Create Pipeline

This creates an pipeline.

---

POST

https://controller.${CLOUD_REGION}.zillizcloud.com/v1/pipelines

---

Example

📘Notes

This API requires an API key as the authentication token.

Currently, you can create pipelines to ingest data into and search/purge data from your collections. The request parameters vary with the type of pipelines you want to create and the data you want to process.

Ingestion

Text Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY=""

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "name": "my_text_ingestion_pipeline",
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "projectId": "proj-xxxx"，
        "collectionName": "my_collection",
        "description": "A pipeline that generates text embeddings and stores additional fields.",
        "type": "INGESTION",  
        "functions": [
            { 
                "name": "index_my_text",
                "action": "INDEX_TEXT", 
                "language": "ENGLISH",
                "embedding": "zilliz/bge-base-en-v1.5"
            },
            {
                "name": "keep_text_info",
                "action": "PRESERVE", 
                "inputField": "source", 
                "outputField": "source",
                "fieldType": "VarChar" 
            }
        ]   
    }'

Possible response is similar to the following

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_text_ingestion_pipeline",
    "type": "INGESTION",
    "clusterId": "inxx-xxxxxxxxxxxxxxx",
    "collectionName": "my_collection"
    "description": "A pipeline that generates text embeddings and stores additional fields.",
    "status": "SERVING",
    "functions": [
      {
        "action": "INDEX_TEXT",
        "name": "index_my_text",
        "inputFields": ["text_list"],
        "language": "ENGLISH",
        "embedding": "zilliz/bge-base-en-v1.5"
      },
      {
        "action": "PRESERVE",
        "name": "keep_text_info",
        "inputField": "source",
        "outputField": "source",
        "fieldType": "VarChar"
      }
    ]
  }
}

Document Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY=""    

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx"，
        "name": "my_doc_ingestion_pipeline",
        "description": "A pipeline that splits a doc file into chunks and generates embeddings. It also stores the publish_year with each chunk.",
        "type": "INGESTION",  
        "functions": [
            { 
                "name": "index_my_doc",
                "action": "INDEX_DOC", 
                "language": "ENGLISH",
                "chunkSize": 500,
                "embedding": "zilliz/bge-base-en-v1.5",
                "splitBy": ["\n\n", "\n", " ", ""]
            },
            {
                "name": "keep_doc_info",
                "action": "PRESERVE", 
                "inputField": "publish_year", 
                "outputField": "publish_year",
                "fieldType": "Int16" 
            }
        ],
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "newCollectionName": "my_collection"
    }'

Possible response is similar to the following:

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_doc_ingestion_pipeline",
    "type": "INGESTION",
    "description": "A pipeline that splits a doc file into chunks and generates embeddings. It also stores the publish_year with each chunk.",
    "status": "SERVING",
    "functions": [
      {
        "action": "INDEX_DOC",
        "name": "index_my_doc",
        "inputField": "doc_url",
        "language": "ENGLISH",
        "chunkSize": 500,
        "embedding": "zilliz/bge-base-en-v1.5"，
        "splitBy": ["\n\n", "\n", " ", ""]
      },
      {
        "action": "PRESERVE",
        "name": "keep_doc_info",
        "inputField": "publish_year",
        "outputField": "publish_year",
        "fieldType": "Int16"
      }
    ],
    "clusterId": "inxx-xxxxxxxxxxxxxxx",
    "newCollectionName": "my_collection"
  }
}

Image Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"   

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "name": "my_image_ingestion_pipeline",
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "projectId": "proj-xxxx"，
        "collectionName": "my_collection",
        "description": "A pipeline that converts an image into vector embeddings and store in efficient index for search.",
        "type": "INGESTION",  
        "functions": [
            { 
                "name": "index_my_image",
                "action": "INDEX_IMAGE", 
                "embedding": "zilliz/vit-base-patch16-224"
            },
            {
                "name": "keep_image_tag",
                "action": "PRESERVE", 
                "inputField": "image_title", 
                "outputField": "image_title",
                "fieldType": "VarChar" 
            }
        ]   
    }'

Possible response is similar to the following:

