RAG Engine API

使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora

{
  "display_name" : "CORPUS_DISPLAY_NAME",
  "description": "CORPUS_DESCRIPTION",
}

  // CreateRagCorpus
  // Input: LOCATION, PROJECT_ID, CORPUS_DISPLAY_NAME
  // 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"
    }'

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
display_name = "CORPUS_DISPLAY_NAME"
description = "CORPUS_DESCRIPTION"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

# Configure backend_config
backend_config=rag.RagVectorDbConfig(
      rag_embedding_model_config=rag.RagEmbeddingModelConfig(
          vertex_prediction_endpoint=rag.VertexPredictionEndpoint(
              publisher_model="publishers/google/models/text-embedding-005"
          )
      )
)

corpus = rag.create_corpus(
    display_name=display_name,
    description=description,
    backend_config=backend_config,
)
print(corpus)
# Example response:
# RagCorpus(name='projects/1234567890/locations/us-central1/ragCorpora/1234567890',
# display_name='test_corpus', description='Corpus Description', embedding_model_config=...
# ...

PATCH https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/CORPUS_ID

{
  "display_name" : "CORPUS_DISPLAY_NAME",
  "description": "CORPUS_DESCRIPTION",
  "rag_vector_db_config": {
    "vertex_vector_search": {
        "index": "INDEX_NAME",
        "index_endpoint": "INDEX_ENDPOINT_NAME",
    }
  }
}

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora?page_size=PAGE_SIZE&page_token=PAGE_TOKEN

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
LOCATION = "us-central1"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location=LOCATION)

corpora = rag.list_corpora()
print(corpora)
# Example response:
# ListRagCorporaPager<rag_corpora {
#   name: "projects/[PROJECT_ID]/locations/us-central1/ragCorpora/2305843009213693952"
#   display_name: "test_corpus"
#   create_time {
# ...

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID

    PROJECT_ID: Your project ID.
    LOCATION: The region to process the request.
    RAG_CORPUS_ID: The corpus ID of your RAG corpus.
  ```

```sh
  // GetRagCorpus
  // Input: LOCATION, PROJECT_ID, RAG_CORPUS_ID
  // Output: RagCorpus
  curl -X GET \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID

