File: aiplatform_v1beta1.projects.locations.ragCorpora.html

package info (click to toggle)
python-googleapi 2.180.0-1
links: PTS
area: main
in suites: forky
size: 527,124 kB
sloc: python: 11,076; javascript: 249; sh: 114; makefile: 59
file content (893 lines) | stat: -rw-r--r-- 97,288 bytes
parent folder | download | duplicates (2)
<html><body>
<style>

body, h1, h2, h3, div, span, p, pre, a {
  margin: 0;
  padding: 0;
  border: 0;
  font-weight: inherit;
  font-style: inherit;
  font-size: 100%;
  font-family: inherit;
  vertical-align: baseline;
}

body {
  font-size: 13px;
  padding: 1em;
}

h1 {
  font-size: 26px;
  margin-bottom: 1em;
}

h2 {
  font-size: 24px;
  margin-bottom: 1em;
}

h3 {
  font-size: 20px;
  margin-bottom: 1em;
  margin-top: 1em;
}

pre, code {
  line-height: 1.5;
  font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}

pre {
  margin-top: 0.5em;
}

h1, h2, h3, p {
  font-family: Arial, sans serif;
}

h1, h2, h3 {
  border-bottom: solid #CCC 1px;
}

.toc_element {
  margin-top: 0.5em;
}

.firstline {
  margin-left: 2 em;
}

.method  {
  margin-top: 1em;
  border: solid 1px #CCC;
  padding: 1em;
  background: #EEE;
}

.details {
  font-weight: bold;
  font-size: 14px;
}

</style>

<h1><a href="aiplatform_v1beta1.html">Vertex AI API</a> . <a href="aiplatform_v1beta1.projects.html">projects</a> . <a href="aiplatform_v1beta1.projects.locations.html">locations</a> . <a href="aiplatform_v1beta1.projects.locations.ragCorpora.html">ragCorpora</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
  <code><a href="aiplatform_v1beta1.projects.locations.ragCorpora.operations.html">operations()</a></code>
</p>
<p class="firstline">Returns the operations Resource.</p>

<p class="toc_element">
  <code><a href="aiplatform_v1beta1.projects.locations.ragCorpora.ragFiles.html">ragFiles()</a></code>
</p>
<p class="firstline">Returns the ragFiles Resource.</p>

<p class="toc_element">
  <code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
  <code><a href="#create">create(parent, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Creates a RagCorpus.</p>
<p class="toc_element">
  <code><a href="#delete">delete(name, force=None, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes a RagCorpus.</p>
<p class="toc_element">
  <code><a href="#get">get(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets a RagCorpus.</p>
<p class="toc_element">
  <code><a href="#list">list(parent, pageSize=None, pageToken=None, x__xgafv=None)</a></code></p>
<p class="firstline">Lists RagCorpora in a Location.</p>
<p class="toc_element">
  <code><a href="#list_next">list_next()</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<p class="toc_element">
  <code><a href="#patch">patch(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Updates a RagCorpus.</p>
<h3>Method Details</h3>
<div class="method">
    <code class="details" id="close">close()</code>
  <pre>Close httplib2 connections.</pre>
</div>

<div class="method">
    <code class="details" id="create">create(parent, body=None, x__xgafv=None)</code>
  <pre>Creates a RagCorpus.

Args:
  parent: string, Required. The resource name of the Location to create the RagCorpus in. Format: `projects/{project}/locations/{location}` (required)
  body: object, The request body.
    The object takes the form of:

{ # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
  &quot;corpusStatus&quot;: { # RagCorpus status. # Output only. RagCorpus state.
    &quot;errorStatus&quot;: &quot;A String&quot;, # Output only. Only when the `state` field is ERROR.
    &quot;state&quot;: &quot;A String&quot;, # Output only. RagCorpus life state.
  },
  &quot;corpusTypeConfig&quot;: { # The config for the corpus type of the RagCorpus. # Optional. The corpus type config of the RagCorpus.
    &quot;documentCorpus&quot;: { # Config for the document corpus. # Optional. Config for the document corpus.
    },
    &quot;memoryCorpus&quot;: { # Config for the memory corpus. # Optional. Config for the memory corpus.
      &quot;llmParser&quot;: { # Specifies the LLM parsing for RagFiles. # The LLM parser to use for the memory corpus.
        &quot;customParsingPrompt&quot;: &quot;A String&quot;, # The prompt to use for parsing. If not specified, a default prompt will be used.
        &quot;globalMaxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute in this project. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If this value is not specified, max_parsing_requests_per_min will be used by indexing pipeline job as the global limit.
        &quot;maxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.
        &quot;modelName&quot;: &quot;A String&quot;, # The name of a LLM model used for parsing. Format: * `projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}`
      },
    },
  },
  &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was created.
  &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the RagCorpus.
  &quot;displayName&quot;: &quot;A String&quot;, # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  &quot;encryptionSpec&quot;: { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Optional. Immutable. The CMEK key name used to encrypt at-rest data related to this Corpus. Only applicable to RagManagedDb option for Vector DB. This field can only be set at corpus creation time, and cannot be updated or deleted.
    &quot;kmsKeyName&quot;: &quot;A String&quot;, # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  &quot;name&quot;: &quot;A String&quot;, # Output only. The resource name of the RagCorpus.
  &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the RagCorpus.
    &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
      &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
      &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
        &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
          &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
          &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
          &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
        },
      },
    },
    &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
      &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
      &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
      &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
    },
  },
  &quot;ragFilesCount&quot;: 42, # Output only. Number of RagFiles in the RagCorpus. NOTE: This field is not populated in the response of VertexRagDataService.ListRagCorpora.
  &quot;ragVectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The Vector DB config of the RagCorpus.
    &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
      &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
        &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
        &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
      },
    },
    &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
      &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
    },
    &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
      &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
        &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
        &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
          &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
            &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
            &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
            &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
          },
        },
      },
      &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
    },
    &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
      &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
        &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
        &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
      },
      &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
      },
    },
    &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
      &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
    },
    &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
      &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
      &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
    },
    &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
      &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
      &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
    },
  },
  &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was last updated.
  &quot;vectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The config for the Vector DBs.
    &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
      &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
        &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
        &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
      },
    },
    &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
      &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
    },
    &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
      &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
        &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
        &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
          &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
            &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
            &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
            &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
          },
        },
      },
      &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
    },
    &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
      &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
        &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
        &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
      },
      &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
      },
    },
    &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
      &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
    },
    &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
      &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
      &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
    },
    &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
      &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
      &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
    },
  },
  &quot;vertexAiSearchConfig&quot;: { # Config for the Vertex AI Search. # Optional. Immutable. The config for the Vertex AI Search.
    &quot;servingConfig&quot;: &quot;A String&quot;, # Vertex AI Search Serving Config resource full name. For example, `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}`.
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  &quot;done&quot;: True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  &quot;error&quot;: { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    &quot;code&quot;: 42, # The status code, which should be an enum value of google.rpc.Code.
    &quot;details&quot;: [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
    &quot;message&quot;: &quot;A String&quot;, # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  &quot;metadata&quot;: { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
  &quot;name&quot;: &quot;A String&quot;, # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  &quot;response&quot;: { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="delete">delete(name, force=None, x__xgafv=None)</code>
  <pre>Deletes a RagCorpus.

Args:
  name: string, Required. The name of the RagCorpus resource to be deleted. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` (required)
  force: boolean, Optional. If set to true, any RagFiles in this RagCorpus will also be deleted. Otherwise, the request will only work if the RagCorpus has no RagFiles.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  &quot;done&quot;: True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  &quot;error&quot;: { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    &quot;code&quot;: 42, # The status code, which should be an enum value of google.rpc.Code.
    &quot;details&quot;: [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
    &quot;message&quot;: &quot;A String&quot;, # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  &quot;metadata&quot;: { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
  &quot;name&quot;: &quot;A String&quot;, # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  &quot;response&quot;: { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="get">get(name, x__xgafv=None)</code>
  <pre>Gets a RagCorpus.