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_image_ingestion_pipeline",
    "type": "INGESTION",
    "clusterId": "in03-***************",
    "collectionName": "my_collection"
    "description": "A pipeline that converts an image into vector embeddings and store in efficient index for search.",
    "status": "SERVING",
    "functions": [
      {
        "action": "INDEX_IMAGE",
        "name": "index_my_image",
        "inputFields": ["image_url", "image_id"],
        "embedding": "zilliz/vit-base-patch16-224"
      },
      {
        "action": "PRESERVE",
        "name": "keep_image_tag",
        "inputField": "image_title",
        "outputField": "image_title",
        "fieldType": "VarChar"
      }
    ]
  }
}

Search

Text Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY=""

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",       
        "name": "my_text_search_pipeline",
        "description": "A pipeline that receives text and search for semantically similar texts",
        "type": "SEARCH",
        "functions": [
            {
                "name": "search_text",
                "action": "SEARCH_TEXT",
                "clusterId": "inxx-xxxxxxxxxxxxxxx",
                "collectionName": "my_collection",
                "embedding": "zilliz/bge-base-en-v1.5",
                "reranker": "zilliz/bge-reranker-base"
            }
        ]
    }'

Possible response is similar to the following

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_text_search_pipeline",
    "type": "SEARCH",
    "description": "A pipeline that receives text and search for semantically similar texts",
    "status": "SERVING",
    "functions": 
      {
        "action": "SEARCH_TEXT",
        "name": "search_text",
        "inputFields": "query_text",
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName": "my_collection",
        "embedding": "zilliz/bge-base-en-v1.5",
        "reranker": "zilliz/bge-reranker-base"
      }
  }
}

Document Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"    

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",       
        "name": "my_text_search_pipeline",
        "description": "A pipeline that receives text and search for semantically similar doc chunks",
        "type": "SEARCH",
        "functions": [
            {
                "name": "search_chunk_text_and_title",
                "action": "SEARCH_DOC_CHUNK",
                "clusterId": "inxx-xxxxxxxxxxxxxxx",
                "collectionName": "my_collection",
                "embedding": "zilliz/bge-base-en-v1.5",
                "reranker": "zilliz/bge-reranker-base"
            }
        ]
    }'

Possible response is similar to the following:

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-84e6d9dba930e035150972",
    "name": "my_text_search_pipeline",
    "type": "SEARCH",
    "description": "A pipeline that receives text and search for semantically similar doc chunks",
    "status": "SERVING",
    "functions": 
      {
        "action": "SEARCH_DOC_CHUNK",
        "name": "search_chunk_text_and_title",
        "inputField": "query_text",
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName": "my_collection",
        "embedding": "zilliz/bge-base-en-v1.5",
        "reranker": "zilliz/bge-reranker-base"
      }
  }
}

Image Data

You can create a pipeline to search images by either an image or a query text.

• Create a pipeline to search images by an image

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"   

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",       
        "name": "my_image_search_pipeline",
        "description": "A pipeline that searches image by image.",
        "type": "SEARCH",
        "functions": [
            {
                "name": "search_image_by_image",
                "action": "SEARCH_IMAGE_BY_IMAGE",
                "embedding": "zilliz/vit-base-patch16-224",
                "clusterId": "inxx-xxxxxxxxxxxxxxx",
                "collectionName": "my_collection"
            }
        ]
    }'

Possible response is similar to the following:

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_image_search_pipeline",
    "type": "SEARCH",
    "description": "A pipeline that searches image by image.",
    "status": "SERVING",
    "functions": 
      {
        "action": "SEARCH_IMAGE_BY_IMAGE",
        "name": "search_image_by_image",
        "inputFields": ["query_image_url"],
        "clusterId": "in03-***************",
        "collectionName": "my_collection",
        "embedding": "zilliz/vit-base-patch16-224"
      }
  }
}

• Create a pipeline to search images by a query text

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"   

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",       
        "name": "my_text_image_search_pipeline",
        "description": "A pipeline that searches image by text.",
        "type": "SEARCH",
        "functions": [
            {
                "name": "search_image_by_text",
                "action": "SEARCH_IMAGE_BY_TEXT",
                "embedding": "zilliz/clip-vit-base-patch32-multilingual-v1",
                "clusterId": "inxx-xxxxxxxxxxxxxxx",
                "collectionName": "my_collection"
            }
        ]
    }'

