vector_store.py

import faiss
from langchain.vectorstores import FAISS
from langchain.schema import Document
from embeddings import get_embedding  # Import the updated embedding function

# FAISS parameters
dim = 384  # Size of the embedding (MiniLM has 384-dimensional vectors)
index = faiss.IndexFlatL2(dim)
vector_db = FAISS(embedding_function=get_embedding, index=index)

def add_document(text, doc_id):
    """Add document embeddings to FAISS."""
    doc = Document(page_content=text, metadata={"id": doc_id})
    vector_db.add_documents([doc])

def search(query):
    """Search FAISS index for similar documents."""
    results = vector_db.similarity_search(query, k=3)
    return results