llamaindex · Schema

LlamaIndex Pipeline

A document ingestion pipeline (index) in LlamaCloud that processes, embeds, and indexes documents for retrieval in RAG applications.

Properties

Name	Type	Description
id	string	Unique identifier of the pipeline.
name	string	Human-readable name of the pipeline.
project_id	string	Identifier of the project the pipeline belongs to.
status	string	Current processing status of the pipeline.
embedding_model	string	Name of the embedding model used for vectorization.
sync_interval	integer	Scheduled sync frequency in seconds. Zero means manual sync only.
data_sources	array	Data sources connected to this pipeline for automatic ingestion.
data_sinks	array	Data sinks where processed content is stored.
created_at	string	Timestamp when the pipeline was created.
updated_at	string	Timestamp when the pipeline was last updated.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://llamaindex.ai/schemas/llamaindex/pipeline.json",
  "title": "LlamaIndex Pipeline",
  "description": "A document ingestion pipeline (index) in LlamaCloud that processes, embeds, and indexes documents for retrieval in RAG applications.",
  "type": "object",
  "required": ["id", "name", "project_id"],
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique identifier of the pipeline."
    },
    "name": {
      "type": "string",
      "description": "Human-readable name of the pipeline.",
      "minLength": 1,
      "maxLength": 255
    },
    "project_id": {
      "type": "string",
      "description": "Identifier of the project the pipeline belongs to."
    },
    "status": {
      "type": "string",
      "enum": ["active", "syncing", "error", "idle"],
      "description": "Current processing status of the pipeline."
    },
    "embedding_model": {
      "type": "string",
      "description": "Name of the embedding model used for vectorization."
    },
    "sync_interval": {
      "type": "integer",
      "minimum": 0,
      "description": "Scheduled sync frequency in seconds. Zero means manual sync only."
    },
    "data_sources": {
      "type": "array",
      "description": "Data sources connected to this pipeline for automatic ingestion.",
      "items": {
        "$ref": "#/$defs/DataSource"
      }
    },
    "data_sinks": {
      "type": "array",
      "description": "Data sinks where processed content is stored.",
      "items": {
        "$ref": "#/$defs/DataSink"
      }
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "description": "Timestamp when the pipeline was created."
    },
    "updated_at": {
      "type": "string",
      "format": "date-time",
      "description": "Timestamp when the pipeline was last updated."
    }
  },
  "$defs": {
    "DataSource": {
      "type": "object",
      "description": "A data source that provides documents for automatic ingestion into a pipeline.",
      "required": ["id", "name", "source_type"],
      "properties": {
        "id": {
          "type": "string",
          "description": "Unique identifier of the data source."
        },
        "name": {
          "type": "string",
          "description": "Human-readable name of the data source.",
          "minLength": 1,
          "maxLength": 255
        },
        "source_type": {
          "type": "string",
          "description": "Type of the data source (e.g., document, table, api, database, web)."
        },
        "project_id": {
          "type": "string",
          "description": "Identifier of the project the data source belongs to."
        },
        "config": {
          "type": "object",
          "additionalProperties": true,
          "description": "Configuration specific to the data source type."
        },
        "created_at": {
          "type": "string",
          "format": "date-time",
          "description": "Timestamp when the data source was created."
        }
      }
    },
    "DataSink": {
      "type": "object",
      "description": "A data sink that receives processed and embedded content, such as a vector database.",
      "required": ["id", "name", "sink_type"],
      "properties": {
        "id": {
          "type": "string",
          "description": "Unique identifier of the data sink."
        },
        "name": {
          "type": "string",
          "description": "Human-readable name of the data sink.",
          "minLength": 1,
          "maxLength": 255
        },
        "sink_type": {
          "type": "string",
          "description": "Type of the data sink (e.g., vector_store)."
        },
        "config": {
          "type": "object",
          "additionalProperties": true,
          "description": "Configuration specific to the data sink type."
        }
      }
    }
  }
}