Guide de démarrage rapide RAG

Cette page vous explique comment utiliser le SDK Vertex AI pour exécuter des tâches du moteur RAG de Vertex AI.

Vous pouvez également suivre avec le notebook Présentation du moteur RAG de Vertex AI.

Rôles requis

Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/aiplatform.user 

gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE

Replace the following:

  • PROJECT_ID: Your project ID.
  • USER_IDENTIFIER: The identifier for your user account. For example, myemail@example.com.
  • ROLE: The IAM role that you grant to your user account.

Préparer votre console Google Cloud

Pour utiliser le moteur RAG de Vertex AI, procédez comme suit :

  1. Installez le SDK Vertex AI pour Python.

  2. Exécutez cette commande dans la console Google Cloud pour configurer votre projet.

    gcloud config set project {project}

  3. Exécutez cette commande pour autoriser votre connexion.

    gcloud auth application-default login

Exécuter le moteur RAG de Vertex AI

Copiez et collez cet exemple de code dans la console Google Cloud pour exécuter le moteur RAG de Vertex AI.

Python

Pour savoir comment installer ou mettre à jour le SDK Vertex AI pour Python, consultez Installer le SDK Vertex AI pour Python. Pour en savoir plus, consultez la documentation de référence de l'API Python. 

from vertexai import rag
from vertexai.generative_models import GenerativeModel, Tool
import vertexai

# Create a RAG Corpus, Import Files, and Generate a response

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# display_name = "test_corpus"
# paths = ["https://drive.google.com/file/d/123", "gs://my_bucket/my_files_dir"]  # Supports Google Cloud Storage and Google Drive Links

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="us-east4")

# Create RagCorpus
# Configure embedding model, for example "text-embedding-005".
embedding_model_config = rag.RagEmbeddingModelConfig(
    vertex_prediction_endpoint=rag.VertexPredictionEndpoint(
        publisher_model="publishers/google/models/text-embedding-005"
    )
)

rag_corpus = rag.create_corpus(
    display_name=display_name,
    backend_config=rag.RagVectorDbConfig(
        rag_embedding_model_config=embedding_model_config
    ),
)

# Import Files to the RagCorpus
rag.import_files(
    rag_corpus.name,
    paths,
    # Optional
    transformation_config=rag.TransformationConfig(
        chunking_config=rag.ChunkingConfig(
            chunk_size=512,
            chunk_overlap=100,
        ),
    ),
    max_embedding_requests_per_min=1000,  # Optional
)

# Direct context retrieval
rag_retrieval_config = rag.RagRetrievalConfig(
    top_k=3,  # Optional
    filter=rag.Filter(vector_distance_threshold=0.5),  # Optional
)
response = rag.retrieval_query(
    rag_resources=[
        rag.RagResource(
            rag_corpus=rag_corpus.name,
            # Optional: supply IDs from `rag.list_files()`.
            # rag_file_ids=["rag-file-1", "rag-file-2", ...],
        )
    ],
    text="What is RAG and why it is helpful?",
    rag_retrieval_config=rag_retrieval_config,
)
print(response)

# Enhance generation
# Create a RAG retrieval tool
rag_retrieval_tool = Tool.from_retrieval(
    retrieval=rag.Retrieval(
        source=rag.VertexRagStore(
            rag_resources=[
                rag.RagResource(
                    rag_corpus=rag_corpus.name,  # Currently only 1 corpus is allowed.
                    # Optional: supply IDs from `rag.list_files()`.
                    # rag_file_ids=["rag-file-1", "rag-file-2", ...],
                )
            ],
            rag_retrieval_config=rag_retrieval_config,
        ),
    )
)

# Create a Gemini model instance
rag_model = GenerativeModel(
    model_name="gemini-2.0-flash-001", tools=[rag_retrieval_tool]
)

# Generate response
response = rag_model.generate_content("What is RAG and why it is helpful?")
print(response.text)
# Example response:
#   RAG stands for Retrieval-Augmented Generation.
#   It's a technique used in AI to enhance the quality of responses
# ...

curl

  1. Créez un corpus RAG.

      export LOCATION=LOCATION
  export PROJECT_ID=PROJECT_ID
  export CORPUS_DISPLAY_NAME=CORPUS_DISPLAY_NAME

  // CreateRagCorpus
  // Output: CreateRagCorpusOperationMetadata
  curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora \
  -d '{
        "display_name" : "'"CORPUS_DISPLAY_NAME"'"
    }'

    Pour en savoir plus, consultez Exemple de création d'un corpus RAG.

  2. Importez un fichier RAG.

      // ImportRagFiles
  // Import a single Cloud Storage file or all files in a Cloud Storage bucket.
  // Input: LOCATION, PROJECT_ID, RAG_CORPUS_ID, GCS_URIS
  export RAG_CORPUS_ID=RAG_CORPUS_ID
  export GCS_URIS=GCS_URIS
  export CHUNK_SIZE=CHUNK_SIZE
  export CHUNK_OVERLAP=CHUNK_OVERLAP
  export EMBEDDING_MODEL_QPM_RATE=EMBEDDING_MODEL_QPM_RATE

  // Output: ImportRagFilesOperationMetadataNumber
  // Use ListRagFiles, or import_result_sink to get the correct rag_file_id.
  curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles:import \
  -d '{
    "import_rag_files_config": {
      "gcs_source": {
        "uris": "GCS_URIS"
      },
      "rag_file_chunking_config": {
        "chunk_size": CHUNK_SIZE,
        "chunk_overlap": CHUNK_OVERLAP
      },
      "max_embedding_requests_per_min": EMBEDDING_MODEL_QPM_RATE
    }
  }'

    Pour en savoir plus, consultez l'exemple d'importation de fichiers RAG.

  3. Exécutez une requête de récupération RAG.

      export RAG_CORPUS_RESOURCE=RAG_CORPUS_RESOURCE
  export VECTOR_DISTANCE_THRESHOLD=VECTOR_DISTANCE_THRESHOLD
  export SIMILARITY_TOP_K=SIMILARITY_TOP_K

  {
  "vertex_rag_store": {
      "rag_resources": {
        "rag_corpus": "RAG_CORPUS_RESOURCE"
      },
      "vector_distance_threshold": VECTOR_DISTANCE_THRESHOLD
    },
    "query": {
    "text": TEXT
    "similarity_top_k": SIMILARITY_TOP_K
    }
  }

  curl -X POST \
      -H "Authorization: Bearer $(gcloud auth print-access-token)" \
      -H "Content-Type: application/json; charset=utf-8" \
      -d @request.json \
      "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION:retrieveContexts"

    Pour en savoir plus, consultez API du moteur RAG.

  4. Génération de contenu

    {
"contents": {
  "role": "USER",
  "parts": {
    "text": "INPUT_PROMPT"
  }
},
"tools": {
  "retrieval": {
  "disable_attribution": false,
  "vertex_rag_store": {
    "rag_resources": {
      "rag_corpus": "RAG_CORPUS_RESOURCE"
    },
    "similarity_top_k": "SIMILARITY_TOP_K",
    "vector_distance_threshold": VECTOR_DISTANCE_THRESHOLD
  }
  }
}
}

curl -X POST \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "Content-Type: application/json; charset=utf-8" \
    -d @request.json \
    "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:GENERATION_METHOD"

    Pour en savoir plus, consultez API du moteur RAG.

Étapes suivantes