Início rápido da RAG

Esta página mostra-lhe como usar o SDK do Vertex AI para executar tarefas do Vertex AI RAG Engine.

Também pode seguir este bloco de notas Introdução ao motor RAG do Vertex AI.

Funções necessárias

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.

Prepare a sua Google Cloud consola

Para usar o Vertex AI RAG Engine, faça o seguinte:

  1. Instale o SDK Vertex AI para Python.

  2. Execute este comando na consola do Google Cloud para configurar o seu projeto.

    gcloud config set project {project}

  3. Execute este comando para autorizar o seu início de sessão.

    gcloud auth application-default login

Execute o Vertex AI RAG Engine

Copie e cole este exemplo de código na Google Cloud consola para executar o motor RAG do Vertex AI.

Python

Para saber como instalar ou atualizar o SDK Vertex AI para Python, consulte o artigo Instale o SDK Vertex AI para Python. Para mais informações, consulte a Python documentação de referência da API. 

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. Crie um 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"'"
    }'

    Para mais informações, consulte o exemplo de criação de um corpus RAG.

  2. Importe um ficheiro 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
    }
  }'

    Para mais informações, consulte o exemplo de importação de ficheiros RAG.

  3. Execute uma consulta de obtenção de 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"

    Para mais informações, consulte a API RAG Engine.

  4. Gerar conteúdo.

    {
"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"

    Para mais informações, consulte a API RAG Engine.

O que se segue?