Update app.py

app.py

@@ -1,172 +1,74 @@
-from flask import Flask, render_template, request, send_from_directory
-from datetime import datetime
-from langchain_community.llms import HuggingFaceHub
-from langchain.prompts import PromptTemplate
 import requests
-import json
-import nltk
-from textblob import TextBlob
-from nltk.tokenize import word_tokenize
-from nltk.stem import PorterStemmer
-from nltk.stem import WordNetLemmatizer
-import spacy
-from bs4 import BeautifulSoup
-
-
-# Download NLTK resources
-nltk.download('punkt')
-nltk.download('wordnet')
-
-# Download Spacy model
-def download_spacy_model():
-    import spacy
-    try:
-        spacy.load("en_core_web_sm")
-    except OSError:
-        import spacy.cli
-        spacy.cli.download("en_core_web_sm")
-
-download_spacy_model()
-
-nlp = spacy.load("en_core_web_sm")
+from flask import Flask, render_template, request
+import speech_recognition as sr
 
 app = Flask(__name__)
+with open('i.txt', 'r') as file:
+    data = file.read()
+API_URL = "https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1"
+headers = {"Authorization": f"Bearer hf{data}"}
 
-# Load the JSON data from the file
-with open('ai_chatbot_data.json', 'r') as file:
-    json_data = json.load(file)
-
-# Updated prompt template for Bitcoin trading
-template = "🌟 **Analysis Report for BTC Trading & Prediction** 🌟\n\n📩 **User Message:**\n{message}\n\n💰 **BTC Price Now** 💹\nCurrent Price: ${bitcoin_price}\nTime: {date_time}\n\n📊 **BTC Historical Data** 📈\nCheck the historical data to analyze price trends.\nTrading Data from 01/01/2024 to {date_time}:\n{result}\n\n🗣️ **Current Conversation Overview** 💬\nRefer to user interactions for context.\nUser Interaction:\n{history}\n\n🤔 **User Sentiment Analysis** 📝\nAnalyze user sentiment for market insights.\nUser Sentiment: {sentiment}\n\n💻 **System Data** 📊\nUtilize system insights for decision-making.\nSystem Insights:\n{json_data}\n\n💡 **Response Recommendations** 💬\nBased on the data provided, suggest trading strategies or predictions.\nAI System Data: {json_data}\n\nResponse:"
-prompt = PromptTemplate(template=template, input_variables=["message", "sentiment", "history", "date_time", "bitcoin_price", "result", "json_data"])
-conversation_history = []
-
-MAX_HISTORY_LENGTH = 55
-
-
-def update_conversation_history(message):
-    if len(conversation_history) >= MAX_HISTORY_LENGTH:
-        conversation_history.pop(0)
-    conversation_history.append(message)
-
-# Function to retrieve Bitcoin price
-def get_bitcoin_price():
-    current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-    url = 'https://api.coindesk.com/v1/bpi/currentprice.json'
-    response = requests.get(url)
-
-    if response.status_code == 200:
-        data = response.json()
-        bitcoin_price = data['bpi']['USD']['rate']
-        return bitcoin_price, current_time
-    else:
-        return 'Error fetching data', current_time
-
-
-
+recognizer = sr.Recognizer()
 
-def get_div_content(url):
-    response = requests.get(url)
-    soup = BeautifulSoup(response.content, 'html.parser')
-    
-    div_content = soup.find('div', {'id': '45'})
-    if div_content:
-        return div_content
-    else:
-        return "No div with id=45 found on the page."
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
 
-url = "https://dooratre-info.hf.space/?logs=container&__sign=eyJhbGciOiJFZERTQSJ9.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sIm9uQmVoYWxmT2YiOnsia2luZCI6InVzZXIiLCJfaWQiOiI2NWIyYzMyNjJiZTk2NjBmMGIxMjg0MDAiLCJ1c2VyIjoiRG9vcmF0cmUifSwiaWF0IjoxNzEyNjgwNTY4LCJzdWIiOiIvc3BhY2VzL0Rvb3JhdHJlL2luZm8iLCJleHAiOjE3MTI3NjY5NjgsImlzcyI6Imh0dHBzOi8vaHVnZ2luZ2ZhY2UuY28ifQ.R_PX6Hw5SMheYTQWPGe1Qla9q8gVBU0mAFF_u8Iad06jSpZ9sPzZqquSowWn7PGVLRYBW21DnvqSwXIoNZ4CAA"
+conversation_history = []
 
