Clone Collection
curl --request POST \
--url https://api.mixpeek.com/v1/collections/{collection_identifier}/clone \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"collection_name": "<string>",
"description": "Cloned from product_embeddings with CLIP v2",
"source": {
"bucket_ids": [
"bkt_marketing_videos"
],
"type": "bucket"
},
"feature_extractor": {
"feature_extractor_name": "text_extractor",
"field_passthrough": [
{
"required": true,
"source_path": "title"
},
{
"source_path": "author"
}
],
"input_mappings": {
"text": "content"
},
"parameters": {
"model": "text-embedding-3-small"
},
"version": "v1"
},
"enabled": true,
"metadata": {},
"taxonomy_applications": [
{
"taxonomy_id": "<string>",
"execution_mode": "materialize",
"target_collection_id": "<string>",
"scroll_filters": {
"AND": [
{
"field": "name",
"operator": "eq",
"value": "John"
},
{
"field": "age",
"operator": "gte",
"value": 30
}
],
"OR": [
{
"field": "status",
"operator": "eq",
"value": "active"
},
{
"field": "role",
"operator": "eq",
"value": "admin"
}
],
"NOT": [
{
"field": "department",
"operator": "eq",
"value": "HR"
},
{
"field": "location",
"operator": "eq",
"value": "remote"
}
],
"case_sensitive": true
},
"execution_phase": 1,
"priority": 0,
"hierarchical_enrichment_style": "combined"
}
]
}
'import requests
url = "https://api.mixpeek.com/v1/collections/{collection_identifier}/clone"
payload = {
"collection_name": "<string>",
"description": "Cloned from product_embeddings with CLIP v2",
"source": {
"bucket_ids": ["bkt_marketing_videos"],
"type": "bucket"
},
"feature_extractor": {
"feature_extractor_name": "text_extractor",
"field_passthrough": [{
"required": True,
"source_path": "title"
}, { "source_path": "author" }],
"input_mappings": { "text": "content" },
"parameters": { "model": "text-embedding-3-small" },
"version": "v1"
},
"enabled": True,
"metadata": {},
"taxonomy_applications": [
{
"taxonomy_id": "<string>",
"execution_mode": "materialize",
"target_collection_id": "<string>",
"scroll_filters": {
"AND": [
{
"field": "name",
"operator": "eq",
"value": "John"
},
{
"field": "age",
"operator": "gte",
"value": 30
}
],
"OR": [
{
"field": "status",
"operator": "eq",
"value": "active"
},
{
"field": "role",
"operator": "eq",
"value": "admin"
}
],
"NOT": [
{
"field": "department",
"operator": "eq",
"value": "HR"
},
{
"field": "location",
"operator": "eq",
"value": "remote"
}
],
"case_sensitive": True
},
"execution_phase": 1,
"priority": 0,
"hierarchical_enrichment_style": "combined"
}
]
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
collection_name: '<string>',
description: 'Cloned from product_embeddings with CLIP v2',
source: {bucket_ids: ['bkt_marketing_videos'], type: 'bucket'},
feature_extractor: {
feature_extractor_name: 'text_extractor',
field_passthrough: [{required: true, source_path: 'title'}, {source_path: 'author'}],
input_mappings: {text: 'content'},
parameters: {model: 'text-embedding-3-small'},
version: 'v1'
},
enabled: true,
metadata: {},
taxonomy_applications: [
{
taxonomy_id: '<string>',
execution_mode: 'materialize',
target_collection_id: '<string>',
scroll_filters: {
AND: [
{field: 'name', operator: 'eq', value: 'John'},
{field: 'age', operator: 'gte', value: 30}
],
OR: [
{field: 'status', operator: 'eq', value: 'active'},
{field: 'role', operator: 'eq', value: 'admin'}
],
NOT: [
{field: 'department', operator: 'eq', value: 'HR'},
{field: 'location', operator: 'eq', value: 'remote'}
],
case_sensitive: true
},
execution_phase: 1,
priority: 0,
hierarchical_enrichment_style: 'combined'
}
]
})
};
fetch('https://api.mixpeek.com/v1/collections/{collection_identifier}/clone', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.mixpeek.com/v1/collections/{collection_identifier}/clone",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'collection_name' => '<string>',
'description' => 'Cloned from product_embeddings with CLIP v2',
'source' => [
