss.normalize_L2(embeddings)
    index.add(embeddings)
    return index

def search_similar(index, query_embedding, k=5):
    faiss.normalize_L2(query_embedding)
    distances, indices = index.search(query_embedding, k)
    return distances, indices