Extraire des données structurées à l'aide d'appels de fonction

Afficher dans l'IA de Google Exécuter dans Google Colab Afficher la source sur GitHub

Dans ce tutoriel, vous allez utiliser un exemple d'extraction de données structurées à l'aide de l'API Gemini pour extraire les listes de personnages, de relations, d'objets et de lieux d'une histoire.

Préparation

pip install -U -q google-generativeai
import pathlib
import textwrap

import google.generativeai as genai
import google.ai.generativelanguage as glm


from IPython.display import display
from IPython.display import Markdown

from google.api_core import retry

def to_markdown(text):
  text = text.replace('•', '  *')
  return Markdown(textwrap.indent(text, '> ', predicate=lambda _: True))

Une fois la clé API obtenue, transmettez-la au SDK. Pour cela, vous avez le choix entre deux méthodes :

  • Placez la clé dans la variable d'environnement GOOGLE_API_KEY (le SDK la récupérera automatiquement à partir de là).
  • Transmettre la clé à genai.configure(api_key=...)
try:
    # Used to securely store your API key
    from google.colab import userdata

    # Or use `os.getenv('API_KEY')` to fetch an environment variable.
    GOOGLE_API_KEY=userdata.get('GOOGLE_API_KEY')
except ImportError:
    import os
    GOOGLE_API_KEY = os.environ['GOOGLE_API_KEY']

genai.configure(api_key=GOOGLE_API_KEY)

Exemple de tâche

Pour ce tutoriel, vous allez extraire des entités d'histoires en langage naturel. À titre d'exemple, vous trouverez ci-dessous un récit écrit par Gemini.

new_story = False

if new_story:
  model = genai.GenerativeModel(model_name='models/gemini-1.5-pro-latest')

  response = model.generate_content("""
      Write a long story about a girl with magic backpack, her family, and at
      least one other charater. Make sure everyone has names. Don't forget to
      describe the contents of the backpack, and where everyone and everything
      starts and ends up.""", request_options={'retry': retry.Retry()})
  story = response.text
  print(response.candidates[0].citation_metadata)
else:
  story = """In the quaint town of Willow Creek, nestled amidst rolling hills and whispering willows, resided a young girl named Anya. As she stepped out of the creaky wooden door of her modest cottage, her heart skipped a beat with excitement and anticipation. Today was her first day of school, and she couldn't wait to show off her prized possession - a magical backpack.\n\nHanded down to her from her grandmother, the backpack was no ordinary satchel. Its soft, emerald-green fabric shimmered with an ethereal glow, and its leather straps held secrets that only Anya knew. Within its capacious interior lay an enchanted world, filled with wonders that would ignite her imagination and change her life forever.\n\nAnya's parents, kind-hearted Elise and wise-bearded Edward, bid her farewell with warm embraces. "Remember, my dear," whispered her mother, "use your magic wisely and for good." Her father added, "Always seek knowledge, and let the backpack be your trusted companion."\n\nWith a skip in her step, Anya set off towards the town's only schoolhouse. On her way, she passed her best friend, Samuel, a curious and adventurous boy with a mischievous grin. "Hey, Anya," he called out. "Can I see your backpack?"\n\nAnya hesitated for a moment before unzipping the flap and revealing its contents. Samuel's eyes widened in amazement as he peered inside. There, nestled amidst pencils and notebooks, were a shimmering sword, a book of ancient spells, a tiny compass that always pointed north, and a magical key that could open any lock.\n\nTogether, they marveled at the backpack's wonders, promising to keep its secrets safe. As they approached the schoolhouse, Anya noticed a group of older children huddled together, their faces etched with fear. Curiosity getting the better of her, she cautiously approached.\n\n"What's wrong?" she asked.\n\nA tall, lanky boy stepped forward. "There's a monster in the forest," he stammered. "It's been terrorizing the town, attacking animals and even people."\n\nAnya's heart sank. The town of Willow Creek was small and peaceful, and the thought of a monster brought a shiver down her spine. She knew she had to do something to protect her family and friends.\n\nWithout a moment's hesitation, Anya opened her backpack and retrieved the shimmering sword. With a determined gleam in her eye, she turned to her terrified peers. "Don't worry," she said, her voice steady. "I'll take care of it."\n\nWith Samuel close behind her, Anya ventured into the shadowy depths of the forest. The trees seemed to whisper secrets as she passed, and the undergrowth rustled with unseen creatures. As they walked deeper into the forest, the air grew heavy and the ground beneath their feet trembled.\n\nSuddenly, they came to a clearing, and there before their eyes was the monster - a massive beast with sharp teeth, glowing red eyes, and claws that could crush a human with ease. The creature roared, a thunderous sound that shook the forest to its core.\n\nFear surged through Anya, but she refused to let it consume her. She drew the sword from its sheath and charged towards the monster. The blade shimmered in the sunlight, and as it struck the beast's hide, a blinding light erupted, enveloping everything in its radiance.\n\nWhen the light faded, the monster was gone, and in its place was a pile of shattered crystals. Anya had defeated the creature with the magic of her backpack, proving that even the smallest of objects could hold the greatest of powers.\n\nAs she and Samuel returned to the town, they were greeted as heroes. The people of Willow Creek rejoiced, and the legend of Anya, the girl with the magic backpack, was passed down through generations. And so, Anya continued her adventures, using the backpack's wonders to make the world a better place, one magical step at a time."""
to_markdown(story)

