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 = [] # Define the available models models = [key for key in model_links.keys()] # Sidebar for model selection selected_model = st.sidebar.selectbox("Select Model", models) temp_values = st.sidebar.slider('Select a temperature value', 0.0, 1.0, 0.5) st.sidebar.button('Reset Chat', on_click=reset_conversation) 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 = [] 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}"), "label": st.selectbox(f"Label for example {i+1}", labels)} for i in range(num_examples) ] else: few_shot_examples = [] num_to_generate = st.number_input("How many examples to generate?", min_value=1, max_value=100, value=10) 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"): 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 = st.write_stream(stream) except Exception as e: st.error("An error occurred during generation.") st.error(f"Error details: {str(e)}") st.session_state.messages.append({"role": "assistant", "content": response}) else: # Data Labeling Process labeling_classification_type = st.selectbox( "Choose Classification Type for Labeling", ["Sentiment Analysis", "Binary Classification", "Multi-Class Classification"] ) if labeling_classification_type == "Sentiment Analysis": st.write("Sentiment Analysis: Positive, Negative, Neutral") labeling_labels = ["Positive", "Negative", "Neutral"] elif labeling_classification_type == "Binary Classification": labeling_label_1 = st.text_input("Enter first class for labeling") labeling_label_2 = st.text_input("Enter second class for labeling") labeling_labels = [labeling_label_1, labeling_label_2] elif labeling_classification_type == "Multi-Class Classification": labeling_num_classes = st.slider("How many classes for labeling?", 3, 10, 3) labeling_labels = [st.text_input(f"Labeling Class {i+1}") for i in range(labeling_num_classes)] labeling_few_shot = st.radio("Do you want to add few-shot examples for labeling?", ["Yes", "No"]) if labeling_few_shot == "Yes": labeling_num_examples = st.slider("How many few-shot examples for labeling?", 1, 5, 1) labeling_few_shot_examples = [ {"content": st.text_area(f"Labeling Example {i+1}"), "label": st.selectbox(f"Label for labeling example {i+1}", labeling_labels)} for i in range(labeling_num_examples) ] else: labeling_few_shot_examples = [] text_to_classify = st.text_area("Enter text to classify") if st.button("Classify Text"): if text_to_classify: labeling_system_prompt = ( f"You are a professional {labeling_classification_type.lower()} expert. " f"Classify the following text using these labels: {', '.join(labeling_labels)}.\n\n" ) if labeling_few_shot_examples: labeling_system_prompt += "Here are some example classifications:\n" for example in labeling_few_shot_examples: labeling_system_prompt += f"Review: {example['content']}\nLabel: {example['label']}\n\n" labeling_system_prompt += ( f"Text to classify: {text_to_classify}\n" f"Provide only the classification result in this format:\n" f"'Review: [text provided] Label: [appropriate label]'\n" ) with st.spinner("Classifying..."): st.session_state.messages.append({"role": "system", "content": labeling_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=1000, ) response = st.write_stream(stream) except Exception as e: st.error("An error occurred during classification.") st.error(f"Error details: {str(e)}") st.session_state.messages.append({"role": "assistant", "content": response}) else: st.warning("Please enter text to classify.")