Utilize a entrada multimodal com Funções de IA (Pré-visualização)

folder_path = "/lakehouse/default/Files"

folder_path = "abfss://path_to_your_lakehouse"
# or
folder_path = "Files"

df, schema = aifunc.load(folder_path)
# or
df, schema = aifunc.load(folder_path, prompt="Give me candidate's name and the most recent company they worked for.")
display(df)

df, schema = aifunc.load(folder_path)
# or
df, schema = aifunc.load(folder_path, prompt="Give me candidate's name and the most recent company they worked for.")
display(df)

file_path_series = aifunc.list_file_paths(folder_path)
df = pd.DataFrame({"file_path": file_path_series}).reset_index(drop=True)
display(df)

df = aifunc.list_file_paths(folder_path)
display(df)

Para Funções de IA ao nível de série (operando numa única coluna), defina o column_type parâmetro:

df["result"] = df["file_path"].ai.analyze_sentiment(column_type="path")

Para Funções de IA de nível DataFrame (que operam sobre várias colunas), utilize o parâmetro column_type_dict:

df["result"] = df.ai.generate_response(
    prompt="Describe the content.",
    column_type_dict={"file_path": "path"},
)

Para Funções de IA de coluna única , defina o input_col_type parâmetro:

results = df.ai.analyze_sentiment(input_col="file_path", input_col_type="path", output_col="sentiment")

Para Funções de IA de nível DataFrame (que operam sobre várias colunas), utilize o parâmetro col_types:

results = df.ai.generate_response(
    prompt="Describe the content.",
    col_types={"file_path": "path"},
    output_col="response",
)

df, schema = aifunc.load(folder_path, prompt=None, schema=None)

df, schema = aifunc.load(folder_path, prompt=None, schema=None)

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

# Basic load – let the AI infer the table structure
df, schema = aifunc.load(folder_path)
display(df)

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

# Guided load – provide a prompt to specify what to extract
guided_df, guided_schema = aifunc.load(
    folder_path,
    prompt="Give me candidate's name and the most recent company they worked for.",
)
display(guided_df)

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

# Basic load – let the AI infer the table structure
df, schema = aifunc.load(folder_path)
display(df)

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

# Guided load – provide a prompt to specify what to extract
guided_df, guided_schema = aifunc.load(
    folder_path,
    prompt="Give me candidate's name and the most recent company they worked for.",
)
display(guided_df)

file_path_series = aifunc.list_file_paths(folder_path)

file_path_df = aifunc.list_file_paths(folder_path)

Uma Série pandas de yarl.URL objetos, indexados pelas suas representações de string. Estes yarl.URL objetos são automaticamente tratados como caminhos de ficheiro pelas Funções de IA, por isso não precisa de especificar column_type="path".

Um DataFrame Spark com uma file_path coluna contendo as URLs dos ficheiros correspondentes.

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

file_path_series = aifunc.list_file_paths(folder_path)
custom_df = pd.DataFrame({"file_path": file_path_series}).reset_index(drop=True)
display(custom_df)

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

custom_df = aifunc.list_file_paths(folder_path)
display(custom_df)

schema = df["file_path"].ai.infer_schema(column_type="path")

schema = df.ai.infer_schema(input_col="file_path", input_col_type="path")

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

# Infer a schema from file contents
schema = df["file_path"].ai.infer_schema(column_type="path")
for label in schema:
    print(label)

# Use the inferred schema with ai.extract
extracted_df = df["file_path"].ai.extract(*schema, column_type="path")
display(extracted_df)

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

# Infer a schema from file contents
schema = df.ai.infer_schema(input_col="file_path", input_col_type="path")
for label in schema:
    print(label)

# Use the inferred schema with ai.extract
extracted_df = df.ai.extract(labels=schema, input_col="file_path", input_col_type="path")
display(extracted_df)

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

animal_urls = [
    "<image-url-golden-retriever>",  # Replace with URL to an image of a golden retriever
    "<image-url-giant-panda>",  # Replace with URL to an image of a giant panda
    "<image-url-bald-eagle>",  # Replace with URL to an image of a bald eagle
]
animal_df = pd.DataFrame({"file_path": animal_urls})

animal_df["sentiment"] = animal_df["file_path"].ai.analyze_sentiment(column_type="path")
display(animal_df)