Dans la ville pittoresque de Willow Creek, nichée au milieu des collines et des saules chuchotants, vivait une jeune fille nommée Anya. Alors qu'elle sortait de la porte en bois grinçante de sa petite maison, son cœur battait un battement d'enthousiasme et d'impatience. Aujourd'hui, c'était son premier jour d'école et elle avait hâte de montrer son bien précieux : un sac à dos magique.

Remis à sa grand-mère, le sac à dos n'était pas une sacoche ordinaire. Son tissu doux d'un vert émeraude scintillait d'un éclat éthéré, et ses bracelets en cuir renfermaient des secrets que seule Anya connaissait. Au sein de son vaste intérieur se trouvait un monde enchanté, rempli de merveilles qui stimuleraient son imagination et changeaient sa vie à jamais.

Les parents d'Anya, la bienveillante Elise et Edward à la barbe sage, lui dire au revoir par des étreintes chaleureuses. "Souviens-toi, ma chérie", chuchote sa mère, "utilise ta magie à bon escient et pour de bon." Son père ajoute : "Recherchez toujours la connaissance et laissez votre sac à dos votre compagnon de confiance."

Sablée dans son pas, Anya se dirige vers l'unique école de la ville. Sur son chemin, elle passe devant son meilleur ami, Samuel, un garçon curieux et audacieux au sourire malicieux. "Salut Anya", s'exclame-t-il. "Puis-je voir votre sac à dos ?"

Anya a hésité un moment avant de décompresser le rabat et d'en révéler le contenu. Les yeux de Samuel s'élargit de joie en regardant à l'intérieur. Là, nichée entre des crayons et des carnets, il y avait une épée scintillante, un livre de sortilèges antiques, une petite boussole pointant toujours vers le nord et une clé magique pouvant ouvrir n'importe quelle serrure.

Ensemble, ils se sont émerveillés des merveilles du sac à dos et s'est engagé à garder ses secrets en sécurité. En s'approchant de l'école, Anya remarque un groupe d'enfants plus âgés recroquevillés, le visage gravé de peur. La curiosité se perfectionnant, elle s'est approchée avec précaution.

« Qu'est-ce qui ne va pas ? » a-t-elle demandé.

Un garçon grand et dénudé s'avança. "Il y a un monstre dans la forêt", balbutie-t-il. "Ça a terrorisé la ville, les animaux et même les gens."

Le cœur d'Anya a craqué. La ville de Willow Creek était petite et paisible, et la pensée d'un monstre lui donnait un frisson. Elle savait qu'elle devait faire quelque chose pour protéger sa famille et ses amis.

Sans une hésitation, Anya ouvrit son sac à dos et s'empare de l'épée scintillante. Avec un éclat déterminé dans les yeux, elle se tourna vers ses pairs terrifiés. "Ne t'inquiète pas", dit-elle, le ton immobile. "Je m'en occuperai."

