POST
/
pipelines
curl --location 'https://api.mixpeek.com/pipelines' \
--header 'Authorization: Bearer API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "source_destination_mappings": [
        {
            "embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
            "source": {
                "field": "resume_url",
                "type": "file_url",
                "settings": {}
            },
            "destination": {
                "collection": "resume_embeddings",
                "field": "text",
                "embedding": "embedding"
            }
        }
    ],
    "metadata": {
        "pipeline_name": "Resume Processing",
        "description": "Extracts resume information and generates embeddings."
    }
}'

{
  "pipeline_id": "<string>",
  "enabled": true,
  "source_destination_mappings": [
    {}
  ],
  "metadata": {}
}

​
Request

source_destination_mappings
array
required

Defines the mappings between data sources and their destinations, including the transformation models used. Each mapping specifies a source (with its type and any necessary settings), the model used for embedding or transformation, and the destination (including the collection and field where the data should be stored, and the embedding field name if applicable).

metadata
object

Optional metadata to provide context or additional information about the pipeline being created. This could include details such as the pipeline’s purpose, intended use case, or any other relevant information.

​
Response

pipeline_id
string
required

The unique identifier for the newly created pipeline. This ID can be used to reference the pipeline in future operations, such as invoking the pipeline or querying its status.

enabled
boolean

Indicates whether the pipeline is enabled upon creation. This field can be used to immediately start processing data through the pipeline if set to true.

source_destination_mappings
array
required

Echoes back the source-destination mappings provided in the request, confirming the configurations that have been set for the pipeline.

metadata
object

Echoes back any metadata provided in the request, confirming the additional contextual information associated with the pipeline.

EmbedInvoke Pipeline