run.py

import os
import gradio as gr
import json
from huggingface_hub import InferenceClient
import gspread
from google.oauth2 import service_account
from datetime import datetime
import chromadb

# Google Sheets setup
scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
key1 = os.getenv("key1")
key2 = os.getenv("key2")
key3 = os.getenv("key3")
key4 = os.getenv("key4")
key5 = os.getenv("key5")
key6 = os.getenv("key6")
key7 = os.getenv("key7")
key8 = os.getenv("key8")
key9 = os.getenv("key9")
key10 = os.getenv("key10")
key11 = os.getenv("key11")
key12 = os.getenv("key12")
key13 = os.getenv("key13")
key14 = os.getenv("key14")
key15 = os.getenv("key15")
key16 = os.getenv("key16")
key17 = os.getenv("key17")
key18 = os.getenv("key18")
key19 = os.getenv("key19")
key20 = os.getenv("key20")
key21 = os.getenv("key21")
key22 = os.getenv("key22")
key23 = os.getenv("key23")
key24 = os.getenv("key24")
key25 = os.getenv("key25")
key26 = os.getenv("key26")
key27 = os.getenv("key27")
key28 = os.getenv("key28")
pkey="-----BEGIN PRIVATE KEY-----\n"+key2+"\n"+key3+"\n"+ key4+"\n"+key5+"\n"+ key6+"\n"+key7+"\n"+key8+"\n"+key9+"\n"+key10+"\n"+key11+"\n"+key12+"\n"+key13+"\n"+key14+"\n"+key15+"\n"+key16+"\n"+key17+"\n"+key18+"\n"+key19+"\n"+key20+"\n"+key21+"\n"+key22+"\n"+key24+"\n"+key25+"\n"+key26+"\n"+key27+"\n"+key28+"\n-----END PRIVATE KEY-----\n"
json_data={
  "type": "service_account",
  "project_id": "nestolechatbot",
  "private_key_id": key1,
  "private_key": pkey,
  "client_email": "[email protected]",
  "client_email": "[email protected]",
  "client_id": "107457262210035412036",
  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
  "token_uri": "https://oauth2.googleapis.com/token",
  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/nestoleservice%40nestolechatbot.iam.gserviceaccount.com",
  "universe_domain": "googleapis.com"
}
creds = service_account.Credentials.from_service_account_info(json_data, scopes=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 not os.path.exists(path):
    path = "/home/user/app/chromaTS"

print(path)
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")

collection = client.get_collection(name="chromaTS", embedding_function=sentence_transformer_ef)

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

# Global variable to store the URL
global_url = ""

def format_prompt(message, history):
    print("HISTORY")
    print(history)
    prompt = ""
    if history:
        user_prompt, bot_response = history[-1]
        prompt += f"[INST] {user_prompt} [/INST] {bot_response}</s> "
    prompt += f"[INST] {message} [/INST]"
    print("Final P")
    print(prompt)
    return prompt

def response(prompt, history, temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0):
    global global_url
    print(f"Working with URL: {global_url}")  # You can use the URL here
    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,
    )
    search_prompt = format_prompt(prompt, history)
    results = collection.query(
        query_texts=[search_prompt],
        n_results=60,
    )
    dists = ["<br><small>(relevance: " + str(round((1-d)*100)/100) + ";" for d in results['distances'][0]]
    results = results['documents'][0]
    combination = zip(results, dists)
    combination = [' '.join(triplets) for triplets in 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 = inference_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
    now = str(datetime.now())
    save_to_sheet(now, prompt, output)
    yield output

def js_code():
    return """
    <script>
        function getUrl() {
            const url = window.location.href;
            const xhr = new XMLHttpRequest();
            xhr.open("POST", "/submit_url", true);
            xhr.setRequestHeader("Content-Type", "application/json");
            xhr.onreadystatechange = function() {
                if (xhr.readyState === 4 && xhr.status === 200) {
                    console.log("URL submitted successfully");
                }
            };
            xhr.send(JSON.stringify({ url: url }));
        }
        window.onload = getUrl;
    </script>
    """

def submit_url(url: str):
    global global_url
    global_url = url  # Save the URL in the global variable
    print(f"Received URL: {url}")
    return url

iface = gr.Interface(
    fn=response,
    inputs=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"
)

# Add a route to handle the URL submission
iface.launch(share=True, js=js_code())

@gr.routes.post("/submit_url")
async def process_url(request):
    data = await request.json()
    url = data.get("url", "")
    submit_url(url)
    return {"status": "success"}

print("Interface up and running!")