Avec Samuel à proximité derrière elle, Anya s'est lancée dans les profondeurs sombres de la forêt. Les arbres semblaient chuchoter ses secrets à mesure qu'elle passait, et les sous-bois bruyaient avec des créatures inconnues. Alors qu'ils entraient encore plus profondément dans la forêt, l'air devenait lourd et le sol sous leurs pieds tremblait.

Soudain, ils arrivaient dans une clairière où se trouvait le monstre sous leurs yeux. C'était une bête énorme, dotée de dents acérées, d'yeux rouges lumineux et de griffes capables d'écraser facilement un humain. La créature rugira, au son d'un ton irrésistible qui secoua le cœur de la forêt.

La peur s'est répandue dans Anya, mais elle a refusé que celle-ci la consomme. Elle tire l'épée de son fourreau et charge en direction du monstre. La pale scintillait à la lumière du soleil, et alors qu'elle frappait la peau de la bête, une lumière aveugle éclata, recouvrant tout dans son éclat.

Lorsque la lumière s'estompe, le monstre a disparu et a été remplacé par une pile de cristaux brisés. Anya avait défait cette créature avec la magie de son sac à dos, prouvant ainsi que même les plus petits objets pouvaient contenir les plus grands pouvoirs.

À leur retour, Samuel et elle sont accueillis comme des héros. Les habitants de Willow Creek se sont réjouis et la légende d'Anya, la fille du sac à dos magique, a été transmise de génération en génération. C'est ainsi qu'Anya a continué ses aventures, en utilisant les merveilles du sac à dos pour rendre le monde meilleur, pas par la magie.

Utiliser Natural Language

Les grands modèles de langage sont de puissants outils multitâches. Souvent, vous pouvez simplement demander à Gemini ce que vous voulez, et cela ira bien.

L'API Gemini n'utilise pas de mode JSON. Vous devez donc être attentif à certains points lorsque vous générez des structures de données de cette manière:

  • Il arrive que l'analyse échoue.
  • Le schéma ne peut pas être strictement appliqué.

Vous les résoudrez dans la section suivante. Tout d'abord, essayez une requête simple en langage naturel avec le schéma écrit sous forme de texte. Ceci n'a pas été optimisé:

model = model = model = genai.GenerativeModel(
    model_name='models/gemini-1.5-pro-latest')

response = model.generate_content(
  textwrap.dedent("""\
    Please return JSON describing the the people, places, things and relationships from this story using the following schema:

    {"people": list[PERSON], "places":list[PLACE], "things":list[THING], "relationships": list[RELATIONSHIP]}

    PERSON = {"name": str, "description": str, "start_place_name": str, "end_place_name": str}
    PLACE = {"name": str, "description": str}
    THING = {"name": str, "description": str, "start_place_name": str, "end_place_name": str}
    RELATIONSHIP = {"person_1_name": str, "person_2_name": str, "relationship": str}

    All fields are required.

    Important: Only return a single piece of valid JSON text.

    Here is the story:

