Update app.py

app.py

@@ -1,60 +1,142 @@
-import os
+from flask import Flask, render_template, request, send_from_directory, url_for
+from datetime import datetime
+from langchain_community.llms import HuggingFaceHub
+from langchain.prompts import PromptTemplate
 import requests
 import json
-from io import BytesIO
-
-from flask import Flask, jsonify, render_template, request, send_file
-
-from modules.inference import infer_t5
-from modules.dataset import query_emotion
-
-# https://huggingface.co/settings/tokens
-# https://huggingface.co/spaces/{username}/{space}/settings
-API_TOKEN = os.getenv("BIG_GAN_TOKEN")
+import nltk
+from textblob import TextBlob
+from nltk.tokenize import word_tokenize
+from nltk.stem import PorterStemmer
+from nltk.stem import WordNetLemmatizer
 
 app = Flask(__name__)
 
+# Load the JSON data from the file
+with open('ai_chatbot_data.json', 'r') as file:
+    json_data = json.load(file)
 
-@app.route("/")
-def index():
-    return render_template("index.html")
-
-
-@app.route("/infer_biggan")
-def biggan():
-    input = request.args.get("input")
-
-    output = requests.request(
-        "POST",
-        "https://api-inference.huggingface.co/models/osanseviero/BigGAN-deep-128",
-        headers={"Authorization": f"Bearer {API_TOKEN}"},
-        data=json.dumps(input),
-    )
+with open('info.txt', 'r') as file:
+    database_content = file.read()
+database_tag = database_content
 
-    return send_file(BytesIO(output.content), mimetype="image/png")
+template = "Message: {message}\n\nConversation History: {history}\n\nDate and Time: {date_time}\n\nBitcoin Price: ${bitcoin_price}\n\nBitcoin history from 1-jan-2024 to today: {database_tag}\n\nYour system: {json_data}.\n\nResponse:"
+prompt = PromptTemplate(template=template, input_variables=["message","history", "date_time", "bitcoin_price", "database_tag", "json_data"])
+conversation_history = []
 
+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)
 
-@app.route("/infer_t5")
-def t5():
-    input = request.args.get("input")
+    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
 
-    output = infer_t5(input)
-
-    return jsonify({"output": output})
-
-
-@app.route("/query_emotion")
-def emotion():
-    start = request.args.get("start")
-    end = request.args.get("end")
-
-    print(start)
-    print(end)
-
-    output = query_emotion(int(start), int(end))
-
-    return jsonify({"output": output})
+@app.route('/assets/<path:path>')
+def send_static(path):
+    return send_from_directory('assets', path)
 
+@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')
+
+    tokens = word_tokenize(user_input)
+    ps = PorterStemmer()
+    stemmed_tokens = [ps.stem(token) for token in tokens]
+
+    lemmatizer = WordNetLemmatizer()
+    lemmatized_tokens = [lemmatizer.lemmatize(token) for token in tokens]
+
+    sentiment = TextBlob(user_input).sentiment
+
+    bitcoin_price, current_time = get_bitcoin_price()
+
+    conversation_history.append("User: " + user_input)
+    
+    # NLTK processing for conversation history
+    history_tokens = word_tokenize("<br>".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, history="<br>".join(conversation_history), database_tag=database_content, date_time=current_time, bitcoin_price=bitcoin_price, json_data=json_data,history_tokens=history_tokens,history_stemmed_tokens=history_stemmed_tokens,history_lemmatized_tokens=history_lemmatized_tokens)
+    response = llm(model_input)
+
+    bot_response = response.split('Response:')[1].strip()
+    bot_response = bot_response.strip().replace('\n', '<br>')
+    conversation_history.append("Bot: " + bot_response)
+
+    conversation_html = '<br>'.join(conversation_history)
+
+    return bot_response
+##############################################################################################
+@app.route('/add_data', methods=['GET', 'POST'])
+def add_data():
+    if request.method == 'POST':
+        date = request.form['date']
+        open_price = request.form['open_price']
+        high_price = request.form['high_price']
+        low_price = request.form['low_price']
+        close_price = request.form['close_price']
+        adj_close = request.form['adj_close']
+        volume = request.form['volume']
+        
+        new_data = [date, open_price, high_price, low_price, close_price, adj_close, volume]
+
+        with open('info.txt', 'a') as file:
+            file.write('\t'.join(new_data) + '\n')
+
+    return render_template('admin.html')
+################################################################################################################################
+@app.route('/clear_history')
+def clear_history():
+    global conversation_history
+    conversation_history = []
+    return 'Conversation history cleared'
+
+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": 512,
+                             "top_p": 0.3,
+                             "repetition_penalty": 1.2,
+                             "num_beams": 3,
+                             "length_penalty": 1.5,
+                             "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)