'bucket_ids' => [
'bkt_marketing_videos'
],
'type' => 'bucket'
],
'feature_extractor' => [
'feature_extractor_name' => 'text_extractor',
'field_passthrough' => [
[
'required' => true,
'source_path' => 'title'
],
[
'source_path' => 'author'
]
],
'input_mappings' => [
'text' => 'content'
],
'parameters' => [
'model' => 'text-embedding-3-small'
],
'version' => 'v1'
],
'enabled' => true,
'metadata' => [
],
'taxonomy_applications' => [
[
'taxonomy_id' => '<string>',
'execution_mode' => 'materialize',
'target_collection_id' => '<string>',
'scroll_filters' => [
'AND' => [
[
'field' => 'name',
'operator' => 'eq',
'value' => 'John'
],
[
'field' => 'age',
'operator' => 'gte',
'value' => 30
]
],
'OR' => [
[
'field' => 'status',
'operator' => 'eq',
'value' => 'active'
],
[
'field' => 'role',
'operator' => 'eq',
'value' => 'admin'
]
],
'NOT' => [
[
'field' => 'department',
'operator' => 'eq',
'value' => 'HR'
],
[
'field' => 'location',
'operator' => 'eq',
'value' => 'remote'
]
],
'case_sensitive' => true
],
'execution_phase' => 1,
'priority' => 0,
'hierarchical_enrichment_style' => 'combined'
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.mixpeek.com/v1/collections/{collection_identifier}/clone"
payload := strings.NewReader("{\n \"collection_name\": \"<string>\",\n \"description\": \"Cloned from product_embeddings with CLIP v2\",\n \"source\": {\n \"bucket_ids\": [\n \"bkt_marketing_videos\"\n ],\n \"type\": \"bucket\"\n },\n \"feature_extractor\": {\n \"feature_extractor_name\": \"text_extractor\",\n \"field_passthrough\": [\n {\n \"required\": true,\n \"source_path\": \"title\"\n },\n {\n \"source_path\": \"author\"\n }\n ],\n \"input_mappings\": {\n \"text\": \"content\"\n },\n \"parameters\": {\n \"model\": \"text-embedding-3-small\"\n },\n \"version\": \"v1\"\n },\n \"enabled\": true,\n \"metadata\": {},\n \"taxonomy_applications\": [\n {\n \"taxonomy_id\": \"<string>\",\n \"execution_mode\": \"materialize\",\n \"target_collection_id\": \"<string>\",\n \"scroll_filters\": {\n \"AND\": [\n {\n \"field\": \"name\",\n \"operator\": \"eq\",\n \"value\": \"John\"\n },\n {\n \"field\": \"age\",\n \"operator\": \"gte\",\n \"value\": 30\n }\n ],\n \"OR\": [\n {\n \"field\": \"status\",\n \"operator\": \"eq\",\n \"value\": \"active\"\n },\n {\n \"field\": \"role\",\n \"operator\": \"eq\",\n \"value\": \"admin\"\n }\n ],\n \"NOT\": [\n {\n \"field\": \"department\",\n \"operator\": \"eq\",\n \"value\": \"HR\"\n },\n {\n \"field\": \"location\",\n \"operator\": \"eq\",\n \"value\": \"remote\"\n }\n ],\n \"case_sensitive\": true\n },\n \"execution_phase\": 1,\n \"priority\": 0,\n \"hierarchical_enrichment_style\": \"combined\"\n }\n ]\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.mixpeek.com/v1/collections/{collection_identifier}/clone")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"collection_name\": \"<string>\",\n \"description\": \"Cloned from product_embeddings with CLIP v2\",\n \"source\": {\n \"bucket_ids\": [\n \"bkt_marketing_videos\"\n ],\n \"type\": \"bucket\"\n },\n \"feature_extractor\": {\n \"feature_extractor_name\": \"text_extractor\",\n \"field_passthrough\": [\n {\n \"required\": true,\n \"source_path\": \"title\"\n },\n {\n \"source_path\": \"author\"\n }\n ],\n \"input_mappings\": {\n \"text\": \"content\"\n },\n \"parameters\": {\n \"model\": \"text-embedding-3-small\"\n },\n \"version\": \"v1\"\n },\n \"enabled\": true,\n \"metadata\": {},\n \"taxonomy_applications\": [\n {\n \"taxonomy_id\": \"<string>\",\n \"execution_mode\": \"materialize\",\n \"target_collection_id\": \"<string>\",\n \"scroll_filters\": {\n \"AND\": [\n {\n \"field\": \"name\",\n \"operator\": \"eq\",\n \"value\": \"John\"\n },\n {\n \"field\": \"age\",\n \"operator\": \"gte\",\n \"value\": 30\n }\n ],\n \"OR\": [\n {\n \"field\": \"status\",\n \"operator\": \"eq\",\n \"value\": \"active\"\n },\n {\n \"field\": \"role\",\n \"operator\": \"eq\",\n \"value\": \"admin\"\n }\n ],\n \"NOT\": [\n {\n \"field\": \"department\",\n \"operator\": \"eq\",\n \"value\": \"HR\"\n },\n {\n \"field\": \"location\",\n \"operator\": \"eq\",\n \"value\": \"remote\"\n }\n ],\n \"case_sensitive\": true\n },\n \"execution_phase\": 1,\n \"priority\": 0,\n \"hierarchical_enrichment_style\": \"combined\"\n }\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mixpeek.com/v1/collections/{collection_identifier}/clone")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"collection_name\": \"<string>\",\n \"description\": \"Cloned from product_embeddings with CLIP v2\",\n \"source\": {\n \"bucket_ids\": [\n \"bkt_marketing_videos\"\n ],\n \"type\": \"bucket\"\n },\n \"feature_extractor\": {\n \"feature_extractor_name\": \"text_extractor\",\n \"field_passthrough\": [\n {\n \"required\": true,\n \"source_path\": \"title\"\n },\n {\n \"source_path\": \"author\"\n }\n ],\n \"input_mappings\": {\n \"text\": \"content\"\n },\n \"parameters\": {\n \"model\": \"text-embedding-3-small\"\n },\n \"version\": \"v1\"\n },\n \"enabled\": true,\n \"metadata\": {},\n \"taxonomy_applications\": [\n {\n \"taxonomy_id\": \"<string>\",\n \"execution_mode\": \"materialize\",\n \"target_collection_id\": \"<string>\",\n \"scroll_filters\": {\n \"AND\": [\n {\n \"field\": \"name\",\n \"operator\": \"eq\",\n \"value\": \"John\"\n },\n {\n \"field\": \"age\",\n \"operator\": \"gte\",\n \"value\": 30\n }\n ],\n \"OR\": [\n {\n \"field\": \"status\",\n \"operator\": \"eq\",\n \"value\": \"active\"\n },\n {\n \"field\": \"role\",\n \"operator\": \"eq\",\n \"value\": \"admin\"\n }\n ],\n \"NOT\": [\n {\n \"field\": \"department\",\n \"operator\": \"eq\",\n \"value\": \"HR\"\n },\n {\n \"field\": \"location\",\n \"operator\": \"eq\",\n \"value\": \"remote\"\n }\n ],\n \"case_sensitive\": true\n },\n \"execution_phase\": 1,\n \"priority\": 0,\n \"hierarchical_enrichment_style\": \"combined\"\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"collection": {
"collection_name": "<string>",
"feature_extractor": {
"feature_extractor_name": "<string>",
"version": "<string>",
"feature_extractor_id": "<string>",
"params": {},
"parameters": {
"extractor_type": "audio_fingerprint_extractor",
"normalize_embeddings": true,
"sample_rate": 48000,
"segment_duration_sec": 5,
"segment_hop_sec": 2.5
},
"input_mappings": {
"image": "product_image",
"text": "title"
},
"field_passthrough": [
{
"source_path": "<string>",
"target_path": "title",
"default": "Unknown",
"required": false
}
],
"include_all_source_fields": false
},
"source": {
"bucket_ids": [
"bkt_marketing_videos"
],
"source_namespace_id": "<string>",
"collection_id": "col_video_frames",
"collection_ids": [
"col_us_products",
"col_eu_products"
],
"inherited_bucket_ids": [
"bkt_marketing_videos"
],
"source_filters": {
"filters": {
"AND": [
{
"field": "blobs.type",
"operator": "eq",
"value": "video"
}
]
}
}
},
"collection_id": "<string>",
"description": "Video frames extracted at 1 FPS with CLIP embeddings",
"input_schema": {
"properties": {
"title": {
"type": "string"
},
"content": {
"type": "text"
}
}
},
"output_schema": {
"properties": {
"title": {
"type": "string"
},
"text_extractor_v1_embedding": {
"type": "array"
}
}
},
"source_bucket_schemas": null,
"source_lineage": [
{
"source_config": {
"bucket_ids": [
"bkt_marketing_videos"
],
"source_namespace_id": "<string>",
"collection_id": "col_video_frames",
"collection_ids": [
"col_us_products",
"col_eu_products"
],
"inherited_bucket_ids": [
"bkt_marketing_videos"
],
"source_filters": {
"filters": {
"AND": [
{
"field": "blobs.type",
"operator": "eq",
"value": "video"
}
]
}
}
},
"feature_extractor": {
"feature_extractor_name": "<string>",
"version": "<string>",
"feature_extractor_id": "<string>",
"params": {},
"parameters": {
"extractor_type": "audio_fingerprint_extractor",
"normalize_embeddings": true,
"sample_rate": 48000,
