Update app.py

app.py

@@ -17,80 +17,115 @@ client = OpenAI(
     api_key=os.environ.get('HUGGINGFACEHUB_API_TOKEN')  # Replace with your token
 )
 
-# Define Llama 3 model
-model_link = "meta-llama/Meta-Llama-3-8B-Instruct"
-model_info = {
-    'description': """The Llama (3) model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n 
-                      It was created by the [**Meta's AI**](https://llama.meta.com/) team and has over **8 billion parameters.** \n""",
-    'logo': 'Llama_logo.png'
-}
-
-# Random dog images for error message
-random_dog = ["0f476473-2d8b-415e-b944-483768418a95.jpg",
-              "1bd75c81-f1d7-4e55-9310-a27595fa8762.jpg",
-              "526590d2-8817-4ff0-8c62-fdcba5306d02.jpg",
-              "1326984c-39b0-492c-a773-f120d747a7e2.jpg"]
-
+# Function to reset conversation
 def reset_conversation():
-    '''Resets Conversation'''
     st.session_state.conversation = []
     st.session_state.messages = []
     return None
 
-# Create a temperature slider
-temp_values = st.sidebar.slider('Select a temperature value', 0.0, 1.0, (0.5))
-
-# Add reset button to clear conversation
-st.sidebar.button('Reset Chat', on_click=reset_conversation)  # Reset button
-
-# Create model description
-st.sidebar.write(f"You're now chatting with **Llama 3**")
-st.sidebar.markdown(model_info['description'])
-st.sidebar.image(model_info['logo'])
-st.sidebar.markdown("*Generated content may be inaccurate or false.*")
-st.sidebar.markdown("\nRun into issues? \nTry again later as GPU access might be limited.")
-
-# Initialize chat history
-if "messages" not in st.session_state:
-    st.session_state.messages = []
+# Define classification options
+classification_types = ["Sentiment Analysis", "Binary Classification", "Multi-Class Classification"]
+
+# Start with a selection between data generation or labeling
+st.sidebar.write("Choose Task:")
+task = st.sidebar.radio("Do you want to generate data or label data?", ("Data Generation", "Data Labeling"))
+
+# If the user selects Data Labeling
+if task == "Data Labeling":
+    st.sidebar.write("Choose Classification Type:")
+    classification_type = st.sidebar.radio("Select a classification type:", classification_types)
+
+    # Handle Sentiment Analysis
+    if classification_type == "Sentiment Analysis":
+        st.sidebar.write("Classes: Positive, Negative, Neutral (fixed)")
+        class_labels = ["Positive", "Negative", "Neutral"]
+
+    # Handle Binary Classification
+    elif classification_type == "Binary Classification":
+        class_1 = st.sidebar.text_input("Enter Class 1:")
+        class_2 = st.sidebar.text_input("Enter Class 2:")
+        class_labels = [class_1, class_2]
+
+    # Handle Multi-Class Classification
+    elif classification_type == "Multi-Class Classification":
+        class_labels = []
+        for i in range(1, 11):  # Allow up to 10 classes
+            label = st.sidebar.text_input(f"Enter Class {i} (leave blank to stop):")
+            if label:
+                class_labels.append(label)
+            else:
+                break
+
+    # Domain selection
+    st.sidebar.write("Specify the Domain:")
+    domain = st.sidebar.radio("Choose a domain:", ("Restaurant Reviews", "E-commerce Reviews", "Custom"))
+    if domain == "Custom":
+        domain = st.sidebar.text_input("Enter Custom Domain:")
+
+    # Specify example length
+    st.sidebar.write("Specify the Length of Examples:")
+    min_words = st.sidebar.number_input("Minimum word count (10 to 90):", 10, 90, 10)
+    max_words = st.sidebar.number_input("Maximum word count (10 to 90):", min_words, 90, 50)
+
+    # Few-shot examples option
+    use_few_shot = st.sidebar.radio("Do you want to use few-shot examples?", ("Yes", "No"))
+    few_shot_examples = []
+    if use_few_shot == "Yes":
+        num_examples = st.sidebar.number_input("How many few-shot examples? (1 to 5)", 1, 5, 1)
+        for i in range(num_examples):
+            example_text = st.text_area(f"Enter example {i+1}:")
+            example_label = st.selectbox(f"Select the label for example {i+1}:", class_labels)
