Update app.py

app.py

@@ -1,50 +1,92 @@
-import gradio as gr
-import tensorflow as tf
-import numpy as np
-
-# Load the trained model
-model = tf.keras.models.load_model('model.h5')
-print("Model loaded successfully!")
-
-def preprocess_image(image):
-    """Process the input image to match MNIST format"""
-    # Convert to grayscale
-    image = image.convert('L')
-    # Resize to 28x28
-    image = image.resize((28, 28))
-    # Convert to numpy array and normalize
-    image_array = np.array(image)
-    image_array = image_array / 255.0
-    # Reshape to match model input
-    image_array = np.expand_dims(image_array, axis=0)
-    return image_array
-
-def predict_digit(image):
-    if image is None:
-        return None
-    
-    # Preprocess the image
-    processed_image = preprocess_image(image)
-    
-    # Make prediction
-    predictions = model.predict(processed_image)
-    pred_scores = tf.nn.softmax(predictions[0]).numpy()
-    pred_class = np.argmax(pred_scores)
-    
-    # Create result string
-    result = f"Prediction: {pred_class}"
-    
-    return result
-
-# Create Gradio interface
-demo = gr.Interface(
-    fn=predict_digit,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Textbox(label="Result"),
-    title="MNIST Digit Recognizer",
-    description="Upload a digit from 0-9 and the model will predict which digit it is.",
-    examples=None,
-)
-
-if __name__ == "__main__":
-    demo.launch()
+import streamlit as st
+from PyPDF2 import PdfReader
+from io import BytesIO
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+
+# Hardcoded Gemini API keys
+API_KEYS = [
+    "AIzaSyBYbyC4qCJoKxKR-r0oIn4SVqj4CfSdx4s",
+    "AIzaSyBfvYURYVijTurxvFUyV3vZkCojpOAAnFk"
+]
+current_key_index = -1
+
+def switch_api_key():
+    global current_key_index
+    current_key_index = (current_key_index + 1) % len(API_KEYS)
+    return API_KEYS[current_key_index]
+
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(BytesIO(pdf.read()))
+        for page in pdf_reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text
+    return text
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    return text_splitter.split_text(text)
+
+def get_vector_store(text_chunks, api_key):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    # Use /tmp for Hugging Face Spaces
+    vector_store.save_local("/tmp/faiss_index")
+
+def get_conversational_chain(api_key):
+    prompt_template = """
+    You are a helpful assistant that only answers based on the context provided from the PDF documents.
+    Do not use any external knowledge or assumptions. If the answer is not found in the context below, reply with "I don't know."
+    Context:
+    {context}
+    Question:
+    {question}
+    Answer:
+    """
+    model = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0, google_api_key=api_key)
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+def user_input(user_question, api_key):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+    # Use /tmp for Hugging Face Spaces
+    new_db = FAISS.load_local("/tmp/faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+    chain = get_conversational_chain(api_key)
+    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+    st.write("Reply: ", response["output_text"])
+
+def main():
+    st.set_page_config(page_title="Chat PDF")
+    st.header("CSC 121: Computers and Scientific Thinking (Chatbot)")
+    st.subheader("Ask a question ONLY from the CSC 121 textbook of Dr. Reed", divider=True)
+
+    user_api_key = st.text_input("Enter your API key (optional)", type="password")
+    user_question = st.text_input("Ask a question")
+
+    if user_question:
+        api_key = user_api_key if user_api_key else switch_api_key()
+        user_input(user_question, api_key)
+
+    pdf_docs = st.file_uploader("Upload PDF files", accept_multiple_files=True, type=['pdf'])
+    if st.button("Submit & Process"):
+        if pdf_docs:
+            with st.spinner("Processing..."):
+                api_key = user_api_key if user_api_key else switch_api_key()
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                get_vector_store(text_chunks, api_key)
+                st.success("Done")
+        else:
+            st.error("Please upload at least one PDF file.")
+
+if __name__ == "__main__":
+    main()