API Reference

Extraction Agents

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

List Extract Agents

ExtractionAgentListPage extractionAgents().list(ExtractionAgentListParamsparams = ExtractionAgentListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

GET/api/v1/beta/extraction-agents

List the extraction agents in a project, newest first.

ParametersExpand Collapse

ExtractionAgentListParams params

Optional<Boolean> includeDefault

Whether to include default agents in the results

Optional<String> organizationId

Optional<Long> pageSize

Number of items per page

maximum1000

minimum1

Optional<String> pageToken

Cursor from the previous page’s next_page_token.

Optional<String> projectId

ReturnsExpand Collapse

class ExtractAgent:

Schema and configuration for an extraction agent.

String id

The id of the extraction agent.

formatuuid

Config config

The configuration parameters for the extraction agent.

Optional<ChunkMode> chunkMode

The mode to use for chunking the document.

One of the following:

PAGE("PAGE")

SECTION("SECTION")

DeprecatedOptional<Boolean> citationBbox

Whether to fetch citation bounding boxes for the extraction. Only available in PREMIUM mode. Deprecated: this is now synonymous with cite_sources.

Optional<Boolean> citeSources

Whether to cite sources for the extraction.

Optional<Boolean> confidenceScores

Whether to fetch confidence scores for the extraction.

Optional<ExtractModel> extractModel

The extract model to use for data extraction. If not provided, uses the default for the extraction mode.

One of the following:

GEMINI_2_0_FLASH("gemini-2.0-flash")

GEMINI_2_5_FLASH("gemini-2.5-flash")

GEMINI_2_5_FLASH_LITE("gemini-2.5-flash-lite")

GEMINI_2_5_PRO("gemini-2.5-pro")

OPENAI_GPT_4_1("openai-gpt-4-1")

OPENAI_GPT_4_1_MINI("openai-gpt-4-1-mini")

OPENAI_GPT_4_1_NANO("openai-gpt-4-1-nano")

OPENAI_GPT_4O("openai-gpt-4o")

OPENAI_GPT_4O_MINI("openai-gpt-4o-mini")

OPENAI_GPT_5("openai-gpt-5")

OPENAI_GPT_5_MINI("openai-gpt-5-mini")

Optional<ExtractionMode> extractionMode

The extraction mode specified (FAST, BALANCED, MULTIMODAL, PREMIUM).

One of the following:

BALANCED("BALANCED")

FAST("FAST")

MULTIMODAL("MULTIMODAL")

PREMIUM("PREMIUM")

Optional<ExtractionTarget> extractionTarget

The extraction target specified.

One of the following:

PER_DOC("PER_DOC")

PER_PAGE("PER_PAGE")

PER_TABLE_ROW("PER_TABLE_ROW")

Optional<Boolean> highResolutionMode

Whether to use high resolution mode for the extraction.

Optional<Boolean> invalidateCache

Whether to invalidate the cache for the extraction.

Optional<Boolean> multimodalFastMode

DEPRECATED: Whether to use fast mode for multimodal extraction.

Optional<Long> numPagesContext

Number of pages to pass as context on long document extraction.

minimum1

Optional<String> pageRange

Comma-separated list of page numbers or ranges to extract from (1-based, e.g., ‘1,3,5-7,9’ or ‘1-3,8-10’).

Optional<ParseModel> parseModel

Public model names.

One of the following:

ANTHROPIC_HAIKU_3_5("anthropic-haiku-3.5")

ANTHROPIC_HAIKU_4_5("anthropic-haiku-4.5")

ANTHROPIC_SONNET_3_5("anthropic-sonnet-3.5")

ANTHROPIC_SONNET_3_5_V2("anthropic-sonnet-3.5-v2")

ANTHROPIC_SONNET_3_7("anthropic-sonnet-3.7")

ANTHROPIC_SONNET_4_0("anthropic-sonnet-4.0")

ANTHROPIC_SONNET_4_5("anthropic-sonnet-4.5")

GEMINI_2_0_FLASH("gemini-2.0-flash")

GEMINI_2_0_FLASH_LITE("gemini-2.0-flash-lite")

GEMINI_2_5_FLASH("gemini-2.5-flash")

GEMINI_2_5_FLASH_LITE("gemini-2.5-flash-lite")

GEMINI_2_5_PRO("gemini-2.5-pro")

GEMINI_3_0_PRO("gemini-3.0-pro")

