Python Code samples related to LLMs

1. Using LLMs as Virtual Assistants for Python Development

python
import requests

class Weather:
    def __init__(self, api_key):
        self.api_key = api_key
        self.temperature = None

    def get_weather(self, city):
        url = 'https://api.openweathermap.org/data/2.5/weather'
        params = {
            'q': city,
            'appid': self.api_key,
            'units': 'imperial'  # Request temperature in Fahrenheit.
        }
        response = requests.get(url, params=params)
        data = response.json()
        if response.status_code == 200:
            self.temperature = data['main']['temp']
            print(f"The temperature in {city} is {self.temperature}°F.")
        else:
            print(f"Error: {data['message']}")

api_key = "YOUR_API_KEY"
weather = Weather(api_key)
weather.get_weather('London')

2. Practical Prompt Engineering Example

python
# Example of using a Python script to test prompt engineering techniques
# This script can be repurposed for other LLM-assisted tasks

# Example of running the script with different data
python app.py testing-chats.txt

3. Scikit-LLM Example for Text Analysis

python
# Example of using Scikit-LLM to integrate LLMs into the scikit-learn framework
# This example demonstrates how to use advanced language models like ChatGPT for text classification and other text analysis tasks

# Example of using Scikit-LLM for sentiment analysis
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

# Load the iris dataset
iris = load_iris()
X = iris.data[:, :2]  # we only take the first two features.
y = iris.target

# Split the data into a training set and a test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create a pipeline with a standard scaler and a logistic regression model
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('logreg', LogisticRegression())
])

# Train the pipeline
pipeline.fit(X_train, y_train)

# Evaluate the pipeline
y_pred = pipeline.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))

4. LLM Chain Example

python
# Example of using LangChain to create dynamic prompts and build LLM Chains with OpenAI models (ChatGPT)
# This example demonstrates how to unlock advanced NLP applications using LLM Chains

# Step 1: Define the prompt template
prompt_template = "Explain the concept of machine learning in one paragraph."

# Step 2: Format the prompt template with user input
user_input = "Machine Learning"
prompt = prompt_template.format(user_input)

# Step 3: Instantiate the LLMChain
llm_chain = LangChain(prompt_template, OpenAI(temperature=0.5))

# Step 4: Execute the LLMChain
response = llm_chain.run(prompt)

# Step 5: Print the response
print(response)

5. Fine-tuning LLMs Example

python
# Example of fine-tuning an existing LLM for a particular use case
# This example demonstrates how to fine-tune an LLM using the LoRA technique

# Step 1: Load the base model
model = DistilBERTForSequenceClassification.from_pretrained('distilbert-base-uncased')

# Step 2: Prepare the data
train_dataset = load_dataset('imdb', split='train')
test_dataset = load_dataset('imdb', split='test')

# Step 3: Define the evaluation metric
eval_metric = accuracy

# Step 4: Fine-tune the model
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
    eval_dataset=test_dataset,
    compute_metrics=compute_metrics
)

trainer.train()

# Step 5: Load the fine-tuned model
fine_tuned_model = trainer.model

These examples demonstrate various ways to integrate LLMs into Python applications, including using them as virtual assistants, fine-tuning them for specific tasks, and leveraging them for text analysis and other NLP tasks[1][2][3][4][5].