Skip to main content
GET
Get Public Retriever Template

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

public_name
string
required

Public name of the published retriever

Response

Successful Response

Response containing public retriever configuration as a reusable template.

This returns the retriever's configuration in a format that can be directly used in a CreateRetrieverRequest. Users can copy this config, modify it for their needs (e.g., change collection_identifiers), and create their own retriever.

Use Case: 1. Browse public retrievers to find patterns you like 2. GET /public/retrievers/{public_name}/template to get the config 3. Modify collection_identifiers and other fields as needed 4. POST /retrievers to create your own retriever with this config 5. Optionally POST /retrievers/{id}/publish to publish it similarly

retriever_name
string
required

Original retriever name (you'll change this when creating your own). Provided as reference.

Examples:

"video-search-example"

"product-catalog-demo"

collection_identifiers
string[]
required

IMPORTANT: These are the original collections. You MUST replace these with your own collection identifiers when creating a retriever from this template.

Examples:
stages
Stages · object[]
required

Pipeline stages configuration. You can use as-is or modify for your needs. This is the core retrieval logic.

input_schema
Input Schema · object
required

Input schema defining expected inputs. If you change the input field names, make sure to update references in stages (e.g., {{inputs.query}}).

budget_limits
Budget Limits · object
required

Budget limits for execution. You can adjust these based on your needs.

source_public_name
string
required

Public name of the source retriever (for reference)

Examples:

"video-search"

"product-catalog"

source_public_url
string
required

Public URL of the source retriever (to view it in action)

Example:

"https://mxp.co/r/video-search"

description
string | null

Original retriever description (you can use or modify this). Provides context about what this retriever does.

tags
string[]

Original tags (optional, for reference)

display_config
DisplayConfig · object | null

OPTIONAL: Display configuration used for the public interface. Include this if you plan to publish your retriever and want to use a similar UI design. Otherwise, you can omit it.

Example:
feature_extractors
Feature Extractors · object[] | null

Feature extractors from all collections used by this retriever. Each extractor includes: feature_extractor_name, version, params, input_mappings, collection_id, and collection_name for reference. Shows how each collection processes data into searchable features.