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

animal_urls = [
    "<image-url-golden-retriever>",  # Replace with URL to an image of a golden retriever
    "<image-url-giant-panda>",  # Replace with URL to an image of a giant panda
    "<image-url-bald-eagle>",  # Replace with URL to an image of a bald eagle
]
animal_df = spark.createDataFrame([(u,) for u in animal_urls], ["file_path"])

results = animal_df.ai.analyze_sentiment(
    input_col="file_path",
    input_col_type="path",
    output_col="sentiment",
)
display(results)

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

custom_df["highest_degree"] = custom_df["file_path"].ai.classify(
    "Master", "PhD", "Bachelor", "Other",
    column_type="path",
)
display(custom_df)

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

results = custom_df.ai.classify(
    labels=["Master", "PhD", "Bachelor", "Other"],
    input_col="file_path",
    input_col_type="path",
    output_col="highest_degree",
)
display(results)

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

extracted = custom_df["file_path"].ai.extract(
    aifunc.ExtractLabel(
        "name",
        description="The full name of the candidate, first letter capitalized.",
        max_items=1,
    ),
    "companies_worked_for",
    aifunc.ExtractLabel(
        "year_of_experience",
        description="The total years of professional work experience the candidate has, excluding internships.",
        type="integer",
        max_items=1,
    ),
    column_type="path",
)
display(extracted)

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

extracted = custom_df.ai.extract(
    labels=[
        aifunc.ExtractLabel(
            "name",
            description="The full name of the candidate, first letter capitalized.",
            max_items=1,
        ),
        "companies_worked_for",
        aifunc.ExtractLabel(
            "year_of_experience",
            description="The total years of professional work experience the candidate has, excluding internships.",
            type="integer",
            max_items=1,
        ),
    ],
    input_col="file_path",
    input_col_type="path",
)
display(extracted)

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

custom_df["corrections"] = custom_df["file_path"].ai.fix_grammar(column_type="path")
display(custom_df)

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

results = custom_df.ai.fix_grammar(
    input_col="file_path",
    input_col_type="path",
    output_col="corrections",
)
display(results)

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

# Series-level: generate a response from each file
animal_df["animal_name"] = animal_df["file_path"].ai.generate_response(
    prompt="What type of animal is in this image? Give me only the animal's common name.",
    column_type="path",
)
display(animal_df)

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

# DataFrame-level: use all columns as context
animal_df["description"] = animal_df.ai.generate_response(
    prompt="Describe this animal's natural habitat and one interesting fact about it.",
    column_type_dict={"file_path": "path"},
)
display(animal_df)

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

# Generate a response from each file
results = animal_df.ai.generate_response(
    prompt="What type of animal is in this image? Give me only the animal's common name.",
    col_types={"file_path": "path"},
    output_col="animal_name",
)
display(results)

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

# DataFrame-level: use all columns as context
results = animal_df.ai.generate_response(
    prompt="Describe this animal's natural habitat and one interesting fact about it.",
    col_types={"file_path": "path"},
    output_col="description",
)
display(results)

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

# Summarize file content from a single column
custom_df["summary"] = custom_df["file_path"].ai.summarize(
    instructions="Summarize this file in one sentence for a support analyst.",
    column_type="path",
)
display(custom_df)

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

# Summarize file content from a single column
results = custom_df.ai.summarize(
    instructions="Summarize this file in one sentence for a support analyst.",
    input_col="file_path",
    input_col_type="path",
    output_col="summary",
)
display(results)

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

custom_df["summary"] = custom_df.ai.summarize(
    column_type_dict={"file_path": "path"},
)
display(custom_df)

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

results = custom_df.ai.summarize(
    col_types={"file_path": "path"},
    output_col="summary",
)
display(results)

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

custom_df["chinese_version"] = custom_df["file_path"].ai.translate(
    "Chinese",
    column_type="path",
)
display(custom_df)

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

results = custom_df.ai.translate(
    to_lang="Chinese",
    input_col="file_path",
    input_col_type="path",
    output_col="chinese_version",
)
display(results)