    """) + story,
  generation_config={'response_mime_type':'application/json'}
)
response.text
'{"people": [\n    {\n        "name": "Anya",\n        "description": "A young girl who lives in the town of Willow Creek with her parents, Elise and Edward. She possesses a magical backpack that was handed down to her from her grandmother.",\n        "start_place_name": "Willow Creek",\n        "end_place_name": "Willow Creek"\n    },\n    {\n        "name": "Elise",\n        "description": "Anya\'s kind-hearted mother",\n        "start_place_name": "Willow Creek",\n        "end_place_name": "Willow Creek"\n    },\n    {\n        "name": "Edward",\n        "description": "Anya\'s wise-bearded father",\n        "start_place_name": "Willow Creek",\n        "end_place_name": "Willow Creek"\n    },\n    {\n        "name": "Samuel",\n        "description": "Anya\'s best friend, a curious and adventurous boy with a mischievous grin.",\n        "start_place_name": "Willow Creek",\n        "end_place_name": "Willow Creek"\n    },\n    {\n        "name": "Monster",\n        "description": "A massive beast with sharp teeth, glowing red eyes, and claws that could crush a human with ease.",\n        "start_place_name": "Forest",\n        "end_place_name": "Forest"\n    }\n], "places": [\n    {\n        "name": "Willow Creek",\n        "description": "A quaint town nestled amidst rolling hills and whispering willows."\n    },\n    {\n        "name": "Forest",\n        "description": "A shadowy place with rustling undergrowth and whispering trees."\n    },\n    {\n        "name": "Schoolhouse",\n        "description": "The only school in the town of Willow Creek."\n    },\n    {\n        "name": "Anya\'s home",\n        "description": "A modest cottage with a creaky wooden door."\n    }\n], "things": [\n    {\n        "name": "Magic backpack",\n        "description": "A magical backpack that was handed down to Anya from her grandmother. Its soft, emerald-green fabric shimmered with an ethereal glow, and its leather straps held secrets that only Anya knew.",\n        "start_place_name": "Anya\'s home",\n        "end_place_name": "Forest"\n    },\n    {\n        "name": "Shimmering sword",\n        "description": "A sword that shimmered in the sunlight and could strike with blinding light.",\n        "start_place_name": "Magic backpack",\n        "end_place_name": "Forest"\n    },\n    {\n        "name": "Book of ancient spells",\n        "description": "A book that contained ancient spells.",\n        "start_place_name": "Magic backpack",\n        "end_place_name": "Forest"\n    },\n    {\n        "name": "Tiny compass",\n        "description": "A compass that always pointed north.",\n        "start_place_name": "Magic backpack",\n        "end_place_name": "Forest"\n    },\n    {\n        "name": "Magical key",\n        "description": "A key that could open any lock.",\n        "start_place_name": "Magic backpack",\n        "end_place_name": "Forest"\n    },\n    {\n        "name": "Shattered crystals",\n        "description": "The remains of the monster after it was defeated by Anya\'s magic backpack.",\n        "start_place_name": "Forest",\n        "end_place_name": "Forest"\n    }\n], "relationships": [\n    {\n        "person_1_name": "Anya",\n        "person_2_name": "Elise",\n        "relationship": "mother-daughter"\n    },\n    {\n        "person_1_name": "Anya",\n        "person_2_name": "Edward",\n        "relationship": "father-daughter"\n    },\n    {\n        "person_1_name": "Anya",\n        "person_2_name": "Samuel",\n        "relationship": "best friends"\n    }\n]}'

Cela a renvoyé une chaîne json. Essayez de l'analyser:

import json

print(json.dumps(json.loads(response.text), indent=4))
{
    "people": [
        {
            "name": "Anya",
            "description": "A young girl who lives in the town of Willow Creek with her parents, Elise and Edward. She possesses a magical backpack that was handed down to her from her grandmother.",
            "start_place_name": "Willow Creek",
            "end_place_name": "Willow Creek"
        },
        {
            "name": "Elise",
            "description": "Anya's kind-hearted mother",
            "start_place_name": "Willow Creek",
            "end_place_name": "Willow Creek"
        },
        {
            "name": "Edward",
            "description": "Anya's wise-bearded father",
            "start_place_name": "Willow Creek",
            "end_place_name": "Willow Creek"
        },
        {
            "name": "Samuel",
            "description": "Anya's best friend, a curious and adventurous boy with a mischievous grin.",
            "start_place_name": "Willow Creek",
            "end_place_name": "Willow Creek"
        },
        {
            "name": "Monster",
            "description": "A massive beast with sharp teeth, glowing red eyes, and claws that could crush a human with ease.",
            "start_place_name": "Forest",
            "end_place_name": "Forest"
        }
    ],
    "places": [
        {
            "name": "Willow Creek",
            "description": "A quaint town nestled amidst rolling hills and whispering willows."
        },
        {
            "name": "Forest",
            "description": "A shadowy place with rustling undergrowth and whispering trees."
        },
        {
            "name": "Schoolhouse",
            "description": "The only school in the town of Willow Creek."
        },
        {
            "name": "Anya's home",
            "description": "A modest cottage with a creaky wooden door."
        }
    ],
    "things": [
        {
            "name": "Magic backpack",
            "description": "A magical backpack that was handed down to Anya from her grandmother. Its soft, emerald-green fabric shimmered with an ethereal glow, and its leather straps held secrets that only Anya knew.",
            "start_place_name": "Anya's home",
            "end_place_name": "Forest"
        },
        {
            "name": "Shimmering sword",
            "description": "A sword that shimmered in the sunlight and could strike with blinding light.",
            "start_place_name": "Magic backpack",
            "end_place_name": "Forest"
        },
        {
            "name": "Book of ancient spells",
            "description": "A book that contained ancient spells.",
            "start_place_name": "Magic backpack",
            "end_place_name": "Forest"
        },
        {
            "name": "Tiny compass",
            "description": "A compass that always pointed north.",
            "start_place_name": "Magic backpack",
            "end_place_name": "Forest"
        },
        {
            "name": "Magical key",
            "description": "A key that could open any lock.",
            "start_place_name": "Magic backpack",
            "end_place_name": "Forest"
        },
        {
            "name": "Shattered crystals",
            "description": "The remains of the monster after it was defeated by Anya's magic backpack.",
            "start_place_name": "Forest",
            "end_place_name": "Forest"
        }
    ],
    "relationships": [
        {
            "person_1_name": "Anya",
            "person_2_name": "Elise",
            "relationship": "mother-daughter"
        },
        {
            "person_1_name": "Anya",
            "person_2_name": "Edward",
            "relationship": "father-daughter"
        },
        {
            "person_1_name": "Anya",
            "person_2_name": "Samuel",
            "relationship": "best friends"
        }
    ]
}

