Guida rapida RAG

Questa pagina mostra come utilizzare l'SDK Vertex AI per eseguire le attività di RAG Engine su Gemini Enterprise Agent Platform.

Puoi anche seguire la procedura utilizzando questo blocco note Introduzione a RAG Engine.

Ruoli obbligatori

Concedi i ruoli al tuo account utente. Esegui il seguente comando una volta per ciascuno dei seguenti ruoli IAM: roles/aiplatform.user 

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

Sostituisci quanto segue:

  • PROJECT_ID: il tuo ID progetto.
  • USER_IDENTIFIER: l'identificatore del tuo account utente. Ad esempio: myemail@example.com.
  • ROLE: il ruolo IAM che concedi al tuo account utente.

Prepara la console Google Cloud

Per utilizzare RAG Engine, segui questi passaggi:

  1. Installa l'SDK Agent Platform per Python.

  2. Esegui questo comando nella console Google Cloud per configurare il progetto.

    gcloud config set project {project}

  3. Esegui questo comando per autorizzare l'accesso.

    gcloud auth application-default login

Esegui RAG Engine

Copia e incolla questo codice campione nella console Google Cloud per eseguire il motore RAG.

Python

Per scoprire come installare o aggiornare l'SDK Vertex AI Python, consulta Installa l'SDK Vertex AI Python. Per saperne di più, consulta la documentazione di riferimento dell'API Python. 

import agentplatform

from agentplatform import types
from google import genai
from google.genai import types as genai_types

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

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# MODEL_ID = "gemini-3.8-flash"
# display_name = "test_corpus"
# gcs_path = "gs://my_bucket/my_files_dir/*"

# Initialize Agent Platform client once per session.
# See https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/rag-engine/rag-overview#supported-regions
client = agentplatform.Client(project=PROJECT_ID, location="us-east5")

# Configure embedding model, for example "text-embedding-005".
embedding_model_config = types.RagEmbeddingModelConfig(
    vertex_prediction_endpoint=types.RagEmbeddingModelConfigVertexPredictionEndpoint(
        endpoint="publishers/google/models/text-embedding-005"
    ),
)

# Create RagCorpus
rag_corpus = client.rag.create_corpus(
    rag_corpus=types.RagCorpus(
        display_name=display_name,
        rag_vector_db_config=types.RagVectorDbConfig(
            rag_embedding_model_config=embedding_model_config
        )
    )
)

# Import Files to the RagCorpus
client.rag.import_files(
    name=rag_corpus.name,
    import_config=types.ImportRagFilesConfig(
        gcs_source=genai_types.GcsSource(uris=[gcs_path]),
        rag_file_transformation_config=types.RagFileTransformationConfig(
            rag_file_chunking_config=types.RagFileChunkingConfig(
                chunk_size=512,
                chunk_overlap=100,
            )
        ),  # optional
        max_embedding_requests_per_min=1000,  # optional
    ),
)

# Direct context retrieval
rag_retrieval_config = genai_types.RagRetrievalConfig(
    top_k=3,  # Optional
    filter=genai_types.RagRetrievalConfigFilter(
        vector_distance_threshold=0.5
    ),  # Optional
)
response = client.rag.retrieve_contexts(
    vertex_rag_store=genai_types.VertexRagStore(
        rag_resources=[
            genai_types.VertexRagStoreRagResource(
                rag_corpus=rag_corpus.name,
            )
        ],
    ),
    query=types.RagQuery(
        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 = genai_types.Tool(
    retrieval=genai_types.Retrieval(
        vertex_rag_store=genai_types.VertexRagStore(
            rag_resources=[
                genai_types.VertexRagStoreRagResource(
                    rag_corpus=rag_corpus.name,
                    # Optional: supply IDs from `rag.list_files()`.
                    # rag_file_ids=["rag-file-1", "rag-file-2", ...],
                )
            ],
            rag_retrieval_config=rag_retrieval_config,
        ),
    )
)

# Call generate_content with the tool using the GenAI SDK

# Create a GenAI SDK client
genai_client = genai.Client(vertexai=True, project=PROJECT_ID, location="global")

response = genai_client.models.generate_content(
    model=MODEL_ID,
    contents="What is RAG and why it is helpful?",
    config=genai_types.GenerateContentConfig(
        tools=[rag_retrieval_tool]
    )
)
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. Crea 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"'"
    }'

    Per saperne di più, consulta Crea un esempio di corpus RAG.

  2. Importa un file 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
    }
  }'

    Per saperne di più, consulta Esempio di importazione di file RAG.

  3. Esegui una query di recupero 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"

    Per saperne di più, consulta l'API RAG Engine.

  4. Crea contenuti.

    {
"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"

    Per saperne di più, consulta l'API RAG Engine.

Passaggi successivi