File size: 5,056 Bytes
f79e226
 
f709b40
70ee030
f709b40
 
 
 
 
 
 
 
70ee030
 
f709b40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a1fb2d
f709b40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a1fb2d
f709b40
 
 
8a1fb2d
f709b40
8a1fb2d
f709b40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a4fe116
 
 
28418e7
a4fe116
28418e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a4fe116
 
f709b40
 
 
 
 
 
 
a4fe116
 
 
 
 
 
f709b40
 
 
 
 
a4fe116
f709b40
 
1c84663
f709b40
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
### title: 010125-daysoff-assistant-api
### file: app.py

import asyncio
import os
import time
import json
import torch

from api_docs_mck import daysoff_api_docs

import chainlit as cl
#from chainlit import LLMSettings # hmm..
#from chainlit.config import config # hmm...

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


HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
LANGCHAIN_API_KEY = os.environ.get("LANGCHAIN_API_KEY")
HF_TOKEN = os.environ.get("HF_TOKEN")

#os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:true"

dtype = torch.float16
device = torch.device("cuda")

daysoff_assistant_booking_template = """
You are a customer support assistant for Daysoff.no. Your expertise is
retrieving booking information for a given booking ID."
Chat History: {chat_history}
Question: {question}
Answer:
"""
daysoff_assistant_booking_prompt= PromptTemplate(
    input_variables=["chat_history", "question"],
    template=daysoff_assistant_booking_template
)

api_url_template = """
Given the following API Documentation for Daysoff's official
booking information API: {api_docs_mck}
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_mck', 'question'],
                                template=api_url_template)

api_response_template = """"
With the API Documentation for Daysoff's official API: {api_docs_mck}
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 user with their booking information,
focusing on delivering the answer with clarity and conciseness,
as if a human customer service agent is providing this information.
Adapt to user's language. By default, you speak Norwegian.
Booking information:
"""
# omitting technical details like response format, and
api_response_prompt = PromptTemplate(input_variables=['api_docs_mck',
                                                      'question',
                                                      'api_url',
                                                      'api_response'],
                                     template=api_response_template)


# --model, memory object, and llm_chain
@cl.on_chat_start
def setup_multiple_chains():
    llm = HuggingFaceHub(repo_id="google/gemma-2-2b-it",
                         temperature=0.7,
                         huggingface_api_token=HUGGINGFACEHUB_API_TOKEN,
                         device=device)

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

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

    api_chain = APIChain.from_llm_and_api_docs_mck(
        llm=llm,
        api_docs_mck=daysoff_api_docs,
        api_url_prompt=api_url_prompt,
        api_response_prompt=api_response_prompt,
        verbose=True,
        limit_to_domains=None)

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


# --regex for alphanum. "LLLLLLxxxxxx", i.e. booking_id  |==> 308.9 trillion unique possibilities
BOOKING_ID = r'\b[A-Z]{6}\d{6}\b'

# --keywords based from email-data
BOOKING_KEYWORDS = [
    "booking",
    "bestillingsnummer",
    "bookingen",
    "ordrenummer",
    "reservation",
    "rezerwacji", 
    "bookingreferanse", 
    "rezerwacja", 
    "logg inn", 
    "booket", 
    "reservation number",
    "bestilling", 
    "order number",
    "booking ID",
    "identyfikacyjny pล‚atnoล›ci"  
]

# --wrapper function around the @cl.on_message decorator; chain trigger(s)
@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")

    is_booking_query = any(
        re.search(keyword, user_message, re.IGNORECASE) 
        for keyword in BOOKING_KEYWORDS + [BOOKING_ID]
    )

    if is_booking_query:
        response = await api_chain.acall(user_message,
                                         callbacks=[cl.AsyncLangchainCallbackHandler()])
    else:
        response = await llm_chain.acall(user_message,
                                         callbacks=[cl.AsyncLangchainCallbackHandler()])
    
    response_key = "output" if "output" in response else "text"
    await cl.Message(response.get(response_key, "")).send()
    return message.content