Args:
  name: string, Required. The name of the RagCorpus resource. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
  &quot;corpusStatus&quot;: { # RagCorpus status. # Output only. RagCorpus state.
    &quot;errorStatus&quot;: &quot;A String&quot;, # Output only. Only when the `state` field is ERROR.
    &quot;state&quot;: &quot;A String&quot;, # Output only. RagCorpus life state.
  },
  &quot;corpusTypeConfig&quot;: { # The config for the corpus type of the RagCorpus. # Optional. The corpus type config of the RagCorpus.
    &quot;documentCorpus&quot;: { # Config for the document corpus. # Optional. Config for the document corpus.
    },
    &quot;memoryCorpus&quot;: { # Config for the memory corpus. # Optional. Config for the memory corpus.
      &quot;llmParser&quot;: { # Specifies the LLM parsing for RagFiles. # The LLM parser to use for the memory corpus.
        &quot;customParsingPrompt&quot;: &quot;A String&quot;, # The prompt to use for parsing. If not specified, a default prompt will be used.
        &quot;globalMaxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute in this project. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If this value is not specified, max_parsing_requests_per_min will be used by indexing pipeline job as the global limit.
        &quot;maxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.
        &quot;modelName&quot;: &quot;A String&quot;, # The name of a LLM model used for parsing. Format: * `projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}`
      },
    },
  },
  &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was created.
  &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the RagCorpus.
  &quot;displayName&quot;: &quot;A String&quot;, # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  &quot;encryptionSpec&quot;: { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Optional. Immutable. The CMEK key name used to encrypt at-rest data related to this Corpus. Only applicable to RagManagedDb option for Vector DB. This field can only be set at corpus creation time, and cannot be updated or deleted.
    &quot;kmsKeyName&quot;: &quot;A String&quot;, # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  &quot;name&quot;: &quot;A String&quot;, # Output only. The resource name of the RagCorpus.
  &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the RagCorpus.
    &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
      &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
      &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
        &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
          &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
          &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
          &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
        },
      },
    },
    &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
      &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
      &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
      &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
    },
  },
  &quot;ragFilesCount&quot;: 42, # Output only. Number of RagFiles in the RagCorpus. NOTE: This field is not populated in the response of VertexRagDataService.ListRagCorpora.
  &quot;ragVectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The Vector DB config of the RagCorpus.
    &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
      &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
        &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
        &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
      },
    },
    &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
      &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
    },
    &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
      &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
        &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
        &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
          &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
            &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
            &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
            &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
          },
        },
      },
      &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
    },
    &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
      &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
        &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
        &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
      },
      &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
      },
    },
    &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
      &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
    },
    &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
      &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
      &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
    },
    &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
      &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
      &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
    },
  },
  &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was last updated.
  &quot;vectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The config for the Vector DBs.
    &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
      &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
        &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
        &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
      },
    },
    &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
      &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
    },
    &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
      &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
        &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
        &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
          &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
            &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
            &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
            &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
          },
        },
      },
      &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
    },
    &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
      &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
        &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
        &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
      },
      &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
      },
    },
    &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
      &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
    },
    &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
      &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
      &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
    },
    &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
      &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
      &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
    },
  },
  &quot;vertexAiSearchConfig&quot;: { # Config for the Vertex AI Search. # Optional. Immutable. The config for the Vertex AI Search.
    &quot;servingConfig&quot;: &quot;A String&quot;, # Vertex AI Search Serving Config resource full name. For example, `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}`.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="list">list(parent, pageSize=None, pageToken=None, x__xgafv=None)</code>
  <pre>Lists RagCorpora in a Location.

