Run Job Test User

POST 
/api/v1/extractionv2/jobs/test

Run Job Test User

Request

Cookie Parameters

session any

application/json

Body

required

job_create

object

required

Schema for creating an extraction job.

extraction_agent_id uuidrequired

The id of the extraction agent

file_id uuidrequired

The id of the file

data_schema_override

object

The data schema to override the extraction agent's data schema with

anyOf

MOD1

property name*

object

anyOf

MOD1

object

MOD2

Array [

]

MOD3

string

MOD4

integer

MOD5

number

MOD6

boolean

config_override

object

The config to override the extraction agent's config with

anyOf

ExtractConfig

Additional parameters for the extraction agent.

extraction_mode ExtractMode (string)

The extraction mode specified.

Possible values: [PER_DOC, PER_PAGE]

Default value: PER_DOC

handle_missing Handle Missing (boolean)

Whether to handle missing fields in the schema.

Default value: false

system_prompt

object

The system prompt to use for the extraction.

anyOf

MOD1

string

extract_settings

object

All settings for the extraction agent. Only the settings in ExtractConfig are exposed to the user.

model Model (string)

The model to use for the extraction.

Default value: gpt-4o

temperature Temperature (number)

The temperature to use for the extraction.

Default value: 0

max_file_size Max File Size (integer)

The maximum file size (in bytes) allowed for the document.

Default value: 5242880

max_num_pages Max Num Pages (integer)

The maximum number of pages allowed for the document.

Default value: 30

extraction_prompt Extraction Prompt (string)

The prompt to use for the extraction.

Default value: The extracted data using the given JSON schema.

error_handling_prompt Error Handling Prompt (string)

The prompt to use for error handling.

Default value: If the text does not contain enough information to comply with the schema, explain the reason. Else, output null and fill out the 'extracted' field.

llama_parse_params

object

Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.

languages ParserLanguages (string)[]

Possible values: [af, az, bs, cs, cy, da, de, en, es, et, fr, ga, hr, hu, id, is, it, ku, la, lt, lv, mi, ms, mt, nl, no, oc, pi, pl, pt, ro, rs_latin, sk, sl, sq, sv, sw, tl, tr, uz, vi, ar, fa, ug, ur, bn, as, mni, ru, rs_cyrillic, be, bg, uk, mn, abq, ady, kbd, ava, dar, inh, che, lbe, lez, tab, tjk, hi, mr, ne, bh, mai, ang, bho, mah, sck, new, gom, sa, bgc, th, ch_sim, ch_tra, ja, ko, ta, te, kn], >= 1

parsing_instruction Parsing Instruction (string)

Default value:

disable_ocr Disable Ocr (boolean)

Default value: false

annotate_links Annotate Links (boolean)

Default value: false

disable_reconstruction Disable Reconstruction (boolean)

Default value: false

disable_image_extraction Disable Image Extraction (boolean)

Default value: false

invalidate_cache Invalidate Cache (boolean)

Default value: false

output_pdf_of_document Output Pdf Of Document (boolean)

Default value: false

do_not_cache Do Not Cache (boolean)

Default value: false

fast_mode Fast Mode (boolean)

Default value: false

skip_diagonal_text Skip Diagonal Text (boolean)

Default value: false

gpt4o_mode Gpt4O Mode (boolean)

Default value: false

gpt4o_api_key Gpt4O Api Key (string)

Default value:

do_not_unroll_columns Do Not Unroll Columns (boolean)

Default value: false

extract_layout Extract Layout (boolean)

Default value: false

html_make_all_elements_visible Html Make All Elements Visible (boolean)

Default value: false

html_remove_navigation_elements Html Remove Navigation Elements (boolean)

Default value: false

html_remove_fixed_elements Html Remove Fixed Elements (boolean)

Default value: false

guess_xlsx_sheet_name Guess Xlsx Sheet Name (boolean)

Default value: false

page_separator

object

anyOf

MOD1

string

bounding_box Bounding Box (string)

Default value:

bbox_top

object

anyOf

MOD1

number

bbox_right

object

anyOf

MOD1

number

bbox_bottom

object

anyOf

MOD1

number

bbox_left

object

anyOf

MOD1

number

target_pages Target Pages (string)

Default value:

use_vendor_multimodal_model Use Vendor Multimodal Model (boolean)

Default value: false

vendor_multimodal_model_name Vendor Multimodal Model Name (string)

Default value:

vendor_multimodal_api_key Vendor Multimodal Api Key (string)

Default value:

page_prefix Page Prefix (string)

Default value:

page_suffix Page Suffix (string)

Default value:

webhook_url Webhook Url (string)

Default value:

take_screenshot Take Screenshot (boolean)

Default value: false

is_formatting_instruction Is Formatting Instruction (boolean)

Default value: true

premium_mode Premium Mode (boolean)

Default value: false

continuous_mode Continuous Mode (boolean)

Default value: false

s3_input_path S3 Input Path (string)

Default value:

input_s3_region Input S3 Region (string)

Default value:

s3_output_path_prefix S3 Output Path Prefix (string)

Default value:

output_s3_region Output S3 Region (string)

