app.py

import streamlit as st
import os
from langchain_google_genai import GoogleGenerativeAIEmbeddings
import google.generativeai as genai
from langchain.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))

@st.cache_resource
def load_models_and_embeddings():
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    conversational_model = ChatGoogleGenerativeAI(model="gemini-2.5-pro", temperature=0.9)
    return embeddings, conversational_model

def get_conversational_chain(conversational_model):
    prompt_template = """
    Answer the question as detailed as possible from the provided context. If the answer is not in the context, say "answer is not available in the context" and do not provide an incorrect answer.\n\n
    Context:\n{context}\n
    Question:\n{question}\n
    Answer:
    """
    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
    chain = load_qa_chain(conversational_model, chain_type="stuff", prompt=prompt)
    return chain

def user_input(user_question, embeddings, conversational_model):
    try:
        new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
        docs = new_db.similarity_search(user_question, k=20)
        
        chain = get_conversational_chain(conversational_model)
        response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)

        # # Display context and response
        # st.write("### Context Used:")
        # for doc in docs:
        #     st.write(doc.page_content)

        st.write("### Answer:")
        st.write(response["output_text"])
    except Exception as e:
        st.error(f"An error occurred: {e}")

def main():
    st.set_page_config(page_title="HawkEyes")
    st.header("HawkEyes BOT")
    embeddings, conversational_model = load_models_and_embeddings()
    user_question = st.text_input("Ask Questions About HawkEyes")

    if user_question:
        user_input(user_question, embeddings, conversational_model)

if __name__ == "__main__":
    main()