Account
configureWebhook
account.configureWebhook
Open the Svix webhook portal URL for this account
Risk: write
await corsair.reducto.api.account.configureWebhook({});
string
version
account.version
Read the Reducto API version
Risk: read
await corsair.reducto.api.account.version({});
string
Classify
classify
classify.classify
Classify a document against a list of categories
Risk: write
await corsair.reducto.api.classify.classify({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
classification_schema | object[] | No | — |
category_groups | Record<string, any> | No | — |
page_range | object | object[] | number[] | null | No | — |
document_metadata | string | null | No | — |
model | default | accurate | No | — |
priority | boolean | No | — |
force_url_result | boolean | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
classification_schema full type
classification_schema full type
{
category: string,
criteria: string[]
}[]
page_range full type
page_range full type
{
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
result | object | Yes | — |
duration | number | null | No | — |
usage | object | null | No | — |
result full type
result full type
{
category: string
} | {
type: url,
url: string,
result_id: string
}
usage full type
usage full type
{
num_pages: number,
credits?: number | null,
num_categories: number
} | null
classifyAsync
classify.classifyAsync
Start a classify job and return its job id
Risk: write
await corsair.reducto.api.classify.classifyAsync({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
classification_schema | object[] | No | — |
category_groups | Record<string, any> | No | — |
page_range | object | object[] | number[] | null | No | — |
document_metadata | string | null | No | — |
model | default | accurate | No | — |
priority | boolean | No | — |
force_url_result | boolean | No | — |
async | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
classification_schema full type
classification_schema full type
{
category: string,
criteria: string[]
}[]
page_range full type
page_range full type
{
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null
async full type
async full type
{
metadata?: Record<string, any> | null,
priority?: boolean,
webhook?: {
mode: direct,
url: string
} | {
mode: svix,
channels?: string[]
} | {
mode: disabled,
channels?: string[]
} | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
Edit
edit
edit.edit
Fill or edit a PDF or DOCX from natural language instructions
Risk: write
await corsair.reducto.api.edit.edit({});
| Name | Type | Required | Description |
|---|---|---|---|
document_url | string | object | Yes | — |
edit_instructions | string | Yes | — |
edit_options | object | No | — |
form_schema | any[] | null | No | — |
priority | boolean | No | — |
document_url full type
document_url full type
string | {
file_id: string,
presigned_url?: string | null
}
edit_options full type
edit_options full type
{
color?: string,
font_size?: number | null,
llm_provider_preference?: string | null,
enable_overflow_pages?: boolean,
flatten?: boolean
}
| Name | Type | Required | Description |
|---|---|---|---|
document_url | string | Yes | — |
job_id | string | null | No | — |
form_schema | any[] | null | No | — |
usage | object | null | No | — |
usage full type
usage full type
{
num_pages: number,
credits?: number | null
} | null
editAsync
edit.editAsync
Start an edit job and return its job id
Risk: write
await corsair.reducto.api.edit.editAsync({});
| Name | Type | Required | Description |
|---|---|---|---|
document_url | string | object | Yes | — |
edit_instructions | string | Yes | — |
edit_options | object | No | — |
form_schema | any[] | null | No | — |
priority | boolean | No | — |
webhook | object | No | — |
document_url full type
document_url full type
string | {
file_id: string,
presigned_url?: string | null
}
edit_options full type
edit_options full type
{
color?: string,
font_size?: number | null,
llm_provider_preference?: string | null,
enable_overflow_pages?: boolean,
flatten?: boolean
}
webhook full type
webhook full type
{
mode: direct,
url: string
} | {
mode: svix,
channels?: string[]
} | {
mode: disabled,
channels?: string[]
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
Extract
extract
extract.extract
Extract fields from a document using a JSON schema
Risk: write
await corsair.reducto.api.extract.extract({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
parsing | object | No | — |
instructions | object | No | — |
settings | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
