Google VertexAI RAG Retrieval Query

Overview

Use this Snap to retrieve embeddings from the RAG corpus.


Snap dialog

Prerequisites

You need to have one of the following accounts configured for your Google VertexAI Snaps:

Snap views

Type Description Examples of upstream and downstream Snaps
Input This Snap has at the most one document input view.
  • JSON Generator
Output

his Snap has at the most one document output view. 

{
                  "contexts" : [ {
                  "chunk" : {
                  "text" : "test-text"
                  },
                  "score" : 0.9,
                  "text" : "test-text"
                  } ]
                  }
  • Google GenAI Prompt Generator
Learn more about Error handling.

Snap settings

Legend:
  • Expression icon (): Allows using JavaScript syntax to access SnapLogic Expressions to set field values dynamically (if enabled). If disabled, you can provide a static value. Learn more.
  • SnapGPT (): Generates SnapLogic Expressions based on natural language using SnapGPT. Learn more.
  • Suggestion icon (): Populates a list of values dynamically based on your Snap configuration. You can select only one attribute at a time using the icon. Type into the field if it supports a comma-separated list of values.
  • Upload : Uploads files. Learn more.
Learn more about the icons in the Snap settings dialog.
Field/Field set Type Description
Label String

Required. Specify a unique name for the Snap. Modify this to be more appropriate, especially if more than one of the same Snaps is in the pipeline.

Default value: Google VertexAI RAG Corpus Get File

Example: Get report document
Location String/Expression/ Suggestion

The location of the corpus.

Default value: N/A

Example: global / us-central1
Corpus name String/Expression/ Suggestion

Required. The name of the corpus.

Default value: N/A

Example: 7991637538768945152:test-corpus
Text String/Expression

Required. The text to query.

Default value: N/A

Example: How many products does the company sell?
Top K Integer/Expression

Maximum number of documents to retrieve based on relevance.

Default value: N/A

Example: .10
Filter configurations

Configuration for corpus-level document filtering.
Vector threshold type Dropdown list/Expression

Defines threshold method: distance or similarity.

  • vectorSimilarityThreshold
  • vectorDistanceThreshold

Default value: N/A

Example: vectorSimilarityThreshold
Vector threshold value Decimal/Expression

Numerical value applied to the vector threshold.

Default value: N/A

Example: 0.75
Metadata filter String/Expression

Filter documents using metadata key-value constraints.

Default value: N/A

Example: date
Ranking configurations

Configuration for ranking retrieved results.
Ranking type Dropdown list/Expression

Select ranking algorithm for retrieved results.

  • llmRanker
  • rankService

Default value: N/A

Example: rankService
Ranking value String/Expression

Parameter controlling how results are ranked.

Default value: N/A

Example: Expression { "model_name": "semantic-ranker-default@latest" }
Snap execution Dropdown list
Choose one of the three modes in which the Snap executes. Available options are:
  • Validate & Execute: Performs limited execution of the Snap and generates a data preview during pipeline validation. Subsequently, performs full execution of the Snap (unlimited records) during pipeline runtime.
  • Execute only: Performs full execution of the Snap during pipeline execution without generating preview data.
  • Disabled: Disables the Snap and all Snaps that are downstream from it.

Default value: Validate & Execute

Example: Execute only