Utiliser une entrée multimodale avec AI Functions (préversion)

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)

Pour les fonctions IA de niveau série (fonctionnant sur une seule colonne), définissez le column_type paramètre :

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

Pour les fonctions IA au niveau dataFrame (fonctionnant sur plusieurs colonnes), utilisez le column_type_dict paramètre :

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

Pour les fonctions IA à colonne unique , définissez le input_col_type paramètre :

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

Pour les fonctions IA au niveau dataFrame (fonctionnant sur plusieurs colonnes), utilisez le col_types paramètre :

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)

Une série pandas d’objets, indexée par leur représentation sous forme de yarl.URL chaîne. Ces yarl.URL objets sont automatiquement traités comme des chemins d’accès de fichiers par AI Functions. Vous n’avez donc pas besoin de spécifier column_type="path".

DataFrame Spark avec une file_path colonne contenant les URL des fichiers correspondants.

# 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)