parsing full type
parsing full type
{
enhance?: {
agentic?: {
scope: text | table | figure,
prompt?: string | null,
mode?: default | auto | max,
advanced_chart_agent?: boolean,
return_overlays?: boolean
}[],
advanced_chart_agent?: boolean,
summarize_figures?: boolean,
intelligent_ordering?: boolean
},
retrieval?: {
chunking?: {
chunk_mode?: variable | section | page | disabled | block | page_sections,
chunk_size?: number | null,
chunk_overlap?: number
},
filter_blocks?: (Header | Footer | Title | Section Header | Page Number | List Item | Figure | Table | Key Value | Text | Comment | Signature)[],
embedding_optimized?: boolean
},
formatting?: {
add_page_markers?: boolean,
table_output_format?: html | json | md | jsonbbox | dynamic | csv,
merge_tables?: boolean,
include?: (change_tracking | highlight | comments | hyperlinks | signatures | ignore_watermarks)[]
},
spreadsheet?: {
split_large_tables?: {
enabled?: boolean,
size?: number
},
include?: (cell_colors | formula | dropdowns)[],
clustering?: accurate | fast | disabled,
exclude?: string[],
max_cell_count?: number | null
},
settings?: {
ocr_system?: standard | legacy,
extraction_mode?: ocr | hybrid,
force_url_result?: boolean,
force_file_extension?: string | null,
return_ocr_data?: boolean,
return_images?: (figure | table | page)[],
embed_pdf_metadata?: boolean,
extract_document_properties?: boolean,
embed_pdf_metadata_dpi?: number,
persist_results?: boolean,
timeout?: number | null,
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null,
document_password?: string | null,
model?: string | null
}
}
instructions full type
instructions full type
{
schema?: any,
system_prompt?: string
}
settings full type
settings full type
{
include_images?: boolean,
optimize_for_latency?: boolean,
force_url_result?: boolean,
array_extract?: boolean,
deep_extract?: boolean,
citations?: {
enabled?: boolean,
numerical_confidence?: boolean,
parent_block?: string
},
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null
}
| Name | Type | Required | Description |
|---|---|---|---|
usage | object | Yes | — |
result | any[] | Record<string, any> | object | Yes | — |
citations | any[] | object | null | No | — |
job_id | string | null | No | — |
duration | number | null | No | — |
studio_link | string | null | No | — |
usage full type
usage full type
{
num_pages: number,
credits?: number | null,
num_fields: number
}
result full type
result full type
any[] | Record<string, any> | {
type: url,
url: string,
result_id: string
}
citations full type
citations full type
any[] | {
type: url,
url: string,
result_id: string
} | null
extractAsync
extract.extractAsync
Start an extract job and return its job id
Risk: write
await corsair.reducto.api.extract.extractAsync({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
parsing | object | No | — |
instructions | object | No | — |
settings | object | No | — |
async | object | No | — |
queue_priority | auto | standard | batch | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
parsing full type
parsing full type
{
enhance?: {
agentic?: {
scope: text | table | figure,
prompt?: string | null,
mode?: default | auto | max,
advanced_chart_agent?: boolean,
return_overlays?: boolean
}[],
advanced_chart_agent?: boolean,
summarize_figures?: boolean,
intelligent_ordering?: boolean
},
retrieval?: {
chunking?: {
chunk_mode?: variable | section | page | disabled | block | page_sections,
chunk_size?: number | null,
chunk_overlap?: number
},
filter_blocks?: (Header | Footer | Title | Section Header | Page Number | List Item | Figure | Table | Key Value | Text | Comment | Signature)[],
embedding_optimized?: boolean
},
formatting?: {
add_page_markers?: boolean,
table_output_format?: html | json | md | jsonbbox | dynamic | csv,
merge_tables?: boolean,
include?: (change_tracking | highlight | comments | hyperlinks | signatures | ignore_watermarks)[]
},
spreadsheet?: {
split_large_tables?: {
enabled?: boolean,
size?: number
},
include?: (cell_colors | formula | dropdowns)[],
clustering?: accurate | fast | disabled,
exclude?: string[],
max_cell_count?: number | null
},
settings?: {
ocr_system?: standard | legacy,
extraction_mode?: ocr | hybrid,
force_url_result?: boolean,
force_file_extension?: string | null,
return_ocr_data?: boolean,
return_images?: (figure | table | page)[],
embed_pdf_metadata?: boolean,
extract_document_properties?: boolean,
embed_pdf_metadata_dpi?: number,
persist_results?: boolean,
timeout?: number | null,
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null,
