Method: locations.retrieveContexts

Full name: projects.locations.retrieveContexts

Retrieves relevant contexts for a query.

Endpoint

post https://{service-endpoint}/v1beta1/{parent}:retrieveContexts

Where {service-endpoint} is one of the supported service endpoints.

Path parameters

parent string

Required. The resource name of the Location from which to retrieve RagContexts. The users must have permission to make a call in the project. Format: projects/{project}/locations/{location}.

Request body

The request body contains data with the following structure:

Fields
query object (RagQuery)

Required. Single RAG retrieve query.

data_source Union type
Data Source to retrieve contexts. data_source can be only one of the following:
vertexRagStore object (VertexRagStore)

The data source for Vertex RagStore.

Response body

Response message for VertexRagService.RetrieveContexts.

If successful, the response body contains data with the following structure:

Fields
contexts object (RagContexts)

The contexts of the query.

JSON representation 
{
  "contexts": {
    object (RagContexts)
  }
}

VertexRagStore

The data source for Vertex RagStore.

Fields
ragCorpora[]
(deprecated) string

Optional. Deprecated. Please use ragResources to specify the data source.

ragResources[] object (RagResource)

Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.

vectorDistanceThreshold
(deprecated) number

Optional. Only return contexts with vector distance smaller than the threshold.

JSON representation 
{
  "ragCorpora": [
    string
  ],
  "ragResources": [
    {
      object (RagResource)
    }
  ],
  "vectorDistanceThreshold": number
}

RagResource

The definition of the Rag resource.

Fields
ragCorpus string

Optional. RagCorpora resource name. Format: projects/{project}/locations/{location}/ragCorpora/{ragCorpus}

ragFileIds[] string

Optional. ragFileId. The files should be in the same ragCorpus set in ragCorpus field.

JSON representation 
{
  "ragCorpus": string,
  "ragFileIds": [
    string
  ]
}

RagQuery

A query to retrieve relevant contexts.

Fields
similarityTopK
(deprecated) integer

Optional. The number of contexts to retrieve.

ranking
(deprecated) object (Ranking)

Optional. Configurations for hybrid search results ranking.

ragRetrievalConfig object (RagRetrievalConfig)

Optional. The retrieval config for the query.

query Union type
The query to retrieve contexts. Currently only text query is supported. query can be only one of the following:
text string

Optional. The query in text format to get relevant contexts.

JSON representation 
{
  "similarityTopK": integer,
  "ranking": {
    object (Ranking)
  },
  "ragRetrievalConfig": {
    object (RagRetrievalConfig)
  },

  // query
  "text": string
  // Union type
}

Ranking

Configurations for hybrid search results ranking.

Fields
alpha number

Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.

JSON representation 
{
  "alpha": number
}

RagContexts

Relevant contexts for one query.

Fields
contexts[] object (Context)

All its contexts.

JSON representation 
{
  "contexts": [
    {
      object (Context)
    }
  ]
}

Context

A context of the query.

Fields
sourceUri string

If the file is imported from Cloud Storage or Google Drive, sourceUri will be original file URI in Cloud Storage or Google Drive; if file is uploaded, sourceUri will be file display name.

sourceDisplayName string

The file display name.

text string

The text chunk.

distance
(deprecated) number

The distance between the query dense embedding vector and the context text vector.

sparseDistance
(deprecated) number

The distance between the query sparse embedding vector and the context text vector.

chunk object (RagChunk)

Context of the retrieved chunk.

score number

According to the underlying Vector DB and the selected metric type, the score can be either the distance or the similarity between the query and the context and its range depends on the metric type.

For example, if the metric type is COSINE_DISTANCE, it represents the distance between the query and the context. The larger the distance, the less relevant the context is to the query. The range is [0, 2], while 0 means the most relevant and 2 means the least relevant.

JSON representation 
{
  "sourceUri": string,
  "sourceDisplayName": string,
  "text": string,
  "distance": number,
  "sparseDistance": number,
  "chunk": {
    object (RagChunk)
  },
  "score": number
}