"segment_duration_sec": 5,
"segment_hop_sec": 2.5
},
"input_mappings": {
"image": "product_image",
"text": "title"
},
"field_passthrough": [
{
"source_path": "<string>",
"target_path": "title",
"default": "Unknown",
"required": false
}
],
"include_all_source_fields": false
},
"output_schema": {
"properties": {}
}
}
],
"vector_indexes": [
"<unknown>"
],
"payload_indexes": [
"<unknown>"
],
"embedding_task": "<string>",
"enabled": true,
"metadata": {
"environment": "production",
"project": "Q4_campaign",
"team": "data-science"
},
"schedule": {
"trigger_type": "<string>",
"schedule_config": {},
"description": "<string>"
},
"trigger_id": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"lifecycle_state": "active",
"s3_vector_index": "<string>",
"last_lifecycle_transition": "2023-11-07T05:31:56Z",
"tiering_rules": [
{
"enabled": false,
"threshold_days": 123
}
],
"document_count": 0,
"schema_version": 1,
"last_schema_sync": "2023-11-07T05:31:56Z",
"schema_sync_enabled": true,
"document_schema": null,
"schema_validation": "off",
"taxonomy_applications": null,
"cluster_applications": null,
"alert_applications": null,
"retriever_enrichments": null
},
"source_collection_id": "<string>"
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}Collections
Clone Collection
Clone a collection with optional modifications.
Purpose: Creates a NEW collection (with new ID) based on an existing one. This is the recommended way to iterate on collection designs when you need to modify core configuration that PATCH doesn’t allow (source, feature_extractor, field_passthrough).
Clone vs PATCH vs Template:
- PATCH: Update metadata only (enabled, metadata, taxonomy_applications)
- Clone: Copy and modify core configuration (source, feature_extractor)
- Template: Start from a pre-configured pattern (for new projects)
Common Use Cases:
- Change feature extractor configuration (model, parameters)
- Modify field_passthrough to include/exclude fields
- Switch to different source (bucket or collection)
- Test modifications before replacing production collection
- Create variants (e.g., different embedding models)
How it works:
- Source collection is copied
- You provide a new name (REQUIRED)
- Optionally override any other fields
- A new collection is created with a new ID
- Original collection remains unchanged
POST
/
v1
/
collections
/
{collection_identifier}
/
clone
Clone Collection
curl --request POST \
--url https://api.mixpeek.com/v1/collections/{collection_identifier}/clone \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"collection_name": "<string>",
"description": "Cloned from product_embeddings with CLIP v2",
"source": {
"bucket_ids": [
"bkt_marketing_videos"
],
"type": "bucket"
},
"feature_extractor": {
"feature_extractor_name": "text_extractor",
"field_passthrough": [
{
"required": true,
"source_path": "title"
},
{
"source_path": "author"
}
],
"input_mappings": {
"text": "content"
},
"parameters": {
"model": "text-embedding-3-small"
},
"version": "v1"
},
"enabled": true,
"metadata": {},
"taxonomy_applications": [
{
"taxonomy_id": "<string>",
"execution_mode": "materialize",
"target_collection_id": "<string>",
"scroll_filters": {
"AND": [
{
"field": "name",
"operator": "eq",
"value": "John"
},
{
"field": "age",
"operator": "gte",
"value": 30
}
],
"OR": [
{
"field": "status",
"operator": "eq",
"value": "active"
},
{
"field": "role",
"operator": "eq",
"value": "admin"
}
],
"NOT": [
{
"field": "department",
"operator": "eq",
"value": "HR"
},
{
"field": "location",
"operator": "eq",
"value": "remote"
}
],
"case_sensitive": true
},
"execution_phase": 1,
"priority": 0,
"hierarchical_enrichment_style": "combined"
}
]
}
'import requests
url = "https://api.mixpeek.com/v1/collections/{collection_identifier}/clone"
payload = {
"collection_name": "<string>",
"description": "Cloned from product_embeddings with CLIP v2",
"source": {
"bucket_ids": ["bkt_marketing_videos"],
