Panduan memulai RAG

Halaman ini menunjukkan cara menggunakan Vertex AI SDK untuk menjalankan Mesin RAG pada tugas Platform Agen Gemini Enterprise.

Anda juga dapat mengikuti menggunakan notebook ini Pengantar Mesin RAG.

Peran yang diperlukan

Berikan peran ke akun pengguna Anda. Jalankan perintah berikut satu kali untuk setiap peran IAM berikut: roles/aiplatform.user 

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

Ganti kode berikut:

  • PROJECT_ID: Project ID Anda.
  • USER_IDENTIFIER: ID untuk akun pengguna Anda. Misalnya, myemail@example.com.
  • ROLE: Peran IAM yang Anda berikan ke akun pengguna Anda.

Menyiapkan Google Cloud konsol

Untuk menggunakan Mesin RAG, lakukan hal berikut:

  1. Instal Agent Platform SDK untuk Python.

  2. Jalankan perintah ini di Google Cloud konsol untuk menyiapkan project Anda.

    gcloud config set project {project}

  3. Jalankan perintah ini untuk mengotorisasi login Anda.

    gcloud auth application-default login

Menjalankan Mesin RAG

Salin dan tempel contoh kode ini ke Google Cloud konsol untuk menjalankan Mesin RAG.

Python

Untuk mempelajari cara menginstal atau mengupdate Vertex AI SDK untuk Python, lihat Menginstal Vertex AI SDK untuk Python. Untuk mengetahui informasi selengkapnya, lihat Python Dokumentasi referensi API. 

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-3.5-flash"
# display_name = "test_corpus"
# gcs_path = "gs://my_bucket/my_files_dir/*"
# google_drive_path ="https://drive.google.com/file/d/123"

# Initialize Agent Platform client once per session
client = agentplatform.Client(project=PROJECT_ID, location="us-east4")

# 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(enterprise=True, project=PROJECT_ID, location="us-east4")


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. Buat korpus 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"'"
    }'

    Untuk mengetahui informasi selengkapnya, lihat Membuat korpus RAG contoh.

  2. Impor 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
    }
  }'

    Untuk mengetahui informasi selengkapnya, lihat Contoh mengimpor file RAG.

  3. Jalankan kueri pengambilan 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"

    Untuk mengetahui informasi selengkapnya, lihat RAG Engine API.

  4. Buat konten.

    {
"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"

    Untuk mengetahui informasi selengkapnya, lihat RAG Engine API.

Langkah berikutnya