-result = get_div_content(url)
-print(result)
-    
-@app.route('/assets/<path:path>')
-def send_static(path):
-    return send_from_directory('assets', path)
+def generate_response(user_input):
+    new_query = {
+        "inputs": f"you are ai for help in anything you are created by Mr,Omar Nuwara he is made you \n\n make sure to help people in anything \n\ntask:complete the reesponse:\n\nconversation history:{conversation_history}\n\nuser message:{user_input}\n\nmake sure to response about it and don't generate alot of words just based on the user message \n\n\n\nresponse:",
+        "parameters": {
+            "top_k": 50,
+            "top_p": 0.9,
+            "temperature": 0.1,
+            "repetition_penalty": 1.2,
+            "max_new_tokens": 512,
+            "max_time": 0,
+            "return_full_text": True,
+            "num_return_sequences": 1,
+            "do_sample": False
+        },
+        "options": {
+            "use_cache": False,
+            "wait_for_model": False
+        }
+    }
+
+    output = query(new_query)
+
+    generated_text = output[0]['generated_text']
+
+    response_start = generated_text.find('response:') + len('response:')
+    response_end = generated_text.find('(end response)')
+
+    response_text = generated_text[response_start:response_end].strip()
+
+    note_index = response_text.find("Note:")
+    if note_index != -1:
+        response_text = response_text[:note_index].strip()
+
+    instruction_index = response_text.find("### Instruction:")
+    if instruction_index != -1:
+        response_text = response_text[:instruction_index].strip()
+
+    return response_text
 
 @app.route('/')
 def index():
-    global conversation_history
-    return render_template('index.html', conversation=conversation_history)
-
-@app.route('/submit', methods=['POST'])
-def submit():
-    user_input = request.json.get('user_input')
-
-    doc = nlp(user_input)
-    tokens = [token.text for token in doc]
-
-    sentiment = TextBlob(user_input).sentiment
-
-    ps = PorterStemmer()
-    stemmed_tokens = [ps.stem(token) for token in tokens]
-
-    lemmatizer = WordNetLemmatizer()
-    lemmatized_tokens = [lemmatizer.lemmatize(token) for token in tokens]
-
-    bitcoin_price, current_time = get_bitcoin_price()
-
-    conversation_history.append("User: " + user_input)
-
-    history_tokens = word_tokenize("\n".join(conversation_history))
-    history_stemmed_tokens = [ps.stem(token) for token in history_tokens]
-    history_lemmatized_tokens = [lemmatizer.lemmatize(token) for token in history_tokens]
-
-    model_input = prompt.format(message=user_input, sentiment=sentiment, history="\n".join(conversation_history), 
-                                result=result, date_time=current_time, bitcoin_price=bitcoin_price, json_data=json_data)
+    return render_template('cont.html')
 
-    response = llm(model_input, context="<br>".join(conversation_history))
-
-    bot_response = response.split('Response:')[1].strip()
-    bot_response = bot_response.strip().replace('\n', '<br>')
-
-    update_conversation_history("Bot: " + bot_response)
-
-    conversation_html = '<br>'.join(conversation_history)
-
-    return bot_response
-
-@app.route('/clear_history')
-def clear_history():
-    global conversation_history
-    conversation_history = []
-    return 'Conversation history cleared'
+@app.route('/chat', methods=['POST'])
+def chat():
+    user_input = request.form['user_input']
+    
+    # Generate AI response based on user input
+    response_text = generate_response(user_input)
+    conversation_history.append({"User": user_input, "AI": response_text})
+    
+    return response_text
 
-with open('i.txt', 'r') as file:
-    data = file.read()
 
-if __name__ == "__main__":
-    repo_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
-    huggingfacehub_api_token = "hf" + data
-
-    llm = HuggingFaceHub(huggingfacehub_api_token=huggingfacehub_api_token,
-                         repo_id=repo_id,
-                         model_kwargs={
-                             "temperature": 0.5,
-                             "max_new_tokens": 256,
-                             "top_p": 0.5,
-                             "repetition_penalty": 1.2,
-                             "num_beams": 3,
-                             "length_penalty": 1.2,
-                             "no_repeat_ngram_size": 2,
-                             "early_stopping": True,
-                             "num_return_sequences": 1,
-                             "use_cache": True,
-                             "task": "predictions",
-                             "data_source": "financial_markets",
-                             "historical_data_fetch": True,
-                             "real-time_data_integration": True,
-                             "feature_engineering": ["technical_indicators", "sentiment_analysis", "volume_analysis"],
-                             "machine_learning_models": ["LSTM", "Random Forest", "ARIMA", "Gradient Boosting"],
-                             "prediction_horizon": "short-term",
-                             "evaluation_metrics": ["accuracy", "MSE", "MAE", "RMSE"],
-                             "model_fine-tuning": True,
-                             "interpretability_explanation": True,
-                             "ensemble_methods": ["voting", "stacking"],
-                             "hyperparameter_optimization": True,
-                             "cross-validation": True,
-                             "online_learning": True,
-                         }
-                         )
-
-    app.run(host="0.0.0.0", port=7860)
+if __name__ == '__main__':
+    app.run(debug=True)