| import pickle | |
| import faiss | |
| import streamlit as st | |
| from sentence_transformers import SentenceTransformer | |
| import pandas as pd | |
| def search(query, model, embeddings, filtered_df, top_x=30): | |
| filtered_df_indecies_list = filtered_df.index | |
| filtered_embeddings = embeddings[filtered_df_indecies_list] | |
| # Load or create FAISS index | |
| dimension = filtered_embeddings.shape[1] | |
| faiss_index = faiss.IndexFlatL2(dimension) | |
| faiss_index.add(filtered_embeddings) | |
| # Convert query to embedding | |
| query_embedding = model.encode([query])[0].reshape(1, -1) | |
| # Perform search | |
| D, I = faiss_index.search(query_embedding, k=top_x) # Search for top x similar items | |
| # Extract the sentences corresponding to the top indices | |
| #print(filtered_df.columns()) | |
| top_indecies = [i for i in I[0]] | |
| return filtered_df.iloc[top_indecies] |