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 

import chainlit as cl

from langchain import hub
from langchain.chains import LLMChain, APIChain
from langchain_core.prompts import PromptTemplate
from langchain.memory.buffer import ConversationBufferMemory

from langchain_openai import OpenAI

from langchain_community.llms import HuggingFaceHub
from langchain_huggingface import HuggingFacePipeline
from langchain_huggingface import HuggingFaceEndpoint
from langchain_core.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
#HF_INFERENCE_ENDPOINT = 
#BOOKING_ID = re.compile(r'\b[A-Z]{6}\d{6}\b')
#HUGGINGFACEHUB_API_TOKEN = os.environ.get("HUGGINGFACEHUB_API_TOKEN")

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 (’kundeservice AI assistent’) for Daysoff.no
By default, you respond in Norwegian language, using a warm, direct and professional tone. 
Your expertise is exclusively in in providing information related to a given booking ID (’bestillingsnummer’)  
and booking-related queries such as firmahytteordning and personvernspolicy. 
You do not provide information outside of this scope. If a question is not about booking or booking-related queries,
respond with, "Ønsker du annen informasjon, må du kontakte oss her på [email protected]"
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  the specific user question: {question} in mind,
and given this API URL: {api_url} for querying,
here is the response from Daysoff's API: {api_response}.
Please provide an summary (in Norwegian) 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 = OpenAI(
        model='gpt-3.5-turbo-instruct',
        temperature=0.7, 
        openai_api_key=OPENAI_API_KEY,
        #max_tokens=512, 
        top_p=0.9,  
        frequency_penalty=0.5,
        presence_penalty=0.3   
    )

    
    #llm = HuggingFaceEndpoint(
        #repo_id="google/gemma-2-2b", #"norallm/normistral-7b-warm-instruct", 
        #endpoint_url="http://localhost:8010/",
    
        #model="google/gemma-2-2b",
        #max_new_tokens=512,
        #top_k=10,
        #top_p=0.95,
        #typical_p=0.95,
        #temperature=0.7,
        #repetition_penalty=1.03,
        #huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
        #task="text-generation"
    #)

    #llm = HuggingFacePipeline.from_model_id(
    #model_id="normistral-7b-warm-instruct",
    #task="text-generation",
    #pipeline_kwargs={"max_new_tokens": 10},
    #)
    
    conversation_memory = ConversationBufferMemory(memory_key="chat_history",
                                                   max_len=300,
                                                   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=None #["https://670dccd0073307b4ee447f2f.mockapi.io/daysoff/api/V1"]
    )

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

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

    # api_keywords = ["firmahytteordning", "personvernspolicy"]
    
    try:
        # --check message for booking ID
        if re.search(r'\b[A-Z]{6}\d{6}\b', user_message):  
            logging.debug(f"Booking ID detected in message: {user_message}")
            response = await api_chain.acall(user_message, callbacks=[cl.AsyncLangchainCallbackHandler()])

        # --check message for API keywords
        elif any(keyword in user_message for keyword in ["firmahytteordning", "personvernspolicy"]):   # any(keyword in user_message for keyword in api_keywords):
            logging.debug(f"API keyword detected in message: {user_message}")
            response = await api_chain.acall(user_message, callbacks=[cl.AsyncLangchainCallbackHandler()])

        else: 
            logging.debug("Triggering LLMChain for everything else.")
            response = await llm_chain.acall(user_message, callbacks=[cl.AsyncLangchainCallbackHandler()])

    except Exception as e:
        logging.error(f"Error in processing message: {str(e)}")
        response = {"output": "Jeg får desverre ikke hentet fram din informasjon akkurat nå."}

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



#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:
        #response = await api_chain.acall(user_message, callbacks=[cl.AsyncLangchainCallbackHandler()])
    # etc..