Cette méthode est relativement simple et fonctionne souvent, mais vous pouvez potentiellement la rendre plus stricte/plus robuste en définissant le schéma à l'aide de la fonctionnalité d'appel de fonction de l'API.

Utiliser l'appel de fonction

Si vous n'avez pas encore suivi le tutoriel Appels de fonctions - Principes de base, faites-le en premier.

Lorsque vous appelez votre fonction et ses paramètres, ils sont décrits dans l'API en tant que glm.FunctionDeclaration. Dans les cas basiques, le SDK peut créer le FunctionDeclaration à partir de la fonction et de ses annotations. Actuellement, le SDK ne gère pas la description des paramètres OBJECT imbriqués (dict). Vous devrez donc les définir explicitement, pour l'instant.

Définir le schéma

Commencez par définir person en tant qu'objet avec les champs de chaîne name, description, start_place_name et end_place_name.

person = glm.Schema(
    type = glm.Type.OBJECT,
    properties = {
        'name':  glm.Schema(type=glm.Type.STRING),
        'description':  glm.Schema(type=glm.Type.STRING),
        'start_place_name': glm.Schema(type=glm.Type.STRING),
        'end_place_name': glm.Schema(type=glm.Type.STRING)
    },
    required=['name', 'description', 'start_place_name', 'end_place_name']
)

Définissez ensuite des personnes comme ARRAY d'objets person:

people = glm.Schema(
    type=glm.Type.ARRAY,
    items=person
)

Procédez de la même manière pour chacune des entités que vous essayez d'extraire:

place = glm.Schema(
    type = glm.Type.OBJECT,
    properties = {
        'name':  glm.Schema(type=glm.Type.STRING),
        'description':  glm.Schema(type=glm.Type.STRING),
    }
)

places = glm.Schema(
    type=glm.Type.ARRAY,
    items=place
)
thing = glm.Schema(
  type = glm.Type.OBJECT,
  properties = {
      'name':  glm.Schema(type=glm.Type.STRING),
      'description':  glm.Schema(type=glm.Type.STRING),
  }
)

things = glm.Schema(
    type=glm.Type.ARRAY,
    items=thing
)
relationship = glm.Schema(
    type = glm.Type.OBJECT,
    properties = {
        'person_1_name':  glm.Schema(type=glm.Type.STRING),
        'person_2_name':  glm.Schema(type=glm.Type.STRING),
        'relationship':  glm.Schema(type=glm.Type.STRING),
    }
)

relationships = glm.Schema(
    type=glm.Type.ARRAY,
    items=relationship
)

Compilez maintenant FunctionDeclaration:

add_to_database = glm.FunctionDeclaration(
    name="add_to_database",
    description=textwrap.dedent("""\
        Adds entities to the database.
        """),
    parameters=glm.Schema(
        type=glm.Type.OBJECT,
        properties = {
            'people': people,
            'places': places,
            'things': things,
            'relationships': relationships
        }
    )
)