Possible response is similar to the following:

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_text_image_search_pipeline",
    "type": "SEARCH",
    "description": "A pipeline that searches image by text.",
    "status": "SERVING",
    "functions": 
      {
        "action": "SEARCH_IMAGE_BY_TEXT",
        "name": "search_image_by_text",
        "inputFields": ["query_text"],
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName": "my_collection",
        "embedding": "zilliz/clip-vit-base-patch32-multilingual-v1"
      }
  }
}

Deletion

Text Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",
        "name": "my_text_deletion_pipeline",
        "description": "A pipeline that deletes entities by expression",
        "type": "DELETION",
        "functions": [
            {
                "name": "purge_data_by_expression",
                "action": "PURGE_BY_EXPRESSION"
            }
        ], 
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName": "my_collection"
    }'

Possible response is similar to the following

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-xxxx",
    "name": "my_text_deletion_pipeline",
    "type": "DELETION",
    "description": "A pipeline that deletes entities by expression",
    "status": "SERVING",
    "functions": [
      {
        "action": "PURGE_BY_EXPRESSION",
        "name": "purge_data_by_expression",
        "inputFields": ["expression"]
      }
    ],
    "clusterId": "inxx-xxxxxxxxxxxxxxx",
    "collectionName": "my_collection"
  }
}

Document Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"    

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",
        "name": "my_doc_deletion_pipeline",
        "description": "A pipeline that deletes all info associated with a doc",
        "type": "DELETION",
        "functions": [
            {
                "name": "purge_chunks_by_doc_name",
                "action": "PURGE_DOC_INDEX"
            }
        ],
    
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName": "my_collection"
    }'

Possible response is similar to the following:

{
  "code": 200,
  "data": {
    "pipelineId": "pipe-ab2874d8138c8554375bb0",
    "name": "my_doc_deletion_pipeline",
    "type": "DELETION",
    "description": "A pipeline that deletes all info associated with a doc",
    "status": "SERVING",
    "functions": [
      {
        "action": "PURGE_DOC_INDEX",
        "name": "purge_chunks_by_doc_name",
        "inputField": "doc_name"
      }
    ],
    "clusterId": "inxx-xxxxxxxxxxxxxxx",
    "collectionName": "my_collection"
  }
}

Image Data

export CLOUD_REGION="gcp-us-west1"
export API_KEY="YOUR_API_KEY"   

curl --request POST \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer ${API_KEY}" \
    --url "https://controller.api.${CLOUD_REGION}.zillizcloud.com/v1/pipelines" \
    -d '{
        "projectId": "proj-xxxx",
        "name": "my_image_deletion_pipeline",
        "description": "A pipeline that deletes image by id",
        "type": "DELETION",
        "functions": [
            {
                "name": "purge_image_by_id",
                "action": "PURGE_IMAGE_INDEX"
            }
        ], 
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName": "my_collection"
    }'

Possible response is similar to the following:

{
    "code": 200,
    "data": {
        "id": 0,
        "name": "my_image_deletion_pipeline",
        "type": "DELETION",
        "description": "A pipeline that deletes image by id",
        "status": "SERVING",
        "functions": [
            {
                "name": "purge_image_by_id",
                "action": "PURGE_IMAGE_INDEX",
                "inputFields": ["image_id"]
            }
        ],
        "clusterId": "inxx-xxxxxxxxxxxxxxx",
        "collectionName":" my_collection"
    }
}

Request

Parameters

• No query parameters required

• No path parameters required

• No header parameters required

Request Body

Option 1:

{
    "name": "string",
    "type": "string",
    "description": "string",
    "functions": [
        {
            "name": "string",
            "action": "string",
            "inputField": "string",
            "outputField": "string",
            "fieldType": "string"
        }
    ],
    "clusterId": "string",
    "collectionName": "string",
    "projectId": "string"
}

