Spaces:
Sleeping
Sleeping
| import numpy as np | |
| import streamlit as st | |
| from openai import OpenAI | |
| import os | |
| from dotenv import load_dotenv | |
| import random | |
| os.environ["BROWSER_GATHERUSAGESTATS"] = "false" | |
| load_dotenv() | |
| # Initialize the client | |
| client = OpenAI( | |
| base_url="https://api-inference.huggingface.co/v1", | |
| api_key=os.environ.get('TOKEN2') # Add your Huggingface token here | |
| ) | |
| # Supported models | |
| model_links = { | |
| "Meta-Llama-3-8B": "meta-llama/Meta-Llama-3-8B-Instruct" | |
| } | |
| # Reset conversation | |
| def reset_conversation(): | |
| st.session_state.conversation = [] | |
| st.session_state.messages = [] | |
| return None | |
| # Define the available models | |
| models = [key for key in model_links.keys()] | |
| # Sidebar for model selection | |
| selected_model = st.sidebar.selectbox("Select Model", models) | |
| # Temperature slider with default adjusted for labeling consistency | |
| temp_values = st.sidebar.slider('Select a temperature value', 0.1, 1.0, 0.3) | |
| # Reset button | |
| st.sidebar.button('Reset Chat', on_click=reset_conversation) | |
| # Model description | |
| st.sidebar.write(f"You're now chatting with **{selected_model}**") | |
| st.sidebar.markdown("*Generated content may be inaccurate or false.*") | |
| # Chat initialization | |
| if "messages" not in st.session_state: | |
| st.session_state.messages = [] | |
| # Display chat messages | |
| for message in st.session_state.messages: | |
| with st.chat_message(message["role"]): | |
| st.markdown(message["content"]) | |
| # Main logic to choose between data generation and data labeling | |
| task_choice = st.selectbox("Choose Task", ["Data Generation", "Data Labeling"]) | |
| if task_choice == "Data Generation": | |
| classification_type = st.selectbox( | |
| "Choose Classification Type", | |
| ["Sentiment Analysis", "Binary Classification", "Multi-Class Classification"] | |
| ) | |
| if classification_type == "Sentiment Analysis": | |
| st.write("Sentiment Analysis: Positive, Negative, Neutral") | |
| labels = ["Positive", "Negative", "Neutral"] | |
| elif classification_type == "Binary Classification": | |
| label_1 = st.text_input("Enter first class") | |
| label_2 = st.text_input("Enter second class") | |
| labels = [label_1, label_2] | |
| elif classification_type == "Multi-Class Classification": | |
| num_classes = st.slider("How many classes?", 3, 10, 3) | |
| labels = [st.text_input(f"Class {i + 1}") for i in range(num_classes)] | |
| domain = st.selectbox("Choose Domain", ["Restaurant reviews", "E-commerce reviews", "Custom"]) | |
| if domain == "Custom": | |
| domain = st.text_input("Specify custom domain") | |
| min_words = st.number_input("Minimum words per example", min_value=10, max_value=90, value=10) | |
| max_words = st.number_input("Maximum words per example", min_value=10, max_value=90, value=90) | |
| few_shot = st.radio("Do you want to use few-shot examples?", ["Yes", "No"]) | |
| if few_shot == "Yes": | |
| num_examples = st.slider("How many few-shot examples?", 1, 5, 1) | |
| few_shot_examples = [ | |
| {"content": st.text_area(f"Example {i + 1}", key=f"few_shot_{i}"), "label": st.selectbox(f"Label for example {i + 1}", labels, key=f"label_{i}")} | |
| for i in range(num_examples) | |
| ] | |
| else: | |
| few_shot_examples = [] | |
| # Ask the user how many examples they need | |
| num_to_generate = st.number_input("How many examples to generate?", min_value=1, max_value=100, value=10) | |
| # User prompt text field | |
| user_prompt = st.text_area("Enter your prompt to guide example generation", "") | |
| # System prompt generation | |
| system_prompt = f"You are a professional {classification_type.lower()} expert. Your role is to generate data for {domain}.\n\n" | |
| if few_shot_examples: | |
| system_prompt += "Use the following few-shot examples as a reference:\n" | |
| for example in few_shot_examples: | |
| system_prompt += f"Example: {example['content']} \n Label: {example['label']}\n" | |
| system_prompt += f"Generate {num_to_generate} unique examples with diverse phrasing.\n" | |
| system_prompt += f"Each example should have between {min_words} and {max_words} words.\n" | |
| system_prompt += f"Use the labels specified: {', '.join(labels)}.\n" | |
| if user_prompt: | |
| system_prompt += f"Additional instructions: {user_prompt}\n" | |
| st.write("System Prompt:") | |
| st.code(system_prompt) | |
| if st.button("Generate Examples"): | |
| # Generate examples by concatenating all inputs and sending it to the model | |
| with st.spinner("Generating..."): | |
| st.session_state.messages.append({"role": "system", "content": system_prompt}) | |
| try: | |
| stream = client.chat_completions.create( | |
| model=model_links[selected_model], | |
| messages=[{"role": m["role"], "content": m["content"]} for m in st.session_state.messages], | |
| temperature=temp_values, | |
| stream=True, | |
| max_tokens=3000 | |
| ) | |
| response = "" | |
| for chunk in stream: | |
| response += chunk['choices'][0]['delta']['content'] | |
| st.session_state.messages.append({"role": "assistant", "content": response}) | |
| st.markdown(response) | |
| except Exception as e: | |
| st.write("Error during generation. Please try again.") | |
| st.write(e) | |
| else: | |
| # Data labeling workflow | |
| st.write("Data Labeling functionality") | |
| # Initialize session state variables for classification | |
| if "labels" not in st.session_state: | |
| st.session_state.labels = [] | |
| if "few_shot_examples" not in st.session_state: | |
| st.session_state.few_shot_examples = [] | |
| if "examples_to_classify" not in st.session_state: | |
| st.session_state.examples_to_classify = [] | |
| # Step 1: Classification Type Selection | |
| classification_type = st.selectbox("Choose Classification Type", ["Sentiment Analysis", "Binary Classification", "Multi-Class Classification"]) | |
| # Step 2: Define Labels based on Classification Type | |
| if classification_type == "Sentiment Analysis": | |
| labels = ["Positive", "Negative", "Neutral"] | |
| st.write("Sentiment Analysis labels: Positive, Negative, Neutral") | |
| elif classification_type == "Binary Classification": | |
| label_1 = st.text_input("Enter first class") | |
| label_2 = st.text_input("Enter second class") | |
| if label_1 and label_2: | |
| labels = [label_1, label_2] | |
| else: | |
| labels = [] | |
| elif classification_type is "Multi-Class Classification": | |
| num_classes = st.slider("How many classes?", 3, 10, 3) | |
| labels = [st.text_input(f"Class {i + 1}", key=f"multi_class_{i}") for i in range(num_classes)] | |
| # Save labels to session state | |
| st.session_state.labels = labels | |
| # Step 3: Few-Shot Examples | |
| use_few_shot = st.radio("Do you want to use few-shot examples?", ["Yes", "No"]) | |
| if use_few_shot == "Yes": | |
| num_examples = st.slider("How many few-shot examples?", 1, 5, 1) | |
| st.session_state.few_shot_examples |