"type": "bucket"
},
"feature_extractor": {
"feature_extractor_name": "text_extractor",
"field_passthrough": [{
"required": True,
"source_path": "title"
}, { "source_path": "author" }],
"input_mappings": { "text": "content" },
"parameters": { "model": "text-embedding-3-small" },
"version": "v1"
},
"enabled": True,
"metadata": {},
"taxonomy_applications": [
{
"taxonomy_id": "<string>",
"execution_mode": "materialize",
"target_collection_id": "<string>",
"scroll_filters": {
"AND": [
{
"field": "name",
"operator": "eq",
"value": "John"
},
{
"field": "age",
"operator": "gte",
"value": 30
}
],
"OR": [
{
"field": "status",
"operator": "eq",
"value": "active"
},
{
"field": "role",
"operator": "eq",
"value": "admin"
}
],
"NOT": [
{
"field": "department",
"operator": "eq",
"value": "HR"
},
{
"field": "location",
"operator": "eq",
"value": "remote"
}
],
"case_sensitive": True
},
"execution_phase": 1,
"priority": 0,
"hierarchical_enrichment_style": "combined"
}
]
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
collection_name: '<string>',
description: 'Cloned from product_embeddings with CLIP v2',
source: {bucket_ids: ['bkt_marketing_videos'], type: 'bucket'},
feature_extractor: {
feature_extractor_name: 'text_extractor',
field_passthrough: [{required: true, source_path: 'title'}, {source_path: 'author'}],
input_mappings: {text: 'content'},
parameters: {model: 'text-embedding-3-small'},
version: 'v1'
},
enabled: true,
metadata: {},
taxonomy_applications: [
{
taxonomy_id: '<string>',
execution_mode: 'materialize',
target_collection_id: '<string>',
scroll_filters: {
AND: [
{field: 'name', operator: 'eq', value: 'John'},
{field: 'age', operator: 'gte', value: 30}
],
OR: [
{field: 'status', operator: 'eq', value: 'active'},
{field: 'role', operator: 'eq', value: 'admin'}
],
NOT: [
{field: 'department', operator: 'eq', value: 'HR'},
{field: 'location', operator: 'eq', value: 'remote'}
],
case_sensitive: true
},
execution_phase: 1,
priority: 0,
hierarchical_enrichment_style: 'combined'
}
]
})
};
fetch('https://api.mixpeek.com/v1/collections/{collection_identifier}/clone', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.mixpeek.com/v1/collections/{collection_identifier}/clone",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'collection_name' => '<string>',
'description' => 'Cloned from product_embeddings with CLIP v2',
'source' => [
'bucket_ids' => [
'bkt_marketing_videos'
],
'type' => 'bucket'
],
'feature_extractor' => [
'feature_extractor_name' => 'text_extractor',
'field_passthrough' => [
[
'required' => true,
'source_path' => 'title'
],
[
'source_path' => 'author'
]
],
'input_mappings' => [
'text' => 'content'
],
'parameters' => [
'model' => 'text-embedding-3-small'
],
'version' => 'v1'
],
'enabled' => true,
'metadata' => [
],
'taxonomy_applications' => [
[
'taxonomy_id' => '<string>',
'execution_mode' => 'materialize',
'target_collection_id' => '<string>',
'scroll_filters' => [
'AND' => [
[
'field' => 'name',
'operator' => 'eq',
'value' => 'John'
],
[
'field' => 'age',
'operator' => 'gte',
'value' => 30
]
],
'OR' => [
[
'field' => 'status',
'operator' => 'eq',
'value' => 'active'
],
[
'field' => 'role',
'operator' => 'eq',
'value' => 'admin'
]
],
'NOT' => [
[
'field' => 'department',
'operator' => 'eq',
'value' => 'HR'
],
[
'field' => 'location',
'operator' => 'eq',
'value' => 'remote'
]
],
'case_sensitive' => true
],
'execution_phase' => 1,
'priority' => 0,
'hierarchical_enrichment_style' => 'combined'
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.mixpeek.com/v1/collections/{collection_identifier}/clone"