document_password?: string | null,
model?: string | null
}
}
instructions full type
instructions full type
{
schema?: any,
system_prompt?: string
}
settings full type
settings full type
{
include_images?: boolean,
optimize_for_latency?: boolean,
force_url_result?: boolean,
array_extract?: boolean,
deep_extract?: boolean,
citations?: {
enabled?: boolean,
numerical_confidence?: boolean,
parent_block?: string
},
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null
}
async full type
async full type
{
metadata?: Record<string, any> | null,
priority?: boolean,
webhook?: {
mode: direct,
url: string
} | {
mode: svix,
channels?: string[]
} | {
mode: disabled,
channels?: string[]
} | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
Files
delete
files.delete
Delete an uploaded file. Free plans return 422 NOT_APPLICABLE; Growth and Enterprise delete it
Risk: destructive · Irreversible
await corsair.reducto.api.files.delete({});
| Name | Type | Required | Description |
|---|---|---|---|
file_id | string | Yes | — |
| Name | Type | Required | Description |
|---|---|---|---|
file_id | string | Yes | — |
upload
files.upload
Upload a file and return a reducto:// file id
Risk: write
await corsair.reducto.api.files.upload({});
| Name | Type | Required | Description |
|---|---|---|---|
file | string | object | custom | Yes | — |
extension | string | null | No | — |
file full type
file full type
string | {
url: string,
filename?: string,
contentType?: string
} | {
base64: string,
filename?: string,
contentType?: string
} | custom
| Name | Type | Required | Description |
|---|---|---|---|
file_id | string | Yes | — |
presigned_url | string | null | No | — |
Jobs
cancel
jobs.cancel
Cancel a running job
Risk: destructive
await corsair.reducto.api.jobs.cancel({});
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
Record<string, any> \| null \| undefined
delete
jobs.delete
Delete a job and its stored artifacts. Returns 202. Free plans return 422 NOT_APPLICABLE
Risk: destructive · Irreversible
await corsair.reducto.api.jobs.delete({});
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
include_persisted | boolean | No | — |
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
get
jobs.get
Retrieve a job status and, when finished, its result
Risk: read
await corsair.reducto.api.jobs.get({});
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
| Name | Type | Required | Description |
|---|---|---|---|
status | string | Yes | — |
result | any | null | No | — |
progress | number | null | No | — |
reason | string | null | No | — |
error | any | null | No | — |
type | string | null | No | — |
source | any | null | No | — |
num_pages | number | null | No | — |
total_pages | number | null | No | — |
duration | number | null | No | — |
created_at | string | null | No | — |
bucket | any | null | No | — |
list
jobs.list
List jobs, page by page, using cursor and limit
Risk: read
await corsair.reducto.api.jobs.list({});
| Name | Type | Required | Description |
|---|---|---|---|
exclude_configs | boolean | No | — |
cursor | string | null | No | — |
limit | number | No | — |
| Name | Type | Required | Description |
|---|---|---|---|
jobs | object[] | Yes | — |
next_cursor | string | null | No | — |
jobs full type
jobs full type
{
job_id: string,
status: string,
type: string,
raw_config?: string,
created_at: string,
source?: any | null,
num_pages?: number | null,
total_pages?: number | null,
duration?: number | null,
bucket?: any | null
}[]
Parse
parse
parse.parse
Parse a document into chunks of text, tables, and figures with bounding boxes
Risk: write
await corsair.reducto.api.parse.parse({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
enhance | object | No | — |
retrieval | object | No | — |
formatting | object | No | — |
spreadsheet | object | No | — |
settings | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
enhance full type
enhance full type
{
agentic?: {
scope: text | table | figure,
prompt?: string | null,
mode?: default | auto | max,
advanced_chart_agent?: boolean,
return_overlays?: boolean
}[],
advanced_chart_agent?: boolean,
summarize_figures?: boolean,
intelligent_ordering?: boolean
}
retrieval full type
retrieval full type
{
chunking?: {
chunk_mode?: variable | section | page | disabled | block | page_sections,
chunk_size?: number | null,
chunk_overlap?: number
},
filter_blocks?: (Header | Footer | Title | Section Header | Page Number | List Item | Figure | Table | Key Value | Text | Comment | Signature)[],