Default value:

project_id

object

anyOf

MOD1

string

azure_openai_deployment_name

object

anyOf

MOD1

string

azure_openai_endpoint

object

anyOf

MOD1

string

azure_openai_api_version

object

anyOf

MOD1

string

azure_openai_key

object

anyOf

MOD1

string

input_url

object

anyOf

MOD1

string

http_proxy

object

anyOf

MOD1

string

auto_mode Auto Mode (boolean)

Default value: false

auto_mode_trigger_on_regexp_in_page

object

anyOf

MOD1

string

auto_mode_trigger_on_text_in_page

object

anyOf

MOD1

string

auto_mode_trigger_on_table_in_page Auto Mode Trigger On Table In Page (boolean)

Default value: false

auto_mode_trigger_on_image_in_page Auto Mode Trigger On Image In Page (boolean)

Default value: false

structured_output Structured Output (boolean)

Default value: false

structured_output_json_schema

object

anyOf

MOD1

string

structured_output_json_schema_name

object

anyOf

MOD1

string

max_pages

object

anyOf

MOD1

integer

max_pages_enforced

object

anyOf

MOD1

integer

extract_charts Extract Charts (boolean)

Default value: false

formatting_instruction

object

anyOf

MOD1

string

complemental_formatting_instruction

object

anyOf

MOD1

string

content_guideline_instruction

object

anyOf

MOD1

string

spreadsheet_extract_sub_tables Spreadsheet Extract Sub Tables (boolean)

Default value: false

job_timeout_in_seconds

object

anyOf

MOD1

number

job_timeout_extra_time_per_page_in_seconds

object

anyOf

MOD1

number

strict_mode_image_extraction Strict Mode Image Extraction (boolean)

Default value: false

strict_mode_image_ocr Strict Mode Image Ocr (boolean)

Default value: false

strict_mode_reconstruction Strict Mode Reconstruction (boolean)

Default value: false

strict_mode_buggy_font Strict Mode Buggy Font (boolean)

Default value: false

Responses

200

Successful Response

application/json

Schema

Schema

id uuidrequired

The id of the extraction job

extraction_agent

object

required

Schema and configuration for creating an extraction agent.

id uuidrequired

The id of the extraction agent.

name Name (string)required

The name of the extraction agent.

project_id uuidrequired

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

data_schema

object

required

The schema of the data.

property name*

object

anyOf

MOD1

object

MOD2

Array [

]

MOD3

string

MOD4

integer

MOD5

number

MOD6

boolean

config

object

required

The configuration parameters for the extraction agent.

extraction_mode ExtractMode (string)

The extraction mode specified.

Possible values: [PER_DOC, PER_PAGE]

Default value: PER_DOC

handle_missing Handle Missing (boolean)

Whether to handle missing fields in the schema.

Default value: false

system_prompt

object

The system prompt to use for the extraction.

anyOf

MOD1

string

created_at

object

The creation time of the extraction agent.

anyOf

MOD1

string

updated_at

object

The last update time of the extraction agent.

anyOf

MOD1

string

status StatusEnum (string)required

Enum for representing the status of a job

Possible values: [PENDING, SUCCESS, ERROR, PARTIAL_SUCCESS, CANCELLED]

error

object

The error that occurred during extraction

anyOf

MOD1

string

file

object

required

Schema for a file.

id uuidrequired

Unique identifier

created_at

object

Creation datetime

anyOf

MOD1

string

updated_at

object

Update datetime

anyOf

MOD1

string

name Name (string)required

Possible values: non-empty and <= 3000 characters

external_file_id External File Id (string)required

The ID of the file in the external system

file_size

object

Size of the file in bytes

anyOf

MOD1

integer

file_type

object

File type (e.g. pdf, docx, etc.)

anyOf

MOD1

string

Possible values: non-empty and <= 3000 characters

project_id uuidrequired

The ID of the project that the file belongs to

last_modified_at

object

The last modified time of the file

anyOf

MOD1

string

resource_info

object

Resource information for the file

anyOf

MOD1

property name*

object

anyOf

MOD1

object

MOD2

Array [

]

MOD3

string

MOD4

integer

MOD5

number

MOD6

boolean

permission_info

object

Permission information for the file

anyOf

MOD1

property name*

object

anyOf

MOD1

object

MOD2

Array [

]

MOD3

string

MOD4

integer

MOD5

number

MOD6

boolean

data_source_id

object

The ID of the data source that the file belongs to

anyOf

MOD1

string

Example (from schema)

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "extraction_agent": {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "name": "string",
    "project_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "data_schema": {},
    "config": {
      "extraction_mode": "PER_DOC",
      "handle_missing": false,
      "system_prompt": "string"
    },
    "created_at": "2024-07-29T15:51:28.071Z",
    "updated_at": "2024-07-29T15:51:28.071Z"
  },
  "status": "PENDING",
  "error": "string",
  "file": {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "created_at": "2024-07-29T15:51:28.071Z",
    "updated_at": "2024-07-29T15:51:28.071Z",
    "name": "string",
    "external_file_id": "string",
    "file_size": 0,
    "file_type": "string",
    "project_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "last_modified_at": "2024-07-29T15:51:28.071Z",
    "resource_info": {},
    "permission_info": {},
    "data_source_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6"
  }
}

422

Validation Error

application/json

Schema

Schema

detail

object[]

Array [

loc

object[]

required

Array [

anyOf

MOD1

string

MOD2

integer

]

msg Message (string)required

type Error Type (string)required

]

Example (from schema)

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}