payload := strings.NewReader("{\n \"collection_name\": \"<string>\",\n \"description\": \"Cloned from product_embeddings with CLIP v2\",\n \"source\": {\n \"bucket_ids\": [\n \"bkt_marketing_videos\"\n ],\n \"type\": \"bucket\"\n },\n \"feature_extractor\": {\n \"feature_extractor_name\": \"text_extractor\",\n \"field_passthrough\": [\n {\n \"required\": true,\n \"source_path\": \"title\"\n },\n {\n \"source_path\": \"author\"\n }\n ],\n \"input_mappings\": {\n \"text\": \"content\"\n },\n \"parameters\": {\n \"model\": \"text-embedding-3-small\"\n },\n \"version\": \"v1\"\n },\n \"enabled\": true,\n \"metadata\": {},\n \"taxonomy_applications\": [\n {\n \"taxonomy_id\": \"<string>\",\n \"execution_mode\": \"materialize\",\n \"target_collection_id\": \"<string>\",\n \"scroll_filters\": {\n \"AND\": [\n {\n \"field\": \"name\",\n \"operator\": \"eq\",\n \"value\": \"John\"\n },\n {\n \"field\": \"age\",\n \"operator\": \"gte\",\n \"value\": 30\n }\n ],\n \"OR\": [\n {\n \"field\": \"status\",\n \"operator\": \"eq\",\n \"value\": \"active\"\n },\n {\n \"field\": \"role\",\n \"operator\": \"eq\",\n \"value\": \"admin\"\n }\n ],\n \"NOT\": [\n {\n \"field\": \"department\",\n \"operator\": \"eq\",\n \"value\": \"HR\"\n },\n {\n \"field\": \"location\",\n \"operator\": \"eq\",\n \"value\": \"remote\"\n }\n ],\n \"case_sensitive\": true\n },\n \"execution_phase\": 1,\n \"priority\": 0,\n \"hierarchical_enrichment_style\": \"combined\"\n }\n ]\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.mixpeek.com/v1/collections/{collection_identifier}/clone")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"collection_name\": \"<string>\",\n \"description\": \"Cloned from product_embeddings with CLIP v2\",\n \"source\": {\n \"bucket_ids\": [\n \"bkt_marketing_videos\"\n ],\n \"type\": \"bucket\"\n },\n \"feature_extractor\": {\n \"feature_extractor_name\": \"text_extractor\",\n \"field_passthrough\": [\n {\n \"required\": true,\n \"source_path\": \"title\"\n },\n {\n \"source_path\": \"author\"\n }\n ],\n \"input_mappings\": {\n \"text\": \"content\"\n },\n \"parameters\": {\n \"model\": \"text-embedding-3-small\"\n },\n \"version\": \"v1\"\n },\n \"enabled\": true,\n \"metadata\": {},\n \"taxonomy_applications\": [\n {\n \"taxonomy_id\": \"<string>\",\n \"execution_mode\": \"materialize\",\n \"target_collection_id\": \"<string>\",\n \"scroll_filters\": {\n \"AND\": [\n {\n \"field\": \"name\",\n \"operator\": \"eq\",\n \"value\": \"John\"\n },\n {\n \"field\": \"age\",\n \"operator\": \"gte\",\n \"value\": 30\n }\n ],\n \"OR\": [\n {\n \"field\": \"status\",\n \"operator\": \"eq\",\n \"value\": \"active\"\n },\n {\n \"field\": \"role\",\n \"operator\": \"eq\",\n \"value\": \"admin\"\n }\n ],\n \"NOT\": [\n {\n \"field\": \"department\",\n \"operator\": \"eq\",\n \"value\": \"HR\"\n },\n {\n \"field\": \"location\",\n \"operator\": \"eq\",\n \"value\": \"remote\"\n }\n ],\n \"case_sensitive\": true\n },\n \"execution_phase\": 1,\n \"priority\": 0,\n \"hierarchical_enrichment_style\": \"combined\"\n }\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mixpeek.com/v1/collections/{collection_identifier}/clone")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"collection_name\": \"<string>\",\n \"description\": \"Cloned from product_embeddings with CLIP v2\",\n \"source\": {\n \"bucket_ids\": [\n \"bkt_marketing_videos\"\n ],\n \"type\": \"bucket\"\n },\n \"feature_extractor\": {\n \"feature_extractor_name\": \"text_extractor\",\n \"field_passthrough\": [\n {\n \"required\": true,\n \"source_path\": \"title\"\n },\n {\n \"source_path\": \"author\"\n }\n ],\n \"input_mappings\": {\n \"text\": \"content\"\n },\n \"parameters\": {\n \"model\": \"text-embedding-3-small\"\n },\n \"version\": \"v1\"\n },\n \"enabled\": true,\n \"metadata\": {},\n \"taxonomy_applications\": [\n {\n \"taxonomy_id\": \"<string>\",\n \"execution_mode\": \"materialize\",\n \"target_collection_id\": \"<string>\",\n \"scroll_filters\": {\n \"AND\": [\n {\n \"field\": \"name\",\n \"operator\": \"eq\",\n \"value\": \"John\"\n },\n {\n \"field\": \"age\",\n \"operator\": \"gte\",\n \"value\": 30\n }\n ],\n \"OR\": [\n {\n \"field\": \"status\",\n \"operator\": \"eq\",\n \"value\": \"active\"\n },\n {\n \"field\": \"role\",\n \"operator\": \"eq\",\n \"value\": \"admin\"\n }\n ],\n \"NOT\": [\n {\n \"field\": \"department\",\n \"operator\": \"eq\",\n \"value\": \"HR\"\n },\n {\n \"field\": \"location\",\n \"operator\": \"eq\",\n \"value\": \"remote\"\n }\n ],\n \"case_sensitive\": true\n },\n \"execution_phase\": 1,\n \"priority\": 0,\n \"hierarchical_enrichment_style\": \"combined\"\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"collection": {