Parameter	Description
name	string Name of the pipeline to create.
type	string Type of the pipeline to create. For an ingestion pipeline, the value should be INGESTION.
description	string Description of the pipeline to create.
functions	array Actions to take in the pipeline to create. For an ingestion pipeline, you can add only one doc-indexing function and multilpe preserve functions.
functions[]	object | object | object | object
functions[][opt_1]	object
functions[][opt_1].name	string Name of the function to create.
functions[][opt_1].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC, INDEX_TEXT, INDEX_IMAGE, and PRESERVE.
functions[][opt_1].embedding	string Name of the embedding model used to convert the text into vector embeddings. For possible values, refer to Ingest, Search, and Delete Data.
functions[][opt_1].language	string Language of your documents. Possible values are ENGLISH and CHINESE.
functions[][opt_2]	object
functions[][opt_2].name	string Name of the function to create.
functions[][opt_2].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC, INDEX_TEXT, INDEX_IMAGE, and PRESERVE.
functions[][opt_2].embedding	string Name of the embedding model used to convert the text into vector embeddings. For possible values, refer to Ingest, Search, and Delete Data.
functions[][opt_2].language	string Language of your documents. Possible values are ENGLISH and CHINESE.
functions[][opt_2].chunkSize	string The maximum size of a splitted doc segment The value defaults to 500
functions[][opt_2][].splitBy	array The splitters for Zilliz Cloud to split the specified document into smaller chunks. The value defaults to ["\n\n", "\n", " ", ""].
functions[][opt_2][].splitBy[]	string A splitter.
functions[][opt_3]	object
functions[][opt_3].name	string Name of the function to create.
functions[][opt_3].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC, INDEX_TEXT, INDEX_IMAGE, and PRESERVE.
functions[][opt_3].embedding	string Name of the embedding model used to convert the text into vector embeddings. For possible values, refer to Ingest, Search, and Delete Data.
functions[][opt_4]	object
functions[][opt_4].name	string Name of the function to create.
functions[][opt_4].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC and PRESERVE.
functions[][opt_4].inputField	string Name the field according to your needs. In a preserve function of an ingestion pipeline, Zilliz Cloud uses the value as the name of a field in the collection to create.
functions[][opt_4].outputField	string Name of the output field. The value should be the same as that of input_field.
functions[][opt_4].fieldType	string Data type of the field to create in the target collection. Possible values are BOOL, INT8, INT16, INT32, INT64, FLOAT, DOUBLE, and VARCHAR.
clusterId	string ID of a target cluster. You can find it in cluster details on Zilliz Cloud console.
collectionName	string Name of the collection to create in the specified cluster. Zilliz Cloud creates a new collection and name it using this value.
projectId	string ID of the project to which the target cluster belongs.

Option 2:

{
    "name": "string",
    "description": "string",
    "type": "string",
    "functions": [
        {
            "name": "string",
            "action": "string",
            "clusterId": "string",
            "collectionName": "string",
            "embedding": "string",
            "reranker": "string"
        }
    ],
    "projectId": "string"
}

Parameter	Description
name	string Name of the pipeline to create.
description	string Description of the pipeline to create.
type	string Type of the pipeline to create. For a search pipeline, the value should be SEARCH.
functions	array Actions to take in the search pipeline to create. You can define multiple functions to retrieve results from different collections.
functions[]	object
functions[].name	string Name of the function to create.
functions[].action	string Type of the function to create. For a search pipeline, possible value is SEARCH_TEXT, SEARCH_DOC_CHUNK, SEARCH_IMAGE_BY_IMAGE, and SEARCH_IMAGE_BY_TEXT.
functions[].clusterId	string ID of a target collection in which Zilliz Cloud concducts the search.
functions[].collectionName	string Name of the collection in which ZIlliz Cloud conducts the search.
functions[].embedding	string The embedding model used during vector search. The model should be consistent with the one chosen in the compatible collection.
functions[].reranker	string If you need to reorder or rank a set of candidate outputs to improve the quality of the search results, set this parameter to a reranker model. This parameter applies only to pipelines for Text and Doc Data. Currently, only zilliz/bge-reranker-base is available as the parameter value.
projectId	string ID of the project to which the target cluster belongs

Option 3:

{
    "name": "string",
    "description": "string",
    "type": "string",
    "functions": [
        {
            "name": "string",
            "action": "string"
        }
    ],
    "clusterId": "string",
    "collectionName": "string",
    "projectId": "string"
}

Parameter	Description
name	string Name of the pipeline to create.
description	string Description of the pipeline to create.
type	string Type of the pipeline to create. For a deletion pipeline, the value should be DELETION
functions	array Actions to take in the pipeline to create.
functions[]	object
functions[].name	string Name of the function to create.
functions[].action	string Type of the function to create. For a delete pipeline, possible value is PURGE_BY_EXPRESSION, PURGE_DOC_INDEX, and PURGE_IMAGE_INDEX.
clusterId	string ID of a target cluster. You can find it in cluster details on Zilliz Cloud console.
collectionName	string Name of the collection to create in the specified cluster. Zilliz Cloud creates a new collection and name it using this value.
projectId	string ID of the project to which the target cluster belongs.

Response

Returns information about the pipeline just created.

Response Body

Option 1:

{
    "code": "integer",
    "data": {
        "pipelineId": "integer",
        "name": "string",
        "type": "string",
        "description": "string",
        "status": "string",
        "functions": {
            "oneOf": [
                {
                    "name": "string",
                    "action": "string",
                    "inputFields": [
                        {}
                    ],
                    "langauge": "string",
                    "embedding": "string"
                },
                {
                    "name": "string",
                    "action": "string",
                    "inputField": "string",
                    "langauge": "string",
                    "chunkSize": "integer",
                    "embedding": "string",
                    "splitBy": "string"
                },
                {
                    "name": "string",
                    "action": "string",
                    "inputFields": [
                        {}
                    ],
                    "embedding": "string"
                },
                {
                    "name": "string",
                    "action": "string",
                    "inputField": "string",
                    "outputField": "string",
                    "fieldType": "string"
                }
            ]
        },
        "clusterID": "string",
        "collectionName": "string"
    }
}

Property	Description
code	integer Indicates whether the request succeeds. 0: The request succeeds. Others: Some error occurs.
data	object
data.pipelineId	integer A pipeline ID.
data.name	string Name of the pipeline.
data.type	string Type of the pipeline. For an ingestion pipeline, the value should be INGESTION.
data.description	string Description of the pipeline.
data.status	string Current status of the pipeline. If the value is other than SERVING, the pipeline is not working.
functions	object | object | object | object Functions in the pipeline. For an ingestion pipeline, there should be only one INDEX_DOC function.
functions[opt_1]	object
functions[opt_1].name	string Name of the function to create.
functions[opt_1].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC and PRESERVE.
functions[opt_1][].inputFields	array Names the fields according to your needs. In an INDEX_TEXT function of an ingestion pipeline, use them for the user-provided texts.
functions[opt_1][].inputFields[]	string An input field.
functions[opt_1].langauge	string Language that your document is in. Possible values are english or chinese. The parameter applies only to ingestion pipelines.
functions[opt_1].embedding	string Name of the embedding model in use.
functions[opt_2]	object
functions[opt_2].name	string Name of the function to create.
functions[opt_2].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC and PRESERVE.
functions[opt_2].inputField	string Name the field according to your needs. In an INDEX_DOC function of an ingestion pipeline, use it for pre-signed document URLs in GCS or AWS S3 buckets.
functions[opt_2].langauge	string Language that your document is in. Possible values are english or chinese. The parameter applies only to ingestion pipelines.
functions[opt_2].chunkSize	integer The maximum size of a splitted document segment.
functions[opt_2].embedding	string Name of the embedding model in use.
functions[opt_2].splitBy	string The splitters that Zilliz Cloud uses to split the specified docs.
functions[opt_3]	object
functions[opt_3].name	string Name of the function to create.
functions[opt_3].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC and PRESERVE.
functions[opt_3][].inputFields	array Names the fields according to your needs. In an INDEX_IMAGE function of an ingestion pipeline: image_url stands for pre-signed image URLs in GCS or AWS S3 buckets, and image_id stands for the image ID.
functions[opt_3][].inputFields[]	string An input field.
functions[opt_3].embedding	string Name of the embedding model in use.
functions[opt_4]	object
functions[opt_4].name	string Name of the function to create.
functions[opt_4].action	string Type of the function to create. For an ingestion pipeline, possible values are INDEX_DOC and PRESERVE.
functions[opt_4].inputField	string Name the field according to your needs. In a preserve function of an ingestion pipeline, Zilliz Cloud uses the value as the name of a field in the collection to create.
functions[opt_4].outputField	string Name of the output field. The value should be the same as that of input_field.
functions[opt_4].fieldType	string Data type of the field to create in the target collection. Possible values are BOOL, INT8, INT16, INT32, INT64, FLOAT, DOUBLE, and VARCHAR.
data.clusterID	string The target cluster to which the pipeline applies.
data.collectionName	string The target collection to which the pipeline applies.

