Update app.py

app.py

@@ -11,12 +11,9 @@ import json
 
 import chainlit as cl
 
-#from tiktoken import encoding_for_model
-
-from pydantic import BaseModel, ConfigDict
-
 from langchain import hub
 from langchain_openai import OpenAI
+from tiktoken import encoding_for_model
 from langchain.chains import LLMChain, APIChain
 from langchain_core.prompts import PromptTemplate
 from langchain.memory.buffer import ConversationBufferMemory
@@ -24,13 +21,10 @@ from langchain.memory import ConversationTokenBufferMemory
 from langchain.memory import ConversationSummaryMemory
 
 from api_docs_mck import api_docs_str 
-#from personvernspolicy import instruction_text_priv, personvernspolicy_data
-#from frequently_asked_questions import instruction_text_faq, faq 
-
+#from api_docs import api_docs_str
 
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
 
-# If you don't know the answer, just say that you don't know, don't try to make up an answer.
 daysoff_assistant_template = """
 #You are a customer support assistant (’kundeservice AI assistent’) for Daysoff. 
 #By default, you respond in Norwegian language, using a warm, direct, and professional tone. 
@@ -59,9 +53,7 @@ API URL:
 """
 api_url_prompt = PromptTemplate(input_variables=['api_docs', 'question'],
                                 template=api_url_template)
-
-# If the response includes booking information, provide the information verbatim (do not summarize it.)
-    
+  
 api_response_template = """
 With the API Documentation for Daysoff's official API: {api_docs} in mind,
 and the specific user question: {question},
@@ -78,19 +70,6 @@ api_response_prompt = PromptTemplate(
     template=api_response_template
 )
 
-# ---------------------------------------------------------------------------------------------------------
-# 100 tokens ≃ 75 words
-# system prompt(s), total = 330 tokens
-# average api response = 250-300 tokens (current)
-# user input "reserved" = 400 tokens (300 words max. /English; Polish, Norwegian {..}?@tiktokenizer), could be reduc3d to 140 tokens ≃ 105 words
-# model output (max_tokens) = 2048
-
-# ConversationBufferMemory = maintains raw chat history; crucial for "nuanced" follow-ups (e.g. "nuanced" ~ for non-English inputs)
-# ConversationTokenBufferMemory (max_token_limit) = 1318 (gives space in chat_history for approximately 10-15 exchanges, assuming ~100 tokens/exchange) 
-# ConversationSummaryMemory = scalable approach, especially useful for extended or complex interactions, caveat: loss of granular context
-# ---------------------------------------------------------------------------------------------------------
-
-
 @cl.on_chat_start
 def setup_multiple_chains():
 
@@ -104,22 +83,10 @@ def setup_multiple_chains():
         presence_penalty=0.1   
     )
 
-    # --ConversationBufferMemory
     conversation_memory = ConversationBufferMemory(memory_key="chat_history", 
-                                                   max_len=30,  # --retains only the last 30 exchanges
+                                                   max_len=30, 
                                                    return_messages=True,
     )
-    
-    # --ConversationTokenBufferMemory
-    #conversation_memory = ConversationTokenBufferMemory(memory_key="chat_history",
-                                                        #max_token_limit=1318,
-                                                        #return_messages=True,
-    #)
-
-    # --ConversationSummaryMemory
-    #conversation_memory = ConversationSummaryMemory(memory_key="chat_history",
-                                                    #return_messages=True,
-    #)
 
     llm_chain = LLMChain(
         llm=llm,