"collection_name": "<string>",
"feature_extractor": {
"feature_extractor_name": "<string>",
"version": "<string>",
"feature_extractor_id": "<string>",
"params": {},
"parameters": {
"extractor_type": "audio_fingerprint_extractor",
"normalize_embeddings": true,
"sample_rate": 48000,
"segment_duration_sec": 5,
"segment_hop_sec": 2.5
},
"input_mappings": {
"image": "product_image",
"text": "title"
},
"field_passthrough": [
{
"source_path": "<string>",
"target_path": "title",
"default": "Unknown",
"required": false
}
],
"include_all_source_fields": false
},
"source": {
"bucket_ids": [
"bkt_marketing_videos"
],
"source_namespace_id": "<string>",
"collection_id": "col_video_frames",
"collection_ids": [
"col_us_products",
"col_eu_products"
],
"inherited_bucket_ids": [
"bkt_marketing_videos"
],
"source_filters": {
"filters": {
"AND": [
{
"field": "blobs.type",
"operator": "eq",
"value": "video"
}
]
}
}
},
"collection_id": "<string>",
"description": "Video frames extracted at 1 FPS with CLIP embeddings",
"input_schema": {
"properties": {
"title": {
"type": "string"
},
"content": {
"type": "text"
}
}
},
"output_schema": {
"properties": {
"title": {
"type": "string"
},
"text_extractor_v1_embedding": {
"type": "array"
}
}
},
"source_bucket_schemas": null,
"source_lineage": [
{
"source_config": {
"bucket_ids": [
"bkt_marketing_videos"
],
"source_namespace_id": "<string>",
"collection_id": "col_video_frames",
"collection_ids": [
"col_us_products",
"col_eu_products"
],
"inherited_bucket_ids": [
"bkt_marketing_videos"
],
"source_filters": {
"filters": {
"AND": [
{
"field": "blobs.type",
"operator": "eq",
"value": "video"
}
]
}
}
},
"feature_extractor": {
"feature_extractor_name": "<string>",
"version": "<string>",
"feature_extractor_id": "<string>",
"params": {},
"parameters": {
"extractor_type": "audio_fingerprint_extractor",
"normalize_embeddings": true,
"sample_rate": 48000,
"segment_duration_sec": 5,
"segment_hop_sec": 2.5
},
"input_mappings": {
"image": "product_image",
"text": "title"
},
"field_passthrough": [
{
"source_path": "<string>",
"target_path": "title",
"default": "Unknown",
"required": false
}
],
"include_all_source_fields": false
},
"output_schema": {
"properties": {}
}
}
],
"vector_indexes": [
"<unknown>"
],
"payload_indexes": [
"<unknown>"
],
"embedding_task": "<string>",
"enabled": true,
"metadata": {
"environment": "production",
"project": "Q4_campaign",
"team": "data-science"
},
"schedule": {
"trigger_type": "<string>",
"schedule_config": {},
"description": "<string>"
},
"trigger_id": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"lifecycle_state": "active",
"s3_vector_index": "<string>",
"last_lifecycle_transition": "2023-11-07T05:31:56Z",
"tiering_rules": [
{
"enabled": false,
"threshold_days": 123
}
],
"document_count": 0,
"schema_version": 1,
"last_schema_sync": "2023-11-07T05:31:56Z",
"schema_sync_enabled": true,
"document_schema": null,
"schema_validation": "off",
"taxonomy_applications": null,
"cluster_applications": null,
"alert_applications": null,
"retriever_enrichments": null
},
"source_collection_id": "<string>"
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}{
"status": 123,
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"details": {}
},
"success": false
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Source collection ID or name to clone.
Body
application/json
Request to clone a collection with optional modifications.
