Skip to content

Get Pipeline Document Status Counts

Deprecated
GET/api/v1/pipelines/{pipeline_id}/documents/status-counts

Count the documents in a pipeline, grouped by ingestion status.

Counts reflect each document’s last recorded status rather than a freshly computed one, so a document that changed status in the last few moments may still be counted under its previous one. Use GET /pipelines/{pipeline_id}/documents/{document_id}/status when a single document’s status has to be up to the moment.

Path ParametersExpand Collapse
pipeline_id: string
Query ParametersExpand Collapse
data_source_id: optional string
file_id: optional string
only_direct_upload: optional boolean
project_id: optional string
Cookie ParametersExpand Collapse
session: optional string
ReturnsExpand Collapse
counts: map[number]

Number of documents per ingestion status; every status is present.

pipeline_id: string

ID of the pipeline the documents belong to.

formatuuid
total_count: number

Total number of documents counted.

data_source_id: optional string

Data source the counts were restricted to.

formatuuid
file_id: optional string

File the counts were restricted to.

formatuuid
only_direct_upload: optional boolean

Whether only directly uploaded documents were counted.

Get Pipeline Document Status Counts

curl https://api.cloud.llamaindex.ai/api/v1/pipelines/$PIPELINE_ID/documents/status-counts \
    -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"
{
  "counts": {
    "foo": 0
  },
  "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "total_count": 0,
  "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "only_direct_upload": true
}
Returns Examples
{
  "counts": {
    "foo": 0
  },
  "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "total_count": 0,
  "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "only_direct_upload": true
}
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/for-agents/mcp/ - Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/