import os from langchain_google_genai import GoogleGenerativeAIEmbeddings from langchain_community.vectorstores import FAISS from langchain_core.documents import Document def create_or_load_vectorstore(text_chunks): embeddings = GoogleGenerativeAIEmbeddings( model="models/embedding-001", google_api_key=os.getenv("GOOGLE_API_KEY") ) documents = [ Document(page_content=chunk, metadata={"source": "resume"}) for chunk in text_chunks ] vectorstore = FAISS.from_documents( documents=documents, embedding=embeddings ) return vectorstore def similarity_search(vectorstore, query, k=5): try: documents = vectorstore.similarity_search(query, k=k) return documents except Exception as e: print(f"Error in similarity search: {str(e)}") return []