RAG-Kurzanleitung

Auf dieser Seite erfahren Sie, wie Sie mit dem Vertex AI SDK Aufgaben der Vertex AI RAG Engine ausführen.

Sie können auch dieses Notebook verwenden: Intro to Vertex AI RAG Engine.

Erforderliche Rollen

Weisen Sie Ihrem Nutzerkonto Rollen zu. Führen Sie den folgenden Befehl für jede der folgenden IAM-Rollen einmal aus: roles/aiplatform.user

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

Ersetzen Sie Folgendes:

PROJECT_ID: Ihre Projekt-ID.
USER_IDENTIFIER: Die Kennung für Ihr Nutzerkonto. Beispiel: myemail@example.com.
ROLE: Die IAM-Rolle, die Sie Ihrem Nutzerkonto zuweisen.

Konsole vorbereiten Google Cloud

So verwenden Sie die Vertex AI RAG Engine:

Installieren Sie Vertex AI SDK für Python.
Führen Sie diesen Befehl in der Google Cloud Konsole aus, um Ihr Projekt einzurichten.

gcloud config set project {project}
Führen Sie diesen Befehl aus, um Ihre Anmeldung zu autorisieren.

gcloud auth application-default login

Vertex AI RAG Engine ausführen

Kopieren Sie diesen Beispielcode und fügen Sie ihn in die Google Cloud Konsole ein, um die Vertex AI RAG Engine auszuführen.

Python

Informationen zur Installation des Vertex AI SDK for Python finden Sie unter Vertex AI SDK for Python installieren. Weitere Informationen finden Sie in der Python API-Referenzdokumentation.

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

Erstellen Sie einen RAG-Korpus.

  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"'"
    }'

Weitere Informationen finden Sie im Beispiel zum Erstellen eines RAG-Korpus.

Importieren Sie eine RAG-Datei.

  // 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
    }
  }'

Weitere Informationen finden Sie im Beispiel zum Importieren von RAG-Dateien.

Führen Sie eine RAG-Abrufabfrage aus.

  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"

Weitere Informationen finden Sie unter RAG Engine API.

Inhalte generieren.

{
"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"