embedding_optimized?: boolean
}
formatting full type
formatting full type
{
add_page_markers?: boolean,
table_output_format?: html | json | md | jsonbbox | dynamic | csv,
merge_tables?: boolean,
include?: (change_tracking | highlight | comments | hyperlinks | signatures | ignore_watermarks)[]
}
spreadsheet full type
spreadsheet full type
{
split_large_tables?: {
enabled?: boolean,
size?: number
},
include?: (cell_colors | formula | dropdowns)[],
clustering?: accurate | fast | disabled,
exclude?: string[],
max_cell_count?: number | null
}
settings full type
settings full type
{
ocr_system?: standard | legacy,
extraction_mode?: ocr | hybrid,
force_url_result?: boolean,
force_file_extension?: string | null,
return_ocr_data?: boolean,
return_images?: (figure | table | page)[],
embed_pdf_metadata?: boolean,
extract_document_properties?: boolean,
embed_pdf_metadata_dpi?: number,
persist_results?: boolean,
timeout?: number | null,
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null,
document_password?: string | null,
model?: string | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
duration | number | Yes | — |
usage | object | Yes | — |
result | object | Yes | — |
response_type | string | null | No | — |
pdf_url | string | null | No | — |
studio_link | string | null | No | — |
document_properties | object | null | No | — |
usage full type
usage full type
{
num_pages: number,
credits?: number | null
}
result full type
result full type
{
type: full,
chunks: {
content: string,
embed?: string,
blocks?: {
type: string,
content?: string,
bbox?: {
left: number,
top: number,
width: number,
height: number,
page: number,
original_page?: number
},
confidence?: string | null,
granular_confidence?: {
parse_confidence?: number | null,
extract_confidence?: number | null
} | null,
image_url?: string | null,
chart_data?: string[] | null,
merged_tables?: any[] | null,
extra?: Record<string, any> | null
}[],
enriched?: string | null,
enrichment_success?: boolean
}[],
ocr?: {
words?: {
text: string,
bbox: {
left: number,
top: number,
width: number,
height: number,
page: number,
original_page?: number
},
confidence?: number | null,
chunk_index?: number | null,
rotation?: number | null
}[],
lines?: {
text: string,
bbox: {
left: number,
top: number,
width: number,
height: number,
page: number,
original_page?: number
},
confidence?: number | null,
chunk_index?: number | null,
rotation?: number | null
}[]
} | null,
custom?: any | null
} | {
type: url,
url: string,
result_id: string
}
document_properties full type
document_properties full type
{
title?: string | null,
author?: string | null,
subject?: string | null,
keywords?: string | null,
creator?: string | null,
producer?: string | null,
last_modified_by?: string | null,
created_at?: string | null,
modified_at?: string | null
} | null
parseAsync
parse.parseAsync
Start a parse job and return its job id
Risk: write
await corsair.reducto.api.parse.parseAsync({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
enhance | object | No | — |
retrieval | object | No | — |
formatting | object | No | — |
spreadsheet | object | No | — |
settings | object | No | — |
async | object | No | — |
queue_priority | auto | standard | batch | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
enhance full type
enhance full type
{
agentic?: {
scope: text | table | figure,
prompt?: string | null,
mode?: default | auto | max,
advanced_chart_agent?: boolean,
return_overlays?: boolean
}[],
advanced_chart_agent?: boolean,
summarize_figures?: boolean,
intelligent_ordering?: boolean
}
retrieval full type
retrieval full type
{
chunking?: {
chunk_mode?: variable | section | page | disabled | block | page_sections,
chunk_size?: number | null,
chunk_overlap?: number
},
filter_blocks?: (Header | Footer | Title | Section Header | Page Number | List Item | Figure | Table | Key Value | Text | Comment | Signature)[],
embedding_optimized?: boolean
}
formatting full type
formatting full type
{
add_page_markers?: boolean,
table_output_format?: html | json | md | jsonbbox | dynamic | csv,
merge_tables?: boolean,
include?: (change_tracking | highlight | comments | hyperlinks | signatures | ignore_watermarks)[]
}
spreadsheet full type
spreadsheet full type
{
split_large_tables?: {
enabled?: boolean,
size?: number
},
include?: (cell_colors | formula | dropdowns)[],
clustering?: accurate | fast | disabled,
exclude?: string[],
max_cell_count?: number | null
}
settings full type
settings full type
{
ocr_system?: standard | legacy,
extraction_mode?