app.py

### title: 010125-daysoff-assistant-api
### file: app.py

import asyncio
import os
import re
import time
import json
import torch

import logging

from api_docs_mck import api_docs_str 
#from daysoff import daysoff_str                        ## make daysoff.py, put json info in dict.
#from personvernpolicy import personvernpolicy_str      ## make personvernpolicy.py, put json info in dict.

import chainlit as cl

from langchain import hub
from langchain.chains import LLMChain, APIChain
from langchain_core.prompts import PromptTemplate
#from langchain_community.llms import HuggingFaceHub
from langchain_huggingface import HuggingFaceEndpoint
from langchain.memory.buffer import ConversationBufferMemory

logging.basicConfig(level=logging.DEBUG)

HUGGINGFACEHUB_API_TOKEN = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
BOOKING_ID = re.compile(r'\b[A-Z]{6}\d{6}\b')
BOOKING_KEYWORDS = [
    "booking",
    "bestillingsnummer",
    "bookingen",
    "ordrenummer",
    "reservation",
    "rezerwacji",
    "bookingreferanse",
    "rezerwacja",
    "booket",
    "reservation number",
    "bestilling",
    "order number",
    "booking ID",
    "identyfikacyjny płatności"
]


daysoff_assistant_template = """
You are a customer support assistant for Daysoff named "Agrippa". Your expertise is in retrieving 
booking details for a given booking ID and answering questions about
Daysoff's personvernspolicy and firmahytteordning. You do not provide information outside of this 
scope. By default, you respond in Norwegian language.
Chat History: {chat_history}
Question: {question}
Answer:
"""
daysoff_assistant_prompt= PromptTemplate(
    input_variables=["chat_history", "question"],
    template=daysoff_assistant_template
)

api_url_template = """
Given the following API Documentation for Daysoff's official
booking information API: {api_docs}
Your task is to construct the most efficient API URL to answer
the user's question, ensuring the
call is optimized to include only the necessary information.
Question: {question}
API URL:
"""
api_url_prompt = PromptTemplate(input_variables=['api_docs', 'question'],
                                template=api_url_template)

# (..) If {question} contains an alphanumeric identifier consisting of 6 letters followed by 6 digits (e.g., DAGHNS116478)
api_response_template = """
With the API Documentation for Daysoff's official API: {api_docs} in mind, 
and user question: {question}, and given this API URL: {api_url} for querying, 
here is the response from Daysoff's API: {api_response}.
Please provide an summary that directly addresses the user's question, 
omitting technical details like response format, and 
focusing on delivering the answer with clarity and conciseness, 
as if a human customer service agent is providing this information.
Summary:
"""

api_response_prompt = PromptTemplate(
    input_variables=['api_docs', 'question', 'api_url', 'api_response'],
    template=api_response_template
)

@cl.on_chat_start
def setup_multiple_chains():
    
    llm = HuggingFaceEndpoint(
    repo_id="google/gemma-2-2b-it", #"norallm/normistral-7b-warm-instruct", 
    huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN, 
    #max_new_tokens=512,  
    temperature=0.7,     
    task="text-generation"  
    )

    conversation_memory = ConversationBufferMemory(memory_key="chat_history",
                                                   max_len=200,
                                                   return_messages=True,
                                                   )
    llm_chain = LLMChain(llm=llm,
                         prompt=daysoff_assistant_prompt,
                         memory=conversation_memory
                        )

    cl.user_session.set("llm_chain", llm_chain)

    api_chain = APIChain.from_llm_and_api_docs(
        llm=llm,
        api_docs=api_docs_str,
        api_url_prompt=api_url_prompt,
        api_response_prompt=api_response_prompt,
        verbose=True,
        limit_to_domains=["https://670dccd0073307b4ee447f2f.mockapi.io/daysoff/api/V1"]
    )

    cl.user_session.set("api_chain", api_chain)
    

@cl.on_message
async def handle_message(message: cl.Message):
    user_message = message.content.lower()
    llm_chain = cl.user_session.get("llm_chain")
    api_chain = cl.user_session.get("api_chain")

    #if any(keyword in user_message for keyword in ["firmahytteordning","personvernpolicy"]):
    
       
    #def is_booking_query(user_message):
        #match = re.search(r'\b[A-Z]{6}\d{6}\b', user_message)
        #return match is not None  # --works boolean
    #booked = is_booking_query(user_message)
    #if booked: 

    if re.search(r'\b[A-Z]{6}\d{6}\b', user_message):   # ex., "Hei, har du booking info for EQJLCQ362149?"
        logging.debug(f"User message: {user_message}")
        response = await api_chain.acall(user_message, 
                                         callbacks=[cl.AsyncLangchainCallbackHandler()])

    else: 
        response = await llm_chain.acall(user_message,
                                         callbacks=[cl.AsyncLangchainCallbackHandler()])

        logging.debug(f"API response: {response}")

    response_key = "output" if "output" in response else "text"
    await cl.Message(response.get(response_key, "")).send()
    return message.content