Skip to content

Create Batch Pipeline Documents

Deprecated
pipelines.documents.create(strpipeline_id, DocumentCreateParams**kwargs) -> DocumentCreateResponse
POST/api/v1/pipelines/{pipeline_id}/documents

Batch create documents for a pipeline.

ParametersExpand Collapse
pipeline_id: str
metadata: Dict[str, object]
text: str
id: Optional[str]
excluded_embed_metadata_keys: Optional[List[str]]
excluded_llm_metadata_keys: Optional[List[str]]
page_positions: Optional[List[int]]

indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].

ReturnsExpand Collapse
id: str
metadata: Dict[str, object]
text: str
excluded_embed_metadata_keys: Optional[List[str]]
excluded_llm_metadata_keys: Optional[List[str]]
page_positions: Optional[List[int]]

indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].

status_metadata: Optional[Dict[str, object]]

Create Batch Pipeline Documents

import os
from llama_cloud import LlamaCloud

client = LlamaCloud(
    api_key=os.environ.get("LLAMA_CLOUD_API_KEY"),  # This is the default and can be omitted
)
cloud_documents = client.pipelines.documents.create(
    pipeline_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    body=[{
        "metadata": {
            "foo": "bar"
        },
        "text": "text",
    }],
)
print(cloud_documents)
[
  {
    "id": "id",
    "metadata": {
      "foo": "bar"
    },
    "text": "text",
    "excluded_embed_metadata_keys": [
      "string"
    ],
    "excluded_llm_metadata_keys": [
      "string"
    ],
    "page_positions": [
      0
    ],
    "status_metadata": {
      "foo": "bar"
    }
  }
]
Returns Examples
[
  {
    "id": "id",
    "metadata": {
      "foo": "bar"
    },
    "text": "text",
    "excluded_embed_metadata_keys": [
      "string"
    ],
    "excluded_llm_metadata_keys": [
      "string"
    ],
    "page_positions": [
      0
    ],
    "status_metadata": {
      "foo": "bar"
    }
  }
]
Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/python/shared/mcp/