+            few_shot_examples.append({"text": example_text, "label": example_label})
+
+    # Generate the system prompt based on classification type
+    if classification_type == "Sentiment Analysis":
+        system_prompt = f"You are a propositional sentiment analysis expert. Your role is to generate sentiment analysis reviews based on the data entered and few-shot examples provided, if any, for the domain '{domain}'."
+    elif classification_type == "Binary Classification":
+        system_prompt = f"You are an expert in binary classification. Your task is to label examples for the domain '{domain}' with either '{class_1}' or '{class_2}', based on the data provided."
+    else:  # Multi-Class Classification
+        system_prompt = f"You are an expert in multi-class classification. Your role is to label examples for the domain '{domain}' using the provided class labels."
+
+    st.sidebar.write("System Prompt:")
+    st.sidebar.write(system_prompt)
+
+    # Step-by-step thinking
+    st.sidebar.write("Generated Data:")
+    st.sidebar.write("Think step by step to ensure accuracy in classification.")
+
+    # Accept user input for generating or labeling data
+    if prompt := st.chat_input(f"Hi, I'm ready to help with {classification_type} for {domain}. Ask me a question or provide data to classify."):
+
+        # Display user message in chat message container
+        with st.chat_message("user"):
+            st.markdown(prompt)
+        # Add user message to chat history
+        st.session_state.messages.append({"role": "user", "content": prompt})
+
+        # Display assistant response in chat message container
+        with st.chat_message("assistant"):
+
+            try:
+                # Stream the response from the model
+                stream = client.chat.completions.create(
+                    model="meta-llama/Meta-Llama-3-8B-Instruct",
+                    messages=[
+                        {"role": m["role"], "content": m["content"]}
+                        for m in st.session_state.messages
+                    ],
+                    temperature=0.5,
+                    stream=True,
+                    max_tokens=3000,
+                )
+
+                response = st.write_stream(stream)
+
+            except Exception as e:
+                response = "😵‍💫 Something went wrong. Try again later."
+                st.write(response)
+
+        st.session_state.messages.append({"role": "assistant", "content": response})
+
+# If the user selects Data Generation
+else:
+    st.sidebar.write("This feature will allow you to generate new data. Coming soon!")
 
-# Display chat messages from history on app rerun
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.markdown(message["content"])
-
-# Accept user input
-if prompt := st.chat_input(f"Hi, I'm Llama 3, ask me a question"):
-
-    # Display user message in chat message container
-    with st.chat_message("user"):
-        st.markdown(prompt)
-    # Add user message to chat history
-    st.session_state.messages.append({"role": "user", "content": prompt})
-
-    # Display assistant response in chat message container
-    with st.chat_message("assistant"):
-
-        try:
-            stream = client.chat.completions.create(
-                model=model_link,
-                messages=[
-                    {"role": m["role"], "content": m["content"]}
-                    for m in st.session_state.messages
-                ],
-                temperature=temp_values,
-                stream=True,
-                max_tokens=3000,
-            )
-    
-            response = st.write_stream(stream)
-
-        except Exception as e:
-            response = "😵‍💫 Looks like something went wrong! Try again later.\nHere's a random pic of a 🐶:"
-            st.write(response)
-            random_dog_pick = 'https://random.dog/' + random_dog[np.random.randint(len(random_dog))]
-            st.image(random_dog_pick)
-            st.write("This was the error message:")
-            st.write(e)
-
-    st.session_state.messages.append({"role": "assistant", "content": response})