main.py

import os
import json
import bcrypt
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from typing import List
from pathlib import Path
from langchain_openai import ChatOpenAI
from langchain.schema.runnable.config import RunnableConfig
from langchain.schema import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate

from langchain.agents import AgentExecutor
from langchain.agents.agent_types import AgentType
from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent, create_csv_agent

import chainlit as cl
from chainlit.input_widget import TextInput, Select, Switch, Slider

from deep_translator import GoogleTranslator
from IPython.display import display

from surveycaa import surveyCaa

@cl.password_auth_callback
def auth_callback(username: str, password: str):
    auth = json.loads(os.environ['CHAINLIT_AUTH_LOGIN'])
    ident = next(d['ident'] for d in auth if d['ident'] == username)
    pwd = next(d['pwd'] for d in auth if d['ident'] == username)
    resultLogAdmin = bcrypt.checkpw(username.encode('utf-8'), bcrypt.hashpw(ident.encode('utf-8'), bcrypt.gensalt())) 
    resultPwdAdmin = bcrypt.checkpw(password.encode('utf-8'), bcrypt.hashpw(pwd.encode('utf-8'), bcrypt.gensalt())) 
    resultRole = next(d['role'] for d in auth if d['ident'] == username)
    if resultLogAdmin and resultPwdAdmin and resultRole == "admindatapcc":
        return cl.User(
            identifier=ident + " : 🧑‍💼 Admin Datapcc", metadata={"role": "admin", "provider": "credentials"}
        )
    elif resultLogAdmin and resultPwdAdmin and resultRole == "userdatapcc":
        return cl.User(
            identifier=ident + " : 🧑‍🎓 User Datapcc", metadata={"role": "user", "provider": "credentials"}
        )
        
def create_agent(filename: str):
    """
    Create an agent that can access and use a large language model (LLM).

    Args:
        filename: The path to the CSV file that contains the data.

    Returns:
        An agent that can access and use the LLM.
    """

    # Create an OpenAI object.
    os.environ['OPENAI_API_KEY'] = os.environ['OPENAI_API_KEY']
    llm = ChatOpenAI(temperature=0, model="gpt-4o-2024-05-13")

    # Read the CSV file into a Pandas DataFrame.
    df = pd.read_csv(filename)

    # Create a Pandas DataFrame agent.
    return create_csv_agent(llm, filename, verbose=False, allow_dangerous_code=True, handle_parsing_errors=True, agent_type=AgentType.OPENAI_FUNCTIONS)

def query_agent(agent, query):
    """
    Query an agent and return the response as a string.

    Args:
        agent: The agent to query.
        query: The query to ask the agent.

    Returns:
        The response from the agent as a string.
    """

    prompt = (
        """
            For the following query, if it requires drawing a table, reply as follows:
            {"table": {"columns": ["column1", "column2", ...], "data": [[value1, value2, ...], [value1, value2, ...], ...]}}

            If the query requires creating a bar chart, reply as follows:
            {"bar": {"columns": ["A", "B", "C", ...], "data": [25, 24, 10, ...]}}

            If the query requires creating a line chart, reply as follows:
            {"line": {"columns": ["A", "B", "C", ...], "data": [25, 24, 10, ...]}}

            There can only be two types of chart, "bar" and "line".

            If it is just asking a question that requires neither, reply as follows:
            {"answer": "answer"}
            Example:
            {"answer": "The title with the highest rating is 'Gilead'"}

            If you do not know the answer, reply as follows:
            {"answer": "I do not know."}

            Return all output as a string.

            All strings in "columns" list and data list, should be in double quotes,

            For example: {"columns": ["title", "ratings_count"], "data": [["Gilead", 361], ["Spider's Web", 5164]]}

            Lets think step by step.

            Below is the query.
            Query: 
            """
        + query
    )

    # Run the prompt through the agent.
    response = agent.invoke(prompt)

    # Convert the response to a string.
    return response.__str__()
    
def decode_response(response: str) -> dict:
    """This function converts the string response from the model to a dictionary object.

    Args:
        response (str): response from the model

    Returns:
        dict: dictionary with response data
    """
    return json.loads("[" + response + "]")

def write_response(response_dict: dict):
    """
    Write a response from an agent to a Streamlit app.

    Args:
        response_dict: The response from the agent.

    Returns:
        None.
    """

    # Check if the response is an answer.
    return response_dict["answer"]

@cl.action_callback("Download")
async def on_action(action):
    content = []
    content.append(action.value)
    arrayContent = np.array(content)
    df = pd.DataFrame(arrayContent)
    with open('./' + action.description + '.txt', 'wb') as csv_file:
        df.to_csv(path_or_buf=csv_file, index=False,header=False, encoding='utf-8')
    elements = [
        cl.File(
            name= action.description + ".txt",
            path="./" + action.description + ".txt",
            display="inline",
        ),
    ]
    await cl.Message(
        content="[Lien] 🔗", elements=elements
    ).send()
    await action.remove()
    
@cl.set_chat_profiles
async def chat_profile():
    return [
        cl.ChatProfile(name="Traitement des données d'enquête : «Expé CFA : questionnaire auprès des professionnels de la branche de l'agencement»",markdown_description="Vidéo exploratoire autour de l'événement",icon="/public/logo-ofipe.png",),
    ]
    
#@cl.set_starters
#async def set_starters():
#    return [
#        cl.Starter(
#            label="Répartition du nombre de CAA dans les entreprises",
#            message="Quel est le nombre de chargé.e d'affaires en agencement dans chaque type d'entreprises?",
#            icon="/public/request-theme.svg",
#            )
#    ]

@cl.on_chat_start
async def on_chat_start():
    await cl.Message(f"> SURVEYIA").send()
    await surveyCaa()
@cl.on_message
async def on_message(message: cl.Message):
    await cl.Message(f"> SURVEYIA").send()
    agent = create_agent("./public/surveyia.csv")
    cb = cl.AsyncLangchainCallbackHandler()
    try:
        res = await agent.acall("Réponds en langue française à la question suivante : " + message.content, callbacks=[cb])
        await cl.Message(author="COPILOT",content=GoogleTranslator(source='auto', target='fr').translate(res['output'])).send()
    except ValueError as e:
        res = str(e)
        resArray = res.split(":")
        ans = ''
        if str(res).find('parsing') != -1:
            for i in range(2,len(resArray)):
                ans += resArray[i]
            await cl.Message(author="COPILOT",content=ans.replace("`","")).send()
        else:
            await cl.Message(author="COPILOT",content="Reformulez votre requête, s'il vous plait 😃").send()
    # Query the agent.
    #response = query_agent(agent=agent, query=message.content)
    # Decode the response.
    #decoded_response = decode_response(response)

    # Write the response to the Streamlit app.
    #result = write_response(decoded_response)   
    #await cl.Message(author="COPILOT",content=GoogleTranslator(source='auto', target='fr').translate(result)).send()