Appeler l'API

Comme nous l'avons vu dans la section Principes de base des appels de fonctions, vous pouvez désormais transmettre ce FunctionDeclaration à l'argument tools du constructeur genai.GenerativeModel (le constructeur accepterait également une représentation JSON équivalente de la déclaration de la fonction):

model = model = genai.GenerativeModel(
    model_name='models/gemini-1.5-pro-latest',
    tools = [add_to_database])

Chaque fois que vous appelez l'API, le SDK envoie les outils avec votre requête, et le modèle doit appeler la fonction que vous avez définie:

result = model.generate_content(f"""
Please add the people, places, things, and relationships from this story to the database:

{story}
""",
# Force a function call
tool_config={'function_calling_config':'ANY'})

Il n'y a plus de texte à analyser. Le résultat est une structure de données.

'text' in result.candidates[0].content.parts[0]
False
'function_call' in result.candidates[0].content.parts[0]
True
fc = result.candidates[0].content.parts[0].function_call
print(type(fc))
<class 'google.ai.generativelanguage_v1beta.types.content.FunctionCall'>

La classe glm.FunctionCall est basée sur Google Protocol Buffers. Convertissez-la en un objet compatible JSON plus familier:

print(json.dumps(type(fc).to_dict(fc), indent=4))
{
    "name": "add_to_database",
    "args": {
        "things": [
            {
                "name": "Magical Backpack",
                "description": "Anya's prized possession, the Magical Backpack, is no ordinary satchel. Its soft, emerald-green fabric shimmers with an ethereal glow, and its leather straps have secrets that only Anya knows. Within its capacious interior lay an enchanted world, filled with wonders that would ignite her imagination and change her life forever."
            },
            {
                "name": "Shimmering Sword",
                "description": "Among the wonders in Anya's Magical Backpack, lies a shimmering sword. With a determined gleam in her eye, she retrieved the shimmering sword and charged towards the monster."
            },
            {
                "description": "Residing within the Magical Backpack, the Book of Ancient Spells holds secrets untold.",
                "name": "Book of Ancient Spells"
            },
            {
                "description": "Tucked away in the Magical Backpack is a tiny compass that always points north.",
                "name": "Tiny Compass that Always Points North"
            },
            {
                "description": "Hidden within the Magical Backpack is a magical key that can open any lock.",
                "name": "Magical Key that Can Open Any Lock"
            }
        ],
        "relationships": [
            {
                "relationship": "Mother-Daughter",
                "person_1_name": "Anya",
                "person_2_name": "Elise"
            },
            {
                "person_2_name": "Edward",
                "relationship": "Father-Daughter",
                "person_1_name": "Anya"
            },
            {
                "person_2_name": "Samuel",
                "person_1_name": "Anya",
                "relationship": "Best Friends"
            }
        ],
        "people": [
            {
                "name": "Anya",
                "description": "Anya, the main character of the story, is a young girl with a magical backpack.",
                "start_place_name": "Willow Creek",
                "end_place_name": "Unknown"
            },
            {
                "name": "Elise",
                "description": "Anya's mother, Elise is a kind-hearted woman.",
                "end_place_name": "Unknown",
                "start_place_name": "Willow Creek"
            },
            {
                "start_place_name": "Willow Creek",
                "end_place_name": "Unknown",
                "name": "Edward",
                "description": "Anya's father, Edward is a wise-bearded man."
            },
            {
                "end_place_name": "Unknown",
                "start_place_name": "Willow Creek",
                "description": "Anya's best friend, Samuel is a curious and adventurous boy with a mischievous grin.",
                "name": "Samuel"
            }
        ],
        "places": [
            {
                "description": "The quaint town of Willow Creek is nestled amidst rolling hills and whispering willows.",
                "name": "Willow Creek"
            },
            {
                "description": "The town's only schoolhouse.",
                "name": "Schoolhouse"
            },
            {
                "description": "A shadowy place filled with secrets and dangers, the Forest is home to a terrifying monster.",
                "name": "Forest"
            }
        ]
    }
}

Conclusion

Bien que l'API puisse gérer les problèmes d'extraction de données structurées avec des entrées et des sorties de texte purs, l'appel de fonction est probablement plus fiable, car il vous permet de définir un schéma strict et élimine une étape d'analyse potentiellement source d'erreurs.