วิธีใช้ LLM สรุปเนื้อหาใน Scikit-Learn Pipelines ด้วย Scikit-LLM

!pip install scikit-llm -q

from google.colab import userdata
from skllm.config import SKLLMConfig
 
# Retrieving API key and routing to Groq's free-tier OpenAI-compatible endpoint
groq_key = userdata.get('GROQ_API_KEY')
SKLLMConfig.set_gpt_url("https://api.groq.com/openai/v1")
SKLLMConfig.set_openai_key(groq_key)

# Raw, lengthy documents and their corresponding class labels
X_long_texts = [
    "The new solar panel technology efficiency has increased by 15% due to the novel perovskite layer, significantly lowering the barrier to entry for residential use and driving green energy adoption by making installations cheaper and faster than ever before.",
    "Financial markets saw a sharp downturn today following the central bank's unexpected interest rate hike, leading to massive sell-offs in the tech sector and triggering volatility indices to reach their highest points in over three years.",
    "The clinical trial for the new arthritis medication showed promising results, reducing joint swelling by 40% in the control group without severe side effects, awaiting FDA approval which could bring relief to millions suffering from autoimmune disorders."
]
 
y_labels = ["Energy", "Finance", "Healthcare"]

from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from skllm.models.gpt.text2text.summarization import GPTSummarizer
 
# THREE-STEP MACHINE LEARNING PIPELINE FOR TEXT CLASSIFICATION, PRECEDED BY SUMMARIZATION
text_pipeline = Pipeline([
    ('summarizer', GPTSummarizer(
        model="custom_url::openai/gpt-oss-20b",
        max_words=20
    )),
    ('vectorizer', TfidfVectorizer()),
    ('classifier', LogisticRegression())
])
 
# Fitting the entire pipeline end-to-end
text_pipeline.fit(X_long_texts, y_labels)

# Inspecting the summaries of "training" examples, accessing the 'summarizer' object
train_summaries = text_pipeline.named_steps['summarizer'].transform(X_long_texts)
 
print("--- TRAINING DATA SUMMARIES ---")
for label, original, summary in zip(y_labels, X_long_texts, train_summaries):
    print(f"[{label.upper()}]\nOriginal: {original}\nSummary:  {summary}\n")

--- TRAINING DATA SUMMARIES ---
[ENERGY]
Original: The new solar panel technology efficiency has increased by 15% due to the novel perovskite layer, significantly lowering the barrier to entry for residential use and driving green energy adoption...
Summary:  New perovskite solar panels boost efficiency by 15%, reducing costs and accelerating residential green energy adoption.
 
[FINANCE]
Original: Financial markets saw a sharp downturn today following the central bank's unexpected interest rate hike, leading to massive sell-offs in the tech sector and triggering volatility indices...
Summary:  Markets plunged after unexpected rate hike, causing tech sell‑offs and high volatility.
 
[HEALTHCARE]
Original: The clinical trial for the new arthritis medication showed promising results, reducing joint swelling by 40% in the control group without severe side effects, awaiting FDA approval...
Summary:  New arthritis drug trial reduces swelling by 40% with no severe side effects, pending FDA approval.

X_new = [
    "A breakthrough mRNA vaccine targeting seasonal flu strains showed 85% efficacy across diverse patient demographics in stage 3 clinical trials, paving the way for a more robust global immune defense next winter.",
    "Researchers have developed a grid-scale sodium-ion battery that promises to store surplus wind and solar power at a fraction of lithium's cost, potentially resolving the intermittency issue of renewables.",
    "Stocks rallied in late trading as technology shares recovered from yesterday's losses, driven by strong earnings reports from major semiconductor manufacturers and optimistic GDP growth forecasts."
]
 
# The pipeline automatically summarizes, vectorizes, and classifies the unseen text
predictions = text_pipeline.predict(X_new)
 
# Access the intermediate summaries for the unseen data to display them
new_summaries = text_pipeline.named_steps['summarizer'].transform(X_new)
 
print("\n--- UNSEEN DATA PREDICTIONS ---")
for text, summary, prediction in zip(X_new, new_summaries, predictions):
    print(f"Original Document: '{text}'")
    print(f"Intermediate Summary: '{summary}'")
    print(f"Final Predicted Category: {prediction}\n" + "-" * 70)

--- UNSEEN DATA PREDICTIONS ---
Original Document: 'A breakthrough mRNA vaccine targeting seasonal flu strains showed 85% efficacy across diverse patient demographics in stage 3 clinical trials, paving the way for a more robust global immune defense next winter.'
Intermediate Summary: 'New mRNA flu vaccine achieved 85% efficacy in diverse patients, promising stronger global immunity next winter.'
Final Predicted Category: Healthcare
----------------------------------------------------------------------
Original Document: 'Researchers have developed a grid-scale sodium-ion battery that promises to store surplus wind and solar power at a fraction of lithium's cost, potentially resolving the intermittency issue of renewables.'
Intermediate Summary: 'New grid‑scale sodium‑ion battery can store excess wind/solar power cheaply, easing renewable intermittency.'
Final Predicted Category: Energy
----------------------------------------------------------------------
Original Document: 'Stocks rallied in late trading as technology shares recovered from yesterday's losses, driven by strong earnings reports from major semiconductor manufacturers and optimistic GDP growth forecasts.'
Intermediate Summary: 'Tech stocks rebound late, fueled by strong semiconductor earnings and hopeful GDP growth, boosting overall market rally.'
Final Predicted Category: Finance
----------------------------------------------------------------------