Purpose: Cloning creates a NEW collection (with new ID) based on an existing one, allowing you to make changes that aren't allowed via PATCH (source, feature_extractor, field_passthrough). This is the recommended way to iterate on collection designs.
Clone vs Template vs Version:
- Clone: Copy THIS collection and modify it (for iteration/fixes)
- Template: Create collection from a reusable pattern (for new projects)
- Version: (Not implemented) - Use clone instead
Use Cases:
- Change feature extractor configuration without breaking production
- Modify field_passthrough to include/exclude fields
- Switch to different source (bucket or collection)
- Test modifications before replacing production collection
- Create variants (e.g., different embedding models)
All fields are OPTIONAL:
- Omit a field to keep the original value
- Provide a field to override the original value
- collection_name is REQUIRED (clones must have unique names)
REQUIRED. Name for the cloned collection. Must be unique and different from the source collection.
Minimum string length:
1Examples:
"product_embeddings_v2"
"video_frames_clip_v2"
OPTIONAL. Description override. If omitted, copies from source collection.
Example:
"Cloned from product_embeddings with CLIP v2"
OPTIONAL. Override source configuration. If omitted, copies from source collection. Allows switching between buckets or collections.
Show child attributes
Show child attributes
Example:
{
"bucket_ids": ["bkt_marketing_videos"],
"type": "bucket"
}
OPTIONAL. Override feature extractor configuration. If omitted, copies from source collection. This is where you'd change models, parameters, or field_passthrough.
Show child attributes
Show child attributes
Example:
{
"feature_extractor_name": "text_extractor",
"field_passthrough": [
{ "required": true, "source_path": "title" },
{ "source_path": "author" }
],
"input_mappings": { "text": "content" },
"parameters": { "model": "text-embedding-3-small" },
"version": "v1"
}
OPTIONAL. Override enabled status. If omitted, copies from source collection.
OPTIONAL. Override metadata. If omitted, copies from source collection.
OPTIONAL. Override taxonomy applications. If omitted, copies from source collection.
Show child attributes
Show child attributes
Response
Successful Response
Response after cloning a collection.
Cloned collection configuration with new collection_id.
Show child attributes
Show child attributes
Examples:
{
"collection_id": "col_a1b2c3d4e5",
"collection_name": "article_embeddings",
"description": "Simple text collection: News articles with text embeddings from bucket source",
"enabled": true,
"feature_extractor": {
"feature_extractor_name": "text_extractor",
"field_passthrough": [{ "source_path": "title" }],
"input_mappings": { "text": "content" },
"version": "v1"
},
"input_schema": {
"properties": {
"title": { "type": "string" },
"content": { "type": "text" }
}
},
"output_schema": {
"properties": {
"title": { "type": "string" },
"text_extractor_v1_embedding": { "type": "array" }
}
},
"source": {
"bucket_id": "bkt_articles",
"type": "bucket"
}
}
{
"collection_id": "col_xyz789abc",
"collection_name": "video_frames",
"description": "Video frames: Extracted at 1 FPS with CLIP embeddings and campaign_id passthrough",
"enabled": true,
"feature_extractor": {
"feature_extractor_name": "multimodal_extractor",
"field_passthrough": [{ "source_path": "campaign_id" }],
"input_mappings": { "video": "video" },
"parameters": { "fps": 1 },
"version": "v1"
},
"input_schema": {
"properties": {
"video": { "type": "video" },
"campaign_id": { "type": "string" }
}
},
"output_schema": {
"properties": {
"campaign_id": { "type": "string" },
"multimodal_extractor_v1_embedding": { "type": "array" }
}
},
"source": {
"bucket_id": "bkt_marketing_videos",
"type": "bucket"
}
}
{
"collection_id": "col_scenes_def",
"collection_name": "detected_scenes",
"description": "Tier 2 decomposition: Scenes detected from frame embeddings (collection source)",
"enabled": true,
"feature_extractor": {
"feature_extractor_name": "scene_extractor",
"field_passthrough": [{ "source_path": "campaign_id" }],
"input_mappings": {
"embedding": "multimodal_extractor_v1_embedding"
},
"version": "v1"
},
"input_schema": {
"properties": {
"campaign_id": { "type": "string" },
"multimodal_extractor_v1_embedding": { "type": "array" }
}
},
"output_schema": {
"properties": {
"campaign_id": { "type": "string" },
"scene_extractor_v1_embedding": { "type": "array" }
}
},
"source": {
"collection_id": "col_video_frames",
"type": "collection"
}
}
ID of the source collection that was cloned.
Was this page helpful?
⌘I