Option 2:

{
    "code": "integer",
    "data": {
        "pipelineId": "integer",
        "name": "string",
        "type": "string",
        "description": "string",
        "status": "string",
        "functions": [
            {
                "name": "string",
                "action": "string",
                "inputFields": [
                    {}
                ],
                "clusterID": "string",
                "collectionName": "string",
                "reranker": "string"
            }
        ]
    }
}

Property	Description
code	integer Indicates whether the request succeeds. 0: The request succeeds. Others: Some error occurs.
data	object
data.pipelineId	integer A pipeline ID.
data.name	string Name of the pipeline
data.type	string Type of the pipeline. For a search pipeline, the value should be SEARCH.
data.description	string Description of the pipeline.
data.status	string Current status of the pipeline. If the value is not SERVING, the pipeline is not working.
data[].functions	array Functions in the pipeline. For a search pipeline, each of its member functions targets at a different collection.
data[].functions[]	object
data[].functions[].name	string Name of the function.
data[].functions[].action	string Type of the function. For a search function, the value should be SEARCH_DOC_CHUNKS, SEARCH_TEXT, SEARCH_IMAGE_BY_IMAGE, and SEARCH_IMAGE_BY_TEXT.
data[].functions[][].inputFields	array Name of the input fields.
data[].functions[][].inputFields[]	string For a SEARCH_DOC_CHUNKS or a SEARCH_IMAGE_BY_TEXT function, you should include query_text as the value.
data[].functions[].clusterID	string Target cluster of this function.
data[].functions[].collectionName	string Target collection of this function.
data[].functions[].reranker	string If you need to reorder or rank a set of candidate outputs to improve the quality of the search results, set this parameter to a reranker model. This parameter applies only to pipelines for Text and Doc Data. Currently, only zilliz/bge-reranker-base is available as the parameter value.

Option 3:

{
    "code": "integer",
    "data": {
        "pipelineId": "integer",
        "name": "string",
        "type": "string",
        "description": "string",
        "status": "string",
        "functions": [
            {
                "name": "string",
                "action": "string",
                "inputField": "string"
            }
        ],
        "clusterID": "string",
        "collectionName": "string"
    }
}

Property	Description
code	integer Indicates whether the request succeeds. 0: The request succeeds. Others: Some error occurs.
data	object
data.pipelineId	integer A pipeline ID.
data.name	string Name of the pipeline.
data.type	string Type of the pipeline. For a deletion pipeline, the value should be DELETION.
data.description	string Description of the pipeline.
data.status	string Current status of the pipeline. If the value is not SERVING, the pipeline is not working.
data[].functions	array Functions in the pipeline. For a deletion pipeline, there can be multiple member functions with each representing a deletion request.
data[].functions[]	object
data[].functions[].name	string Name of the function.
data[].functions[].action	string Type of the function. For a deletion pipeline, its member functions should be of PURGE_BY_EXPRESSION, PURGE_DOC_INDEX, and PURGE_IMAGE_BY_ID.
data[].functions[].inputField	string Name of the input field. For a PURGE_DOC_INDEX function, the value should be the name of the doc to delete.
data.clusterID	string Target cluster of the pipeline.
data.collectionName	string Target collection of the pipeline.

Error Response

{
    "code": integer,
    "message": string
}

Property	Description
code	integer Indicates whether the request succeeds. 0: The request succeeds. Others: Some error occurs.
message	string Indicates the possible reason for the reported error.