Args:
  parent: string, Required. The resource name of the Location from which to list the RagCorpora. Format: `projects/{project}/locations/{location}` (required)
  pageSize: integer, Optional. The standard list page size.
  pageToken: string, Optional. The standard list page token. Typically obtained via ListRagCorporaResponse.next_page_token of the previous VertexRagDataService.ListRagCorpora call.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for VertexRagDataService.ListRagCorpora.
  &quot;nextPageToken&quot;: &quot;A String&quot;, # A token to retrieve the next page of results. Pass to ListRagCorporaRequest.page_token to obtain that page.
  &quot;ragCorpora&quot;: [ # List of RagCorpora in the requested page.
    { # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
      &quot;corpusStatus&quot;: { # RagCorpus status. # Output only. RagCorpus state.
        &quot;errorStatus&quot;: &quot;A String&quot;, # Output only. Only when the `state` field is ERROR.
        &quot;state&quot;: &quot;A String&quot;, # Output only. RagCorpus life state.
      },
      &quot;corpusTypeConfig&quot;: { # The config for the corpus type of the RagCorpus. # Optional. The corpus type config of the RagCorpus.
        &quot;documentCorpus&quot;: { # Config for the document corpus. # Optional. Config for the document corpus.
        },
        &quot;memoryCorpus&quot;: { # Config for the memory corpus. # Optional. Config for the memory corpus.
          &quot;llmParser&quot;: { # Specifies the LLM parsing for RagFiles. # The LLM parser to use for the memory corpus.
            &quot;customParsingPrompt&quot;: &quot;A String&quot;, # The prompt to use for parsing. If not specified, a default prompt will be used.
            &quot;globalMaxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute in this project. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If this value is not specified, max_parsing_requests_per_min will be used by indexing pipeline job as the global limit.
            &quot;maxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.
            &quot;modelName&quot;: &quot;A String&quot;, # The name of a LLM model used for parsing. Format: * `projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}`
          },
        },
      },
      &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was created.
      &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the RagCorpus.
      &quot;displayName&quot;: &quot;A String&quot;, # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
      &quot;encryptionSpec&quot;: { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Optional. Immutable. The CMEK key name used to encrypt at-rest data related to this Corpus. Only applicable to RagManagedDb option for Vector DB. This field can only be set at corpus creation time, and cannot be updated or deleted.
        &quot;kmsKeyName&quot;: &quot;A String&quot;, # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
      },
      &quot;name&quot;: &quot;A String&quot;, # Output only. The resource name of the RagCorpus.
      &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the RagCorpus.
        &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
          &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
            &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
            &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
            &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
          },
          &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
            &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
              &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
              &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
              &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
            },
          },
        },
        &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
      },
      &quot;ragFilesCount&quot;: 42, # Output only. Number of RagFiles in the RagCorpus. NOTE: This field is not populated in the response of VertexRagDataService.ListRagCorpora.
      &quot;ragVectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The Vector DB config of the RagCorpus.
        &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
          &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
            &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
            &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
          },
        },
        &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
          &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
        },
        &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
          &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
            &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
              &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
              &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
              &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
            },
            &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
              &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
                &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
                &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
                &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
              },
            },
          },
          &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
            &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
            &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
            &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
          },
        },
        &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
          &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
            &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
            &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
          },
          &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
          },
        },
        &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
          &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
        },
        &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
          &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
          &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
        },
        &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
          &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
          &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
        },
      },
      &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was last updated.
      &quot;vectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The config for the Vector DBs.
        &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
          &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
            &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
            &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
          },
        },
        &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
          &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
        },
        &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
          &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
            &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
              &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
              &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
              &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
            },
            &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
              &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
                &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
                &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
                &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
              },
            },
          },
          &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
            &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
            &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
            &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
          },
        },
        &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
          &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
            &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
            &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
          },
          &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
          },
        },
        &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
          &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
        },
        &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
          &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
          &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
        },
        &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
          &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
          &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
        },
      },
      &quot;vertexAiSearchConfig&quot;: { # Config for the Vertex AI Search. # Optional. Immutable. The config for the Vertex AI Search.
        &quot;servingConfig&quot;: &quot;A String&quot;, # Vertex AI Search Serving Config resource full name. For example, `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}`.
      },
    },
  ],
}</pre>
</div>

<div class="method">
    <code class="details" id="list_next">list_next()</code>
  <pre>Retrieves the next page of results.

