import streamlit as st import pandas as pd import subprocess import time import random import numpy as np import tensorflow as tf from tensorflow.keras import layers, models from transformers import BertTokenizer, TFBertModel import requests import matplotlib.pyplot as plt from io import BytesIO import base64 # ---------------------------- Helper Function for NER Data ---------------------------- def generate_ner_data(): # Sample NER data for different entities data_person = [{"text": f"Person example {i}", "entities": [{"entity": "Person", "value": f"Person {i}"}]} for i in range(1, 21)] data_organization = [{"text": f"Organization example {i}", "entities": [{"entity": "Organization", "value": f"Organization {i}"}]} for i in range(1, 21)] data_location = [{"text": f"Location example {i}", "entities": [{"entity": "Location", "value": f"Location {i}"}]} for i in range(1, 21)] data_date = [{"text": f"Date example {i}", "entities": [{"entity": "Date", "value": f"Date {i}"}]} for i in range(1, 21)] data_product = [{"text": f"Product example {i}", "entities": [{"entity": "Product", "value": f"Product {i}"}]} for i in range(1, 21)] # Create a dictionary of all NER examples ner_data = { "Person": data_person, "Organization": data_organization, "Location": data_location, "Date": data_date, "Product": data_product } return ner_data # ---------------------------- Fun NER Data Function ---------------------------- def ner_demo(): st.header("๐Ÿค– LLM NER Model Demo ๐Ÿ•ต๏ธโ€โ™€๏ธ") # Generate NER data ner_data = generate_ner_data() # Pick a random entity type to display entity_type = random.choice(list(ner_data.keys())) st.subheader(f"Here comes the {entity_type} entity recognition, ready to show its magic! ๐ŸŽฉโœจ") # Select a random record to display example = random.choice(ner_data[entity_type]) st.write(f"Analyzing: *{example['text']}*") # Display recognized entity for entity in example["entities"]: st.success(f"๐Ÿ” Found a {entity['entity']}: **{entity['value']}**") # A bit of rhyme to lighten up the task st.write("There once was an AI so bright, ๐ŸŽ‡") st.write("It could spot any name in sight, ๐Ÿ‘๏ธ") st.write("With a click or a tap, it put on its cap, ๐ŸŽฉ") st.write("And found entities day or night! ๐ŸŒ™") # ---------------------------- Helper: Text Data Augmentation ---------------------------- def word_subtraction(text): """Subtract words at random positions.""" words = text.split() if len(words) > 2: index = random.randint(0, len(words) - 1) words.pop(index) return " ".join(words) def word_recombination(text): """Recombine words with random shuffling.""" words = text.split() random.shuffle(words) return " ".join(words) # ---------------------------- ML Model Building ---------------------------- def build_small_model(input_shape): model = models.Sequential() model.add(layers.Dense(64, activation='relu', input_shape=(input_shape,))) model.add(layers.Dense(32, activation='relu')) model.add(layers.Dense(1, activation='sigmoid')) model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) return model # ---------------------------- TensorFlow and Keras Integration ---------------------------- def train_model_demo(): st.header("๐Ÿงช Let's Build a Mini TensorFlow Model ๐ŸŽ“") # Generate random synthetic data for simplicity data_size = 100 X_train = np.random.rand(data_size, 10) y_train = np.random.randint(0, 2, size=data_size) st.write(f"๐Ÿš€ **Data Shape**: {X_train.shape}, with binary target labels.") # Build the model model = build_small_model(X_train.shape[1]) st.write("๐Ÿ”ง **Model Summary**:") st.text(model.summary()) # Train the model st.write("๐Ÿš€ **Training the model...**") history = model.fit(X_train, y_train, epochs=5, batch_size=16, verbose=0) # Output training results humorously st.success("๐ŸŽ‰ Training completed! The model now knows its ABCs... or 1s and 0s at least! ๐Ÿ˜‚") st.write(f"Final training loss: **{history.history['loss'][-1]:.4f}**, accuracy: **{history.history['accuracy'][-1]:.4f}**") st.write("Fun fact: This model can make predictions on binary outcomes like whether a cat will sleep or not. ๐Ÿฑ๐Ÿ’ค") # ---------------------------- Additional Useful Examples ---------------------------- def code_snippet_sharing(): st.header("๐Ÿ“ค Code Snippet Sharing with Syntax Highlighting ๐Ÿ–ฅ๏ธ") code = '''def hello_world(): print("Hello, world!")''' st.code(code, language='python') st.write("Developers