Update app.py

app.py

@@ -1,80 +1,67 @@
 # app.py
 import gradio as gr
+import torch
 import pandas as pd
-import numpy as np
+from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
 import yfinance as yf
-from ta import add_all_ta_features
-from ta.utils import dropna
-from transformers import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
-from sentence_transformers import SentenceTransformer
-import faiss
 
-# Load the dataset from Google Drive
-def load_data():
-    url = "https://drive.google.com/uc?export=download&id=1N1bCVRSacs7_nENJzleqqNRHA22-H9B5"
-    df = pd.read_csv(url)
-    return df
+# Load the fine-tuned RAG model and tokenizer
+tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence-base")
+retriever = RagRetriever.from_pretrained("facebook/rag-sequence-base", index_name="custom")
+model = RagSequenceForGeneration.from_pretrained("facebook/rag-sequence-base", retriever=retriever)
 
-# Preprocess the data
-def preprocess_data(df):
-    df = dropna(df)
-    df = add_all_ta_features(df, open="Open", high="High", low="Low", close="Close", volume="Volume", fillna=True)
-    return df
-
-# Train the FAISS index for RAG
-def train_faiss_index(df):
-    model = SentenceTransformer('all-MiniLM-L6-v2')
-    embeddings = model.encode(df['Close'].astype(str).tolist())
-    dimension = embeddings.shape[1]
-    index = faiss.IndexFlatL2(dimension)
-    index.add(embeddings)
-    return index, model
-
-# Load the QA model
-def load_qa_model():
-    model_name = "deepset/roberta-base-squad2"
-    model = AutoModelForQuestionAnswering.from_pretrained(model_name)
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
-    return qa_pipeline
-
-# Get technical analysis
-def get_technical_analysis(df):
-    analysis = {
-        "SMA_50": df['Close'].rolling(window=50).mean().iloc[-1],
-        "SMA_200": df['Close'].rolling(window=200).mean().iloc[-1],
-        "RSI": df['momentum_rsi'].iloc[-1],
-        "MACD": df['trend_macd_diff'].iloc[-1],  # Updated for `ta` library
-    }
-    return analysis
-
-# RAG-based QA function
-def rag_qa(question, df, index, model, qa_pipeline):
-    query_embedding = model.encode([question])
-    distances, indices = index.search(query_embedding, k=1)
-    context = df.iloc[indices[0][0]]['Close']
-    result = qa_pipeline(question=question, context=str(context))
-    return result['answer']
+# Function to fetch and preprocess ICICI Bank data
+def fetch_and_preprocess_data():
+    # Fetch ICICI Bank data using yfinance
+    ticker = "ICICIBANK.NS"
+    data = yf.download(ticker, start="2020-01-01", end="2023-01-01")
+    
+    # Calculate technical indicators
+    data['MA_50'] = data['Close'].rolling(window=50).mean()
+    data['MA_200'] = data['Close'].rolling(window=200).mean()
+    
+    return data
 
-# Gradio Interface
-def trading_analysis_app(question):
-    df = load_data()
-    df = preprocess_data(df)
-    index, model = train_faiss_index(df)
-    qa_pipeline = load_qa_model()
+# Function to analyze trading data using the RAG model
+def analyze_trading_data(question):
+    # Fetch and preprocess data
+    data = fetch_and_preprocess_data()
+    
+    # Prepare context for the RAG model
+    context = (
+        f"ICICI Bank stock data:\n"
+        f"Latest Close Price: {data['Close'].iloc[-1]:.2f}\n"
+        f"50-Day Moving Average: {data['MA_50'].iloc[-1]:.2f}\n"
+        f"200-Day Moving Average: {data['MA_200'].iloc[-1]:.2f}\n"
+    )
+    
+    # Combine question and context
+    input_text = f"Question: {question}\nContext: {context}"
+    
+    # Tokenize the input
+    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)
+    
+    # Generate the answer using the RAG model
+    outputs = model.generate(inputs['input_ids'])
     
-    analysis = get_technical_analysis(df)
-    answer = rag_qa(question, df, index, model, qa_pipeline)
+    # Decode the output to get the answer
+    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
     
-    return f"Technical Analysis: {analysis}\n\nAnswer: {answer}"
+    return answer
 
-# Gradio Interface
+# Gradio interface
 iface = gr.Interface(
-    fn=trading_analysis_app,
+    fn=analyze_trading_data,
     inputs="text",
     outputs="text",
-    title="RAG-based Trading Analysis",
-    description="Enter your question about ICICIBANK's stock to get technical analysis and answers."
+    title="ICICI Bank Trading Analysis",
+    description="Ask any question about ICICI Bank's trading data and get a detailed analysis.",
+    examples=[
+        "What is the current trend of ICICI Bank stock?",
+        "Is the 50-day moving average above the 200-day moving average?",
+        "What is the latest closing price of ICICI Bank?"
+    ]
 )
 
+# Launch the app
 iface.launch()