        Args:
          previous_request: The request for the previous page. (required)
          previous_response: The response from the request for the previous page. (required)

        Returns:
          A request object that you can call &#x27;execute()&#x27; on to request the next
          page. Returns None if there are no more items in the collection.
        </pre>
</div>

<div class="method">
    <code class="details" id="patch">patch(name, body=None, x__xgafv=None)</code>
  <pre>Updates a RagCorpus.

Args:
  name: string, Output only. The resource name of the RagCorpus. (required)
  body: object, The request body.
    The object takes the form of:

{ # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
  &quot;corpusStatus&quot;: { # RagCorpus status. # Output only. RagCorpus state.
    &quot;errorStatus&quot;: &quot;A String&quot;, # Output only. Only when the `state` field is ERROR.
    &quot;state&quot;: &quot;A String&quot;, # Output only. RagCorpus life state.
  },
  &quot;corpusTypeConfig&quot;: { # The config for the corpus type of the RagCorpus. # Optional. The corpus type config of the RagCorpus.
    &quot;documentCorpus&quot;: { # Config for the document corpus. # Optional. Config for the document corpus.
    },
    &quot;memoryCorpus&quot;: { # Config for the memory corpus. # Optional. Config for the memory corpus.
      &quot;llmParser&quot;: { # Specifies the LLM parsing for RagFiles. # The LLM parser to use for the memory corpus.
        &quot;customParsingPrompt&quot;: &quot;A String&quot;, # The prompt to use for parsing. If not specified, a default prompt will be used.
        &quot;globalMaxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute in this project. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If this value is not specified, max_parsing_requests_per_min will be used by indexing pipeline job as the global limit.
        &quot;maxParsingRequestsPerMin&quot;: 42, # The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.
        &quot;modelName&quot;: &quot;A String&quot;, # The name of a LLM model used for parsing. Format: * `projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}`
      },
    },
  },
  &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was created.
  &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the RagCorpus.
  &quot;displayName&quot;: &quot;A String&quot;, # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  &quot;encryptionSpec&quot;: { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Optional. Immutable. The CMEK key name used to encrypt at-rest data related to this Corpus. Only applicable to RagManagedDb option for Vector DB. This field can only be set at corpus creation time, and cannot be updated or deleted.
    &quot;kmsKeyName&quot;: &quot;A String&quot;, # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  &quot;name&quot;: &quot;A String&quot;, # Output only. The resource name of the RagCorpus.
  &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the RagCorpus.
    &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
      &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
      &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
        &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
          &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
          &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
          &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
        },
      },
    },
    &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
      &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
      &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
      &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
    },
  },
  &quot;ragFilesCount&quot;: 42, # Output only. Number of RagFiles in the RagCorpus. NOTE: This field is not populated in the response of VertexRagDataService.ListRagCorpora.
  &quot;ragVectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The Vector DB config of the RagCorpus.
    &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
      &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
        &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
        &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
      },
    },
    &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
      &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
    },
    &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
      &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
        &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
        &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
          &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
            &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
            &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
            &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
          },
        },
      },
      &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
    },
    &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
      &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
        &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
        &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
      },
      &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
      },
    },
    &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
      &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
    },
    &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
      &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
      &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
    },
