Get Public Retriever Template
Get retriever configuration as a reusable template.
Returns the published retriever’s configuration in a format that can be directly used to create your own retriever. This is perfect for discovering patterns and adapting them to your own data.
Authentication:
- NO authentication required - this endpoint is completely public
- Anyone can get the template if they know the public_name
Use Case:
- Browse public retrievers to find patterns you like
- GET this endpoint to get the full configuration
- Copy the config and modify for your needs (especially
collection_identifiers) - POST to
/v1/retrieversto create your own retriever - Optionally publish it with the same display_config
What’s included:
- Retriever configuration (stages, input_schema, budget_limits)
- Display configuration (for publishing with similar UI)
- Original metadata for reference
What you need to change:
collection_identifiers: Replace with your own collection IDsretriever_name: Give it a unique name- Optionally modify stages, inputs, display_config as needed
Example:
# 1. Get the template
curl -X GET "https://api.mixpeek.com/v1/public/retrievers/video-search/template"
# 2. Modify the response and create your own retriever
curl -X POST "https://api.mixpeek.com/v1/retrievers" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"retriever_name": "my_video_search",
"collection_identifiers": ["my_videos"],
"stages": [...], # From template
"input_schema": {...}, # From template
"budget_limits": {...}, # From template
"display_config": {...} # From template (optional)
}'
Response includes:
- All retriever configuration fields
- Display config for publishing (optional to use)
- Source reference (where this template came from)
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
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
Original retriever name (you'll change this when creating your own). Provided as reference.
"video-search-example"
"product-catalog-demo"
IMPORTANT: These are the original collections. You MUST replace these with your own collection identifiers when creating a retriever from this template.
Pipeline stages configuration. You can use as-is or modify for your needs. This is the core retrieval logic.
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 for execution. You can adjust these based on your needs.
Public name of the source retriever (for reference)
"video-search"
"product-catalog"
Public URL of the source retriever (to view it in action)
"https://mxp.co/r/video-search"
Original retriever description (you can use or modify this). Provides context about what this retriever does.
Original tags (optional, for reference)
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.
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.

