app.py

import gradio as gr
import requests
import pandas as pd
from langchain.chat_models import ChatOpenAI
from langchain.document_loaders import CSVLoader
from langchain_together import TogetherEmbeddings
from langchain.vectorstores import Chroma
from langchain_core.vectorstores import InMemoryVectorStore
from langchain import PromptTemplate
from langchain import LLMChain
from langchain_together import Together
import os

os.environ['TOGETHER_API_KEY'] = "your_api_key"

# Initialize global variable for vectorstore
vectorstore = None
embeddings = TogetherEmbeddings(model="togethercomputer/m2-bert-80M-8k-retrieval")
llama3 = Together(model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", max_tokens=1024)

def update_csv_files():
    login_url = "https://livesystem.hisabkarlay.com/auth/login"
    payload = {
        "username": "user@123",
        "password": "user@123",
        "client_secret": "kNqJjlPkxyHdIKt3szCt4PYFWtFOdUheb8QVN8vQ",
        "client_id": "5",
        "grant_type": "password"
    }
    response = requests.post(login_url, data=payload)

    if response.status_code == 200:
        access_token = response.json()['access_token']
    else:
        return f"Failed to log in: {response.status_code}"

    report_url = "https://livesystem.hisabkarlay.com/connector/api/profit-loss-report"
    headers = {"Authorization": f"Bearer {access_token}"}
    response = requests.get(report_url, headers=headers)
    profit_loss_data = response.json()['data']
    keys = list(profit_loss_data.keys())
    del keys[23]
    del keys[20]
    del keys[19]
    data_dict = {}
    for key in keys:
        data_dict[key] = profit_loss_data.get(key)
    df = pd.DataFrame(data_dict, index=[0])
    df.to_csv('profit_loss.csv', index=False)

    report_url = "https://livesystem.hisabkarlay.com/connector/api/purchase-sell"
    response = requests.get(report_url, headers=headers)
    sell_purchase_data = response.json()
    sell_purchase_data = dict(list(sell_purchase_data.items())[2:])
    df = pd.json_normalize(sell_purchase_data)
    df.to_csv('purchase_sell_report.csv', index=False)

    report_url = "https://livesystem.hisabkarlay.com/connector/api/trending-products"
    response = requests.get(report_url, headers=headers)
    trending_product_data = response.json()['data']
    df = pd.DataFrame(trending_product_data)
    df.columns = ['Product Units Sold', 'Product Name', 'Unit Type', 'SKU (Stock Keeping Unit)']
    df.to_csv('trending_product.csv', index=False)

    return "CSV files updated successfully!"

def initialize_embedding():
    global vectorstore

    file_paths = ["profit_loss.csv", "purchase_sell_report.csv", "trending_product.csv"]
    documents = []
    for path in file_paths:
        loader = CSVLoader(path, encoding="windows-1252")
        documents.extend(loader.load())

    vectorstore = InMemoryVectorStore.from_texts(
        [doc.page_content for doc in documents],
        embedding=embeddings,
    )
    return "Embeddings initialized successfully!"

def qa_chain(query):
    if vectorstore is None:
        return "Please initialize the embeddings first."
    
    retriever = vectorstore.as_retriever()
    retrieved_documents = retriever.invoke(query)
    return retrieved_documents

def generate_response(query, history):
    if vectorstore is None:
        return "Please initialize the embeddings first.", history

    retrieved_documents = qa_chain(query)
    chat_template = """
You are a highly intelligent and professional AI assistant.
Generate the response according to the user's query:
Context: {retrieved_documents}
Question: {query}
"""
    prompt = PromptTemplate(
        input_variables=['retrieved_documents', 'query'],
        template=chat_template
    )
    
    Generated_chat = LLMChain(llm=llama3, prompt=prompt)
    response = Generated_chat.invoke({'retrieved_documents': retrieved_documents, 'query': query})

    # Ensure history is always a list of two-element lists [query, response]
    history.append([query, response['text']])
    
    # Return the updated history and the new response for display
    return history, history

def gradio_app():
    with gr.Blocks() as app:
        gr.Markdown("# Embedding and QA Interface")

        # Chatbox elements
        chatbot = gr.Chatbot(label="Chat")
        query_input = gr.Textbox(label="Enter your query")
        generate_response_btn = gr.Button("Generate Response")

        # Status output textboxes for CSV update and embedding initialization
        update_csv_status = gr.Textbox(label="CSV Update Status", interactive=False)
        initialize_status = gr.Textbox(label="Embedding Initialization Status", interactive=False)

        # Buttons for CSV update and embedding initialization
        update_csv_button = gr.Button("Update CSV Files")
        initialize_button = gr.Button("Initialize Embedding")

        # Button click actions
        update_csv_button.click(update_csv_files, outputs=update_csv_status)
        initialize_button.click(initialize_embedding, outputs=initialize_status)

        # Chatbot functionality with history
        history = gr.State([])  # Chat history state
        generate_response_btn.click(generate_response, inputs=[query_input, history], outputs=[chatbot, history])

    app.launch()

# Run the Gradio app
gradio_app()