import chromadb
import os
import gradio as gr
import json
from huggingface_hub import InferenceClient
import gspread
from oauth2client.service_account import ServiceAccountCredentials
from datetime import datetime

# Google Sheets setup
scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
import json
import requests
from huggingface_hub import HfApi, HfFolder
import os

api_key = os.getenv("key")
# Step 1: Authenticate with Hugging Face Hub
api = HfApi()
# Replace 'your_token' with your actual Hugging Face API token
HfFolder.setup_token(api_token=api_key)

# Step 2: Specify your Hugging Face username, Space name, and file name
username = 'thiloid'
space_name = 'envapi'
file_name = 'nestolechatbot-5fe2aa26cb52.json'

# Step 3: Get download URL for the JSON file
download_url = f'https://huggingface.co/{username}/{space_name}/resolve/main/{file_name}'

# Step 4: Download the file content
try:
    response = requests.get(download_url)
    response.raise_for_status()  # Raise an exception for bad responses
except requests.exceptions.HTTPError as e:
    print(f"HTTP error occurred: {e}")
    exit()

# Step 5: Load JSON data
try:
    json_data = json.loads(response.content)
    print("JSON data loaded successfully:")
except json.JSONDecodeError as e:
    print(f"JSON decoding error occurred: {e}")
creds = ServiceAccountCredentials.from_json_keyfile_name(json_data, scope)


#creds = ServiceAccountCredentials.from_json_keyfile_name('/home/user/app/chromaold/nestolechatbot-5fe2aa26cb52.json', scope)
client = gspread.authorize(creds)
sheet = client.open("nestolechatbot").sheet1  # Open the sheet

def save_to_sheet(date,name, message):
    # Write user input to the Google Sheet
    sheet.append_row([date,name, message])
    return f"Thanks {name}, your message has been saved!"

    
path='/Users/thiloid/Desktop/LSKI/ole_nest/Chatbot/LLM/chromaTS'
if(os.path.exists(path)==False): path="/home/user/app/chromaTS"

print(path)
#path='chromaTS'
#settings = Settings(persist_directory=storage_path)
#client = chromadb.Client(settings=settings)
client = chromadb.PersistentClient(path=path)
print(client.heartbeat()) 
print(client.get_version())  
print(client.list_collections()) 
from chromadb.utils import embedding_functions
default_ef = embedding_functions.DefaultEmbeddingFunction()
sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="T-Systems-onsite/cross-en-de-roberta-sentence-transformer")#"VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct")
#instructor_ef = embedding_functions.InstructorEmbeddingFunction(model_name="hkunlp/instructor-large", device="cuda")
#print(str(client.list_collections()))
collection = client.get_collection(name="chromaTS", embedding_function=sentence_transformer_ef)

client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")


def format_prompt(message, history):
  prompt = "" #"<s>"
  #for user_prompt, bot_response in history:
  #  prompt += f"[INST] {user_prompt} [/INST]"
  #  prompt += f" {bot_response}</s> "
  prompt += f"[INST] {message} [/INST]"
  return prompt

def response(
    prompt, history,temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2: temperature = 1e-2
    top_p = float(top_p)
    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )
    addon=""
    results=collection.query(
      query_texts=[prompt],
      n_results=60,
      #where={"source": "google-docs"}
      #where_document={"$contains":"search_string"}
    )
    #print("REsults")
    #print(results)
    #print("_____")
    dists=["<br><small>(relevance: "+str(round((1-d)*100)/100)+";" for d in results['distances'][0]]
  
    #sources=["source: "+s["source"]+")</small>" for s in results['metadatas'][0]]
    results=results['documents'][0]
    print("TEst")
    print(results)
    print("_____")
    combination = zip(results,dists)
    combination = [' '.join(triplets) for triplets in combination]
    #print(str(prompt)+"\n\n"+str(combination))
    if(len(results)>1):
      addon=" Bitte berücksichtige bei deiner Antwort ausschießlich folgende Auszüge aus unserer Datenbank, sofern sie für die Antwort erforderlich sind. Beantworte die Frage knapp und präzise. Ignoriere unpassende Datenbank-Auszüge OHNE sie zu kommentieren, zu erwähnen oder aufzulisten:\n"+"\n".join(results)
    system="Du bist ein deutschsprachiges KI-basiertes Studienberater Assistenzsystem, das zu jedem Anliegen möglichst geeignete Studieninformationen empfiehlt."+addon+"\n\nUser-Anliegen:"   
    formatted_prompt = format_prompt(system+"\n"+prompt,history)
    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""
    for response in stream:
        output += response.token.text
        yield output
    #output=output+"\n\n<br><details open><summary><strong>Sources</strong></summary><br><ul>"+ "".join(["<li>" + s + "</li>" for s in combination])+"</ul></details>"
    # Get current date and time
    now = str(datetime.now())
    save_to_sheet(now,prompt, output)
    yield output

gr.ChatInterface(response, chatbot=gr.Chatbot(value=[[None,"Herzlich willkommen! Ich bin Chätti ein KI-basiertes Studienassistenzsystem, das für jede Anfrage die am besten Studieninformationen empfiehlt.<br>Erzähle mir, was du gerne tust!"]],render_markdown=True),title="German Studyhelper Chätti").queue().launch(share=True) #False, server_name="0.0.0.0", server_port=7864)
print("Interface up and running!")