    &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
      &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
      &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
    },
  },
  &quot;updateTime&quot;: &quot;A String&quot;, # Output only. Timestamp when this RagCorpus was last updated.
  &quot;vectorDbConfig&quot;: { # Config for the Vector DB to use for RAG. # Optional. Immutable. The config for the Vector DBs.
    &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # Authentication config for the chosen Vector DB.
      &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
        &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
        &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
      },
    },
    &quot;pinecone&quot;: { # The config for the Pinecone. # The config for the Pinecone.
      &quot;indexName&quot;: &quot;A String&quot;, # Pinecone index name. This value cannot be changed after it&#x27;s set.
    },
    &quot;ragEmbeddingModelConfig&quot;: { # Config for the embedding model to use for RAG. # Optional. Immutable. The embedding model config of the Vector DB.
      &quot;hybridSearchConfig&quot;: { # Config for hybrid search. # Configuration for hybrid search.
        &quot;denseEmbeddingModelPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.
          &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
          &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
          &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
        },
        &quot;sparseEmbeddingConfig&quot;: { # Configuration for sparse emebdding generation. # Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
          &quot;bm25&quot;: { # Message for BM25 parameters. # Use BM25 scoring algorithm.
            &quot;b&quot;: 3.14, # Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75.
            &quot;k1&quot;: 3.14, # Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2.
            &quot;multilingual&quot;: True or False, # Optional. Use multilingual tokenizer if set to true.
          },
        },
      },
      &quot;vertexPredictionEndpoint&quot;: { # Config representing a model hosted on Vertex Prediction Endpoint. # The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
        &quot;endpoint&quot;: &quot;A String&quot;, # Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}`
        &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: `projects/{project}/locations/{location}/models/{model}`
        &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model.
      },
    },
    &quot;ragManagedDb&quot;: { # The config for the default RAG-managed Vector DB. # The config for the RAG-managed Vector DB.
      &quot;ann&quot;: { # Config for ANN search. RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API. # Performs an ANN search on RagCorpus. Use this if you have a lot of files (&gt; 10K) in your RagCorpus and want to reduce the search latency.
        &quot;leafCount&quot;: 42, # Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid. Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus). Default value is 500.
        &quot;treeDepth&quot;: 42, # The depth of the tree-based structure. Only depth values of 2 and 3 are supported. Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that. Default value is 2.
      },
      &quot;knn&quot;: { # Config for KNN search. # Performs a KNN search on RagCorpus. Default choice if not specified.
      },
    },
    &quot;vertexFeatureStore&quot;: { # The config for the Vertex Feature Store. # The config for the Vertex Feature Store.
      &quot;featureViewResourceName&quot;: &quot;A String&quot;, # The resource name of the FeatureView. Format: `projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}`
    },
    &quot;vertexVectorSearch&quot;: { # The config for the Vertex Vector Search. # The config for the Vertex Vector Search.
      &quot;index&quot;: &quot;A String&quot;, # The resource name of the Index. Format: `projects/{project}/locations/{location}/indexes/{index}`
      &quot;indexEndpoint&quot;: &quot;A String&quot;, # The resource name of the Index Endpoint. Format: `projects/{project}/locations/{location}/indexEndpoints/{index_endpoint}`
    },
    &quot;weaviate&quot;: { # The config for the Weaviate. # The config for the Weaviate.
      &quot;collectionName&quot;: &quot;A String&quot;, # The corresponding collection this corpus maps to. This value cannot be changed after it&#x27;s set.
      &quot;httpEndpoint&quot;: &quot;A String&quot;, # Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it&#x27;s set.
    },
  },
  &quot;vertexAiSearchConfig&quot;: { # Config for the Vertex AI Search. # Optional. Immutable. The config for the Vertex AI Search.
    &quot;servingConfig&quot;: &quot;A String&quot;, # Vertex AI Search Serving Config resource full name. For example, `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}`.
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  &quot;done&quot;: True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  &quot;error&quot;: { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    &quot;code&quot;: 42, # The status code, which should be an enum value of google.rpc.Code.
    &quot;details&quot;: [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
    &quot;message&quot;: &quot;A String&quot;, # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  &quot;metadata&quot;: { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
  &quot;name&quot;: &quot;A String&quot;, # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  &quot;response&quot;: { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
}</pre>
</div>

</body></html>