import os
os.environ["OPENAI_API_KEY"]

from llama_index import (
    VectorStoreIndex,
    SummaryIndex,
    SimpleKeywordTableIndex,
    SimpleDirectoryReader,
    ServiceContext,
    StorageContext,
    load_index_from_storage
)
from llama_index.schema import IndexNode
from llama_index.tools import QueryEngineTool, ToolMetadata
from llama_index.llms import OpenAI

llm = OpenAI(temperature=0, model="gpt-3.5-turbo")
service_context = ServiceContext.from_defaults(llm=llm)

PERSIST_DIR = "arv_metadata"
storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
index = load_index_from_storage(storage_context)
query_engine = index.as_query_engine(similarity_top_k=3, llm=OpenAI(model="gpt-3.5-turbo"))


preamble = (" The person asking the following prompt is a person living with HIV in Kenya."
            " For every response, recognize that they already have HIV and do not suggest that they have to get tested"
            " for HIV or take post-exposure prophylaxis, as that is not relevant, though their partners perhaps should."  
            " Do not suggest anything that is not relevant to someone who already has HIV."
           " They are asking questions through a mobile application called Nishauri"
           " through which they can see their lab results, appointment histories, and upcoming appointments."
           " Here is some information that is authoritative and should guide responses, when relevant."
           " For questions about viral load, be sure to provide specific information"
           " about cutoffs for viral load categories. Under 50 copies/ml is low detectable level,"
           " 50 - 199 copies/ml is low level viremia, 200 - 999 is high level viremia, and "
           " 1000 and above is suspected treatment failure." 
           " A high viral load or non-suppressed viral load is any viral load above 200 copies/ml."
           " A suppressed viral load is one below 200 copies / ml."
           " An established client is one who is on their current ART regimen for a period greater"
           " than 6 months, had no active OI or in the previous 6 months, has adhered to scheduled"
           " clinic visits for the previous 6 months and Viral load results has been less than 200 copies/ml"
           " within the last 6 months."
           " For questions about when patients should get their viral loads taken," 
           " if they are newly initiated on ART, the first viral load sample should be taken after 3 months of"
           " taking ART. Otherwise, if they are not new on ART, then if their previous result was below 50 to 199 cp/ml,"
           " their viral load should be taken after every 12 months. If  their previous result was above 200cp/ml,"
           " then viral load sample should be taken after three months."
           " Please answer the prompt using the information retrieved" 
           " and do not rely at all on your prior knowledge."
           " Please keep your reply to no longer than three sentences, and please use simple language. ")

prompt_intro = (" Here is the prompt: ")

import gradio as gr

def nishauri(question: str, conversation_history: list[str]):
    
    
    context = " ".join([item["user"] + " " + item["chatbot"] for item in conversation_history])
    response = query_engine.query(preamble +
                                  "the user previously asked and received the following: " +
                                  context +
                                  prompt_intro +
                                  question)

    conversation_history.append({"user": question, "chatbot": response.response})   

    source1 = ("File Name: " +
      response.source_nodes[0].metadata["file_name"] +
      "\nPage Number: " +
      response.source_nodes[0].metadata["page_label"] +
      "\n Source Text: " +
     response.source_nodes[0].text)
    
    source2 = ("File Name: " +
      response.source_nodes[1].metadata["file_name"] +
      "\nPage Number: " +
      response.source_nodes[1].metadata["page_label"] +
      "\n Source Text: " +
     response.source_nodes[1].text)
        
    source3 = ("File Name: " +
      response.source_nodes[2].metadata["file_name"] +
      "\nPage Number: " +
      response.source_nodes[2].metadata["page_label"] +
      "\n Source Text: " +
     response.source_nodes[2].text)
    
    return response, source1, source2, source3, conversation_history

inputs = [gr.Textbox(lines=10, label="Question"),
          gr.State(value=[])]
outputs = [
    gr.Textbox(label="Chatbot Response", type="text"),
    gr.Textbox(label="Source 1", max_lines = 10, autoscroll = False, type="text"),
    gr.Textbox(label="Source 2", max_lines = 10, autoscroll = False, type="text"),
    gr.Textbox(label="Source 3", max_lines = 10, autoscroll = False, type="text"),
    gr.State()
]

gr.Interface(fn=nishauri, inputs=inputs, outputs=outputs, title="Nishauri Chatbot", 
             description="Enter a question and see the processed outputs in collapsible boxes.").launch()