GEMINI_3_1_PRO("gemini-3.1-pro")

OPENAI_GPT_4_1("openai-gpt-4-1")

OPENAI_GPT_4_1_MINI("openai-gpt-4-1-mini")

OPENAI_GPT_4_1_NANO("openai-gpt-4-1-nano")

OPENAI_GPT_4O("openai-gpt-4o")

OPENAI_GPT_4O_MINI("openai-gpt-4o-mini")

OPENAI_GPT_5("openai-gpt-5")

OPENAI_GPT_5_MINI("openai-gpt-5-mini")

OPENAI_GPT_5_NANO("openai-gpt-5-nano")

OPENAI_TEXT_EMBEDDING_3_LARGE("openai-text-embedding-3-large")

OPENAI_TEXT_EMBEDDING_3_SMALL("openai-text-embedding-3-small")

OPENAI_WHISPER_1("openai-whisper-1")

Optional<Priority> priority

The priority for the request. This field may be ignored or overwritten depending on the organization tier.

One of the following:

CRITICAL("critical")

HIGH("high")

LOW("low")

MEDIUM("medium")

Optional<String> systemPrompt

The system prompt to use for the extraction.

Optional<Boolean> useReasoning

Whether to use reasoning for the extraction.

DataSchema dataSchema

The schema of the data.

One of the following:

class UnionMember0:

List<JsonValue>

String

double

boolean

String name

The name of the extraction agent.

String projectId

The ID of the project that the extraction agent belongs to.

formatuuid

Optional<LocalDateTime> createdAt

The creation time of the extraction agent.

formatdate-time

Optional<CustomConfiguration> customConfiguration

Custom configuration type for the extraction agent. Currently supports ‘default’.

Optional<LocalDateTime> updatedAt

The last update time of the extraction agent.

formatdate-time

List Extract Agents

Java

HTTP

TypeScript

Python

Go

Java

C#

CLI Tool

package ai.llamaindex.llamacloud.example;

import ai.llamaindex.llamacloud.client.LlamaCloudClient;
import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;
import ai.llamaindex.llamacloud.models.extractionagents.ExtractionAgentListPage;
import ai.llamaindex.llamacloud.models.extractionagents.ExtractionAgentListParams;

public final class Main {
    private Main() {}

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

        ExtractionAgentListPage page = client.extractionAgents().list();
    }
}

200 example

{
  "items": [
    {
      "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "config": {
        "chunk_mode": "PAGE",
        "citation_bbox": true,
        "cite_sources": true,
        "confidence_scores": true,
        "extract_model": "gemini-2.0-flash",
        "extraction_mode": "BALANCED",
        "extraction_target": "PER_DOC",
        "high_resolution_mode": true,
        "invalidate_cache": true,
        "multimodal_fast_mode": true,
        "num_pages_context": 1,
        "page_range": "page_range",
        "parse_model": "anthropic-haiku-3.5",
        "priority": "critical",
        "system_prompt": "system_prompt",
        "use_reasoning": true
      },
      "data_schema": {
        "foo": {
          "foo": "bar"
        }
      },
      "name": "name",
      "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "created_at": "2019-12-27T18:11:19.117Z",
      "custom_configuration": "default",
      "updated_at": "2019-12-27T18:11:19.117Z"
    }
  ],
  "next_page_token": "next_page_token",
  "total_size": 0
}

Returns Examples

200 example

{
  "items": [
    {
      "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "config": {
        "chunk_mode": "PAGE",
        "citation_bbox": true,
        "cite_sources": true,
        "confidence_scores": true,
        "extract_model": "gemini-2.0-flash",
        "extraction_mode": "BALANCED",
        "extraction_target": "PER_DOC",
        "high_resolution_mode": true,
        "invalidate_cache": true,
        "multimodal_fast_mode": true,
        "num_pages_context": 1,
        "page_range": "page_range",
        "parse_model": "anthropic-haiku-3.5",
        "priority": "critical",
        "system_prompt": "system_prompt",
        "use_reasoning": true
      },
      "data_schema": {
        "foo": {
          "foo": "bar"
        }
      },
      "name": "name",
      "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "created_at": "2019-12-27T18:11:19.117Z",
      "custom_configuration": "default",
      "updated_at": "2019-12-27T18:11:19.117Z"
    }
  ],
  "next_page_token": "next_page_token",
  "total_size": 0
}