Utiliser Vertex AI Feature Store dans le moteur de classification RAG Vertex AI

Restez organisé à l'aide des collections Enregistrez et classez les contenus selon vos préférences.

  CREATE TABLE `PROJECT_ID.input_us_central1.rag_source_new` (
    `corpus_id` STRING NOT NULL,
    `file_id` STRING NOT NULL,
    `chunk_id` STRING NOT NULL,
    `chunk_data_type` STRING,
    `chunk_data` STRING,
    `embeddings` ARRAY<FLOAT64>,
    `file_original_uri` STRING
  );

  # TODO(developer): Update and uncomment the following lines:
  # Set feature_view_id
  # Example: "feature_view_test"
  # FEATURE_VIEW_ID = "your-feature-view-id"
  #
  # The big_query_uri generated in the above BigQuery table schema creation step
  # The format should be "bq://" + BigQuery table ID
  # Example: "bq://tester.ragtest1.rag_testdata"
  # BIG_QUERY_URI=YOUR_BIG_QUERY_URI

  # Call CreateFeatureView API to create a FeatureView
  curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/featureOnlineStores/${FEATURE_ONLINE_STORE_ID}/featureViews?feature_view_id=${FEATURE_VIEW_ID} \
    -d '{
          "vertex_rag_source": {
            "uri": '\""${BIG_QUERY_URI}"\"'
          }
      }'

  # Call ListFeatureViews API to verify the FeatureView is created successfully
  curl -X GET -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" -H "Content-Type: application/json" https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/featureOnlineStores/${FEATURE_ONLINE_STORE_ID}/featureViews

# TODO(developer): Update and uncomment the following lines:
# CORPUS_DISPLAY_NAME = "your-corpus-display-name"
#
# Full feature view resource name
# Format: projects/${PROJECT_ID}/locations/us-central1/featureOnlineStores/${FEATURE_ONLINE_STORE_ID}/featureViews/${FEATURE_VIEW_ID}
# FEATURE_VIEW_RESOURCE_NAME = "your-feature-view-resource-name"

# Call CreateRagCorpus API to create a new RAG corpus
curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1beta1/projects//{PROJECT_ID}/locations/us-central1/ragCorpora -d '{
    "display_name" : '\""${CORPUS_DISPLAY_NAME}"\"',
    "rag_vector_db_config" : {
      "vertex_feature_store": {
        "feature_view_resource_name":'\""${FEATURE_VIEW_RESOURCE_NAME}"\"'
      }
    }
  }'

# Call ListRagCorpora API to verify the RAG corpus is created successfully
curl -sS -X GET \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
"https://us-central1-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/us-central1/ragCorpora"

# TODO(developer): Update and uncomment the following lines:
# RAG_CORPUS_ID = "your-rag-corpus-id"
#
# Google Cloud Storage bucket/file location.
# For example, "gs://rag-fos-test/"
# GCS_URIS= "your-gcs-uris"

# Call ImportRagFiles API to embed files and store in the BigQuery table
curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/us-central1/ragCorpora/${RAG_CORPUS_ID}/ragFiles:import \
-d '{
  "import_rag_files_config": {
    "gcs_source": {
      "uris": '\""${GCS_URIS}"\"'
    },
    "rag_file_chunking_config": {
      "chunk_size": 512
    }
  }
}'

# Call ListRagFiles API to verify the files are imported successfully
curl -X GET \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
https://us-central1-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/us-central1/ragCorpora/${RAG_CORPUS_ID}/ragFiles

# TODO(developer): Update and uncomment the following lines:
# RETRIEVAL_QUERY="your-retrieval-query"
#
# Full RAG corpus resource name
# Format:
# "projects/${PROJECT_ID}/locations/us-central1/ragCorpora/${RAG_CORPUS_ID}"
# RAG_CORPUS_RESOURCE="your-rag-corpus-resource"

# Call RetrieveContexts API to retrieve relevant contexts
curl -X POST \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
https://us-central1-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/us-central1:retrieveContexts \
  -d '{
    "vertex_rag_store": {
      "rag_resources": {
          "rag_corpus": '\""${RAG_CORPUS_RESOURCE}"\"',
        },
    },
    "query": {
      "text": '\""${RETRIEVAL_QUERY}"\"',
      "similarity_top_k": 10
    }
  }'

# TODO(developer): Update and uncomment the following lines:
# MODEL_ID=gemini-2.0-flash
# GENERATE_CONTENT_PROMPT="your-generate-content-prompt"

# GenerateContent with contexts retrieved from the FeatureStoreOnline index
curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json"  https://us-central1-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:generateContent \
-d '{
  "contents": {
    "role": "user",
    "parts": {
      "text": '\""${GENERATE_CONTENT_PROMPT}"\"'
    }
  },
  "tools": {
    "retrieval": {
      "vertex_rag_store": {
        "rag_resources": {
            "rag_corpus": '\""${RAG_CORPUS_RESOURCE}"\"',
          },
        "similarity_top_k": 8,
      }
    }
  }
}'