API Reference

Pipelines

Documents

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Get Pipeline Document

CloudDocument pipelines().documents().get(DocumentGetParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}

Return a single document for a pipeline.

ParametersExpand Collapse

DocumentGetParams params

String pipelineId

Optional<String> documentId

ReturnsExpand Collapse

class CloudDocument:

Cloud document stored in S3.

String id

Metadata metadata

String text

Optional<List<String>> excludedEmbedMetadataKeys

Optional<List<String>> excludedLlmMetadataKeys

Optional<List<Long>> pagePositions

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

Optional<StatusMetadata> statusMetadata

Get Pipeline Document

Java

HTTP

TypeScript

Python

Java

Go

CLI Tool

package com.llamacloud_prod.api.example;

import com.llamacloud_prod.api.client.LlamaCloudClient;
import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient;
import com.llamacloud_prod.api.models.pipelines.documents.CloudDocument;
import com.llamacloud_prod.api.models.pipelines.documents.DocumentGetParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();

        DocumentGetParams params = DocumentGetParams.builder()
            .pipelineId("182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e")
            .documentId("document_id")
            .build();
        CloudDocument cloudDocument = client.pipelines().documents().get(params);
    }
}

200 example

{
  "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

200 example

{
  "id": "id",
  "metadata": {
    "foo": "bar"
  },
  "text": "text",
  "excluded_embed_metadata_keys": [
    "string"
  ],
  "excluded_llm_metadata_keys": [
    "string"
  ],
  "page_positions": [
    0
  ],
  "status_metadata": {
    "foo": "bar"
  }
}