Untitled

    meeting_invite_prompt = PromptTemplate(
        template="""
    You are a system that parses a user's meeting request: {query}

    You must return valid response that replies to the users meeting request which collates all the below factors.:
    1. "data_issues"
    2. "meeting_start"
    3. "meeting_end"
    4. "attendees"
 

    Requirements:
    - "data_issues":
      - If there's ambiguity about which user to add in the scenario of two or more similar names in the user_to_email map: {user_to_email}),  provide a clarification message here.
      - If there exist only a singular entry most similar to the attendee add that to the attendee list(as an example 
        the user said 'john' needs to be added but 'john_doe' key exists and we have no other 'john' entries then add 
        'john_doe" email to attendees).
      - If a requested user is not found in user_to_email, provide an appropriate error message here.
      - If there are no issues, do not add this factor as part of the response.
      - If the meeting_start and "meeting_end" cannot be inferred from the  {query} and {current_time} then ask clarifying questioning like 
       which timezone,date,meeting duration etc
    - "meeting_start" / "meeting_end":
      -The current timestamp is {current_time} this is the current date and time in UTC with timezone information attached.
      -Based on the user query  calculate the appropriate meeting_start and meeting_end time stamp 
       by converting the requested meeting time into meeting_start and meeting_end time stamp given  {query} {current_time}
      - The meeting_start and meeting_end must be in the same format as current_time: {current_time} format.
    - "attendees":
      - A list of attendee email addresses.
    -If we have "data_issues" ignore the other factors and give only the response relevant to "data_issues". 
    """,
        input_variables=["query", "user_to_email"],
    )
    chain = meeting_invite_prompt | llm | parser