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.
["public_videos"]["demo_products", "demo_images"]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://apps.mixpeek.com/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.
{
"components": {
"result_card": {
"card_click_action": "viewDetails",
"field_order": ["title", "description", "price"],
"layout": "vertical",
"show_find_similar": true,
"show_thumbnail": true
},
"result_layout": "grid",
"show_hero": true,
"show_results_header": true,
"show_search": true
},
"custom_cta": {
"label": "Search Tips",
"markdown_content": "# Search Tips\n\n- Use quotes for exact phrases\n- Try descriptive terms"
},
"description": "Search through our product catalog",
"exposed_fields": [
"title",
"description",
"price",
"image_url"
],
"external_links": [
{
"name": "GitHub Repository",
"url": "https://github.com/mixpeek/product-search"
},
{
"name": "Blog Post",
"url": "https://blog.mixpeek.com/building-product-search"
}
],
"field_config": {
"price": {
"format": "number",
"format_options": {
"decimals": 2,
"label": "Price",
"prefix": "$"
}
},
"title": {
"format": "text",
"format_options": {
"label": "Product Name",
"truncate_chars": 60
}
}
},
"field_mappings": {
"thumbnail": "image_url",
"title": "title"
},
"inputs": [
{
"field_name": "query",
"field_schema": {
"description": "Search query",
"examples": ["wireless headphones", "laptop"],
"type": "string"
},
"input_type": "text",
"label": "Search Products",
"order": 0,
"placeholder": "What are you looking for?",
"required": true
}
],
"layout": {
"columns": 3,
"gap": "16px",
"mode": "grid"
},
"logo_url": "https://example.com/logo.png",
"markdowns": [
{
"content": "# AI-Powered Product Search\n\nOur search uses **machine learning** to understand your queries and find the most relevant products.\n\n## Features\n\n- **Semantic Search**: Understands meaning, not just keywords\n- **Visual Search**: Upload images to find similar products\n- **Smart Filters**: Automatically suggests relevant filters",
"title": "How it Works"
},
{
"content": "## Tips for Better Results\n\n1. Use descriptive terms (e.g., \"wireless noise-canceling headphones\")\n2. Try different keywords if you don't find what you're looking for\n3. Use filters to narrow down results\n\n*Happy searching!*",
"title": "Search Guide"
}
],
"template_type": "media-search",
"theme": {
"border_radius": "12px",
"card_style": "elevated",
"font_family": "Inter, sans-serif",
"primary_color": "#007AFF"
},
"title": "Product Search"
}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.