often need to share code snippets. Here's how you can display code with syntax highlighting in Streamlit! ๐ŸŒˆ") def file_uploader_example(): st.header("๐Ÿ“ File Uploader Example ๐Ÿ“ค") uploaded_file = st.file_uploader("Choose a CSV file", type="csv") if uploaded_file is not None: data = pd.read_csv(uploaded_file) st.write("๐ŸŽ‰ File uploaded successfully!") st.dataframe(data.head()) st.write("Use file uploaders to allow users to bring their own data into your app! ๐Ÿ“Š") def matplotlib_plot_example(): st.header("๐Ÿ“ˆ Matplotlib Plot Example ๐Ÿ“Š") # Generate data x = np.linspace(0, 10, 100) y = np.sin(x) # Create plot fig, ax = plt.subplots() ax.plot(x, y) ax.set_title('Sine Wave') st.pyplot(fig) st.write("You can integrate Matplotlib plots directly into your Streamlit app! ๐ŸŽจ") def cache_example(): st.header("โšก Streamlit Cache Example ๐Ÿš€") @st.cache def expensive_computation(a, b): time.sleep(2) return a * b st.write("Let's compute something that takes time...") result = expensive_computation(2, 21) st.write(f"The result is {result}. But thanks to caching, it's faster the next time! โšก") # ---------------------------- Display Tweet ---------------------------- def display_tweet(): st.header("๐Ÿฆ Tweet Spotlight: TensorFlow and Transformers ๐ŸŒŸ") tweet_html = '''

Just tried integrating TensorFlow with Transformers for my latest LLM project! ๐Ÿš€ The synergy between them is incredible. TensorFlow's flexibility combined with Transformers' power boosts Generative AI capabilities to new heights! ๐Ÿ”ฅ #TensorFlow #Transformers #AI #MachineLearning

— AI Enthusiast (@ai_enthusiast) September 30, 2024
''' st.components.v1.html(tweet_html, height=300) st.write("Tweets can be embedded to showcase social proof or updates. Isn't that neat? ๐Ÿค") # ---------------------------- Header and Introduction ---------------------------- st.set_page_config(page_title="LLMs and Tiny ML Models", page_icon="๐Ÿค–", layout="wide", initial_sidebar_state="expanded") st.title("๐Ÿค–๐Ÿ“Š LLMs and Tiny ML Models with TensorFlow ๐Ÿ“Š๐Ÿค–") st.markdown("This app demonstrates how to build small TensorFlow models, solve common developer problems, and augment text data using word subtraction and recombination strategies.") st.markdown("---") # ---------------------------- Main Navigation ---------------------------- st.sidebar.title("Navigation") options = st.sidebar.radio("Go to", ['NER Demo', 'TensorFlow Model', 'Text Augmentation', 'Code Sharing', 'File Uploader', 'Matplotlib Plot', 'Streamlit Cache', 'Tweet Spotlight']) if options == 'NER Demo': if st.button('๐Ÿงช Run NER Model Demo'): ner_demo() else: st.write("Click the button above to start the AI NER magic! ๐ŸŽฉโœจ") elif options == 'TensorFlow Model': if st.button('๐Ÿš€ Build and Train a TensorFlow Model'): train_model_demo() elif options == 'Text Augmentation': st.subheader("๐ŸŽฒ Fun Text Augmentation with Random Strategies ๐ŸŽฒ") input_text = st.text_input("Enter a sentence to see some augmentation magic! โœจ", "TensorFlow is awesome!") if st.button("Subtract Random Words"): st.write(f"Original: **{input_text}**") st.write(f"Augmented: **{word_subtraction(input_text)}**") if st.button("Recombine Words"): st.write(f"Original: **{input_text}**") st.write(f"Augmented: **{word_recombination(input_text)}**") st.write("Try both and see how the magic works! ๐ŸŽฉโœจ") elif options == 'Code Sharing': code_snippet_sharing() elif options == 'File Uploader': file_uploader_example() elif options == 'Matplotlib Plot': matplotlib_plot_example() elif options == 'Streamlit Cache': cache_example() elif options == 'Tweet Spotlight': display_tweet() st.markdown("---") # ---------------------------- Footer and Additional Resources ---------------------------- st.subheader("๐Ÿ“š Additional Resources") st.markdown(""" - [Official Streamlit Documentation](https://docs.streamlit.io/) - [TensorFlow Documentation](https://www.tensorflow.org/api_docs) - [Transformers Documentation](https://huggingface.co/docs/transformers/index) - [Streamlit Cheat Sheet](https://docs.streamlit.io/library/cheatsheet) - [Matplotlib Documentation](https://matplotlib.org/stable/contents.html) """) # ---------------------------- requirements.txt ---------------------------- st.markdown(''' Reference Libraries: plaintext streamlit pandas numpy tensorflow transformers matplotlib ''')