ใช้ ai.summarize กับ PySpark

df.ai.summarize(input_col="text", output_col="summaries")

df.ai.summarize(output_col="summaries")

# This code uses AI. Always review output for mistakes.

df = spark.createDataFrame([
        ("Microsoft Teams", "2017",
        """
        The ultimate messaging app for your organization—a workspace for real-time 
        collaboration and communication, meetings, file and app sharing, and even the 
        occasional emoji! All in one place, all in the open, all accessible to everyone.
        """,),
        ("Microsoft Fabric", "2023",
        """
        An enterprise-ready, end-to-end analytics platform that unifies data movement, 
        data processing, ingestion, transformation, and report building into a seamless, 
        user-friendly SaaS experience. Transform raw data into actionable insights.
        """,)
    ], ["product", "release_year", "description"])

summaries = df.ai.summarize(input_col="description", output_col="summaries")
display(summaries)

Output:

# This code uses AI. Always review output for mistakes.

df = spark.createDataFrame([
        ("Microsoft Teams", "2017",
        """
        The ultimate messaging app for your organization—a workspace for real-time 
        collaboration and communication, meetings, file and app sharing, and even the 
        occasional emoji! All in one place, all in the open, all accessible to everyone.
        """,),
        ("Microsoft Fabric", "2023",
        """
        An enterprise-ready, end-to-end analytics platform that unifies data movement, 
        data processing, ingestion, transformation, and report building into a seamless, 
        user-friendly SaaS experience. Transform raw data into actionable insights.
        """,)
    ], ["product", "release_year", "description"])

summaries = df.ai.summarize(output_col="summaries")
display(summaries)

Output:

# This code uses AI. Always review output for mistakes.

summaries = df.ai.summarize(
    input_col="description",
    output_col="executive_summary",
    instructions="Write one concise sentence for a business executive. Focus on product value and avoid marketing language.",
)
display(summaries)

# This code uses AI. Always review output for mistakes.

summaries = df.ai.summarize(
    output_col="release_note",
    instructions="Write one sentence that includes the product name, release year, and main customer benefit.",
)
display(summaries)