  // ListRagCorpora
  curl -sS -X GET \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/
  ```

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
LOCATION = "LOCATION"
corpus_name = "projects/{PROJECT_ID}/locations/{LOCATION}/ragCorpora/{rag_corpus_id}"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location=LOCATION)

corpus = rag.get_corpus(name=corpus_name)
print(corpus)
# Example response:
# RagCorpus(name='projects/[PROJECT_ID]/locations/us-central1/ragCorpora/1234567890',
# display_name='test_corpus', description='Corpus Description',
# ...

DELETE https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
corpus_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

rag.delete_corpus(name=corpus_name)
print(f"Corpus {corpus_name} deleted.")
# Example response:
# Successfully deleted the RagCorpus.
# Corpus projects/[PROJECT_ID]/locations/us-central1/ragCorpora/123456789012345 deleted. import rag

curl -X POST \
-H "X-Goog-Upload-Protocol: multipart" \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-F metadata="{'rag_file': {'display_name':' DISPLAY_NAME', 'description':'DESCRIPTION'}}" \
-F file=@LOCAL_FILE_PATH \
"https://LOCATION-aiplatform.googleapis.com/upload/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles:upload"

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
corpus_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID"
path = "path/to/local/file.txt"
display_name = "file_display_name"
description = "file description"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

rag_file = rag.upload_file(
    corpus_name=corpus_name,
    path=path,
    display_name=display_name,
    description=description,
)
print(rag_file)
# RagFile(name='projects/[PROJECT_ID]/locations/us-central1/ragCorpora/1234567890/ragFiles/09876543',
#  display_name='file_display_name', description='file description')

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles:import

{
  "import_rag_files_config": {
    "gcs_source": {
      "uris": "GCS_URIS"
    },
    "rag_file_chunking_config": {
      "chunk_size": "CHUNK_SIZE",
      "chunk_overlap": "CHUNK_OVERLAP"
    }
  }
}

// ImportRagFiles
// Import a single Cloud Storage file or all files in a Cloud Storage bucket.
// Input: LOCATION, PROJECT_ID, RAG_CORPUS_ID, GCS_URIS
// Output: ImportRagFilesOperationMetadataNumber
// Use ListRagFiles to find the server-generated 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
  }
}'

// ImportRagFiles
// Import all files in a Google Drive folder.
// Input: LOCATION, PROJECT_ID, RAG_CORPUS_ID, FOLDER_RESOURCE_ID
// Output: ImportRagFilesOperationMetadataNumber
// Use ListRagFiles to find the server-generated 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": {
    "google_drive_source": {
      "resource_ids": {
        "resource_id": "FOLDER_RESOURCE_ID",
        "resource_type": "RESOURCE_TYPE_FOLDER"
      }
    },
    "max_embedding_requests_per_min": EMBEDDING_MODEL_QPM_RATE
  }
}'

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
corpus_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID"
paths = ["https://drive.google.com/file/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="LOCATION")

response = rag.import_files(
    corpus_name=corpus_name,
    paths=paths,
    transformation_config=rag.TransformationConfig(
        rag.ChunkingConfig(chunk_size=512, chunk_overlap=100)
    ),
    max_embedding_requests_per_min=900, # Optional
)
print(f"Imported {response.imported_rag_files_count} files.")
# Example response:
# Imported 2 files.

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles?page_size=PAGE_SIZE&page_token=PAGE_TOKEN

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
corpus_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

files = rag.list_files(corpus_name=corpus_name)
for file in files:
    print(file.display_name)
    print(file.name)
# Example response:
# g-drive_file.txt
# projects/1234567890/locations/us-central1/ragCorpora/111111111111/ragFiles/222222222222
# g_cloud_file.txt
# projects/1234567890/locations/us-central1/ragCorpora/111111111111/ragFiles/333333333333

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles/RAG_FILE_ID

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
file_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles/RAG_FILE_ID"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

rag_file = rag.get_file(name=file_name)
print(rag_file)
# Example response:
# RagFile(name='projects/1234567890/locations/LOCATION/ragCorpora/11111111111/ragFiles/22222222222',
# display_name='file_display_name', description='file description')

DELETE https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles/RAG_FILE_ID

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
file_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID/ragFiles/RAG_FILE_ID"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

rag.delete_file(name=file_name)
print(f"File {file_name} deleted.")
# Example response:
# Successfully deleted the RagFile.
# File projects/1234567890/locations/us-central1/ragCorpora/1111111111/ragFiles/2222222222 deleted.

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION:retrieveContexts

{
"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
  }
}

from vertexai import rag
import vertexai

PROJECT_ID = "PROJECT_ID"
corpus_name = "projects/[PROJECT_ID]/locations/LOCATION/ragCorpora/RAG_CORPUS_ID"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

response = rag.retrieval_query(
  rag_resources=[
      rag.RagResource(
          rag_corpus=corpus_name,
          # Optional: supply IDs from `rag.list_files()`.
          # rag_file_ids=["rag-file-1", "rag-file-2", ...],
      )
  ],
  text="TEXT",
  rag_retrieval_config=rag.RagRetrievalConfig(
      top_k=SIMILARITY_TOP_K,
      filter=rag.utils.resources.Filter(vector_distance_threshold=VECTOR_DISTANCE_THRESHOLD),
  ),
)
print(response)
# Example response:
# contexts {
#   contexts {
#     source_uri: "gs://your-bucket-name/file.txt"
#     text: "....
#   ....

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:GENERATION_METHOD

{
"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
  }
  }
}
}

from vertexai import rag
from vertexai.generative_models import GenerativeModel, Tool
import vertexai

PROJECT_ID = "PROJECT_ID"
corpus_name = "projects/{PROJECT_ID}/locations/LOCATION/ragCorpora/RAG_CORPUS_ID"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="LOCATION")

rag_retrieval_tool = Tool.from_retrieval(
    retrieval=rag.Retrieval(
        source=rag.VertexRagStore(
            rag_resources=[
                rag.RagResource(
                    rag_corpus="RAG_CORPUS_RESOURCE",
                    # Optional: supply IDs from `rag.list_files()`.
                    # rag_file_ids=["rag-file-1", "rag-file-2", ...],
                )
            ],
            similarity_top_k=SIMILARITY_TOP_K,  # Optional
            vector_distance_threshold=VECTOR_DISTANCE_THRESHOLD,  # Optional
        ),
    )
)

rag_model = GenerativeModel(
    model_name="MODEL_ID", tools=[rag_retrieval_tool]
)
response = rag_model.generate_content("Why is the sky blue?")
print(response.text)
# Example response:
#   The sky appears blue due to a phenomenon called Rayleigh scattering.
#   Sunlight, which contains all colors of the rainbow, is scattered
#   by the tiny particles in the Earth's atmosphere....
#   ...