Create app6.py

app6.py

@@ -0,0 +1,190 @@
+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('GP2_2')  # 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.")