Update app.py

app.py

@@ -26,8 +26,16 @@ def search_similar(query_embedding, index, stored_texts, top_k=3):
     results = [(stored_texts[i], distances[0][idx]) for idx, i in enumerate(indices[0])]
     return results
 
+# Function to generate code based on a prompt
+def generate_code_from_prompt(prompt, model="gpt-4o-mini"):
+    response = openai.ChatCompletion.create(
+        model=model,
+        messages=[{"role": "user", "content": prompt}]
+    )
+    return response['choices'][0]['message']['content']
+
 # Streamlit app starts here
-st.title("Course Query Assistant")
+st.title("AI Assistance")
 
 # Input OpenAI API key
 openai_api_key = st.text_input("Enter your OpenAI API key:", type="password")
@@ -35,59 +43,85 @@ openai_api_key = st.text_input("Enter your OpenAI API key:", type="password")
 if openai_api_key:
     openai.api_key = openai_api_key
 
-    # Upload course materials
-    uploaded_files = st.file_uploader("Upload Course Materials (PDFs)", type=["pdf"], accept_multiple_files=True)
+    # Sidebar to toggle between Course Query Assistant and Code Generator
+    st.sidebar.title("Select Mode")
+    mode = st.sidebar.radio("Choose an option", ("Course Query Assistant", "Code Generator"))
+
+    if mode == "Course Query Assistant":
+        st.header("Course Query Assistant")
+
+        # Upload course materials
+        uploaded_files = st.file_uploader("Upload Course Materials (PDFs)", type=["pdf"], accept_multiple_files=True)
+
+        if uploaded_files:
+            st.write("Processing uploaded course materials...")
+
+            # Extract text and generate embeddings for all uploaded PDFs
+            course_texts = []
+            for uploaded_file in uploaded_files:
+                text = extract_text_from_pdf(uploaded_file)
+                course_texts.append(text)
 
-    if uploaded_files:
-        st.write("Processing uploaded course materials...")
+            # Combine all course materials into one large text
+            combined_text = " ".join(course_texts)
 
-        # Extract text and generate embeddings for all uploaded PDFs
-        course_texts = []
-        for uploaded_file in uploaded_files:
-            text = extract_text_from_pdf(uploaded_file)
-            course_texts.append(text)
+            # Split combined text into smaller chunks for embedding (max tokens ~1000)
+            chunks = [combined_text[i:i+1000] for i in range(0, len(combined_text), 1000)]
 
-        # Combine all course materials into one large text
-        combined_text = " ".join(course_texts)
+            # Generate embeddings for all chunks
+            embeddings = [get_embeddings(chunk) for chunk in chunks]
 
-        # Split combined text into smaller chunks for embedding (max tokens ~1000)
-        chunks = [combined_text[i:i+1000] for i in range(0, len(combined_text), 1000)]
+            # Convert the list of embeddings into a NumPy array (shape: [num_chunks, embedding_size])
+            embeddings_np = np.array(embeddings).astype("float32")
 
-        # Generate embeddings for all chunks
-        embeddings = [get_embeddings(chunk) for chunk in chunks]
+            # Create a FAISS index for similarity search
+            index = faiss.IndexFlatL2(len(embeddings_np[0]))  # Use the length of the embedding vectors for the dimension
+            index.add(embeddings_np)
 
-        # Convert the list of embeddings into a NumPy array (shape: [num_chunks, embedding_size])
-        embeddings_np = np.array(embeddings).astype("float32")
+            st.write("Course materials have been processed and indexed.")
 
-        # Create a FAISS index for similarity search
-        index = faiss.IndexFlatL2(len(embeddings_np[0]))  # Use the length of the embedding vectors for the dimension
-        index.add(embeddings_np)
+            # User query
+            query = st.text_input("Enter your question about the course materials:")
 
-        st.write("Course materials have been processed and indexed.")
+            if query:
+                # Generate embedding for the query
+                query_embedding = get_embeddings(query)
 
-        # User query
-        query = st.text_input("Enter your question about the course materials:")
+                # Search for similar chunks in the FAISS index
+                results = search_similar(query_embedding, index, chunks)
 
-        if query:
-            # Generate embedding for the query
-            query_embedding = get_embeddings(query)
+                # Create the context for the GPT prompt
+                context = "\n".join([result[0] for result in results])
+                modified_prompt = f"Context: {context}\n\nQuestion: {query}\n\nProvide a detailed answer based on the context."
 
-            # Search for similar chunks in the FAISS index
-            results = search_similar(query_embedding, index, chunks)
+                # Get the GPT-4 response
+                response = openai.ChatCompletion.create(
+                    model="gpt-4o-mini",  # Update to GPT-4 (or your desired model)
+                    messages=[{"role": "user", "content": modified_prompt}]
+                )
 
-            # Create the context for the GPT prompt
-            context = "\n".join([result[0] for result in results])
-            modified_prompt = f"Context: {context}\n\nQuestion: {query}\n\nProvide a detailed answer based on the context."
+                # Get the response content
+                response_content = response['choices'][0]['message']['content']
 
-            # Get the GPT-4 response
-            response = openai.ChatCompletion.create(
-                model="gpt-4o-mini",  # Update to GPT-4 (or your desired model)
-                messages=[{"role": "user", "content": modified_prompt}]
-            )
+                # Display the response in Streamlit (Intelligent Reply)
+                st.write("### Intelligent Reply:")
+                st.write(response_content)
 
-            # Get the response content
-            response_content = response['choices'][0]['message']['content']
+    elif mode == "Code Generator":
+        st.header("Code Generator")
 
-            # Display the response in Streamlit (Intelligent Reply)
-            st.write("### Intelligent Reply:")
-            st.write(response_content)
+        # Code generation prompt input
+        code_prompt = st.text_area("Describe the code you want to generate:", 
+                                   "e.g., Write a Python program that generates Fibonacci numbers.")
+        
+        if st.button("Generate Code"):
+            if code_prompt:
+                with st.spinner("Generating code..."):
+                    # Generate code using GPT-4
+                    generated_code = generate_code_from_prompt(code_prompt)
+                    
+                    # Display the generated code
+                    st.write("### Generated Code:")
+                    st.code(generated_code, language="python")
+            else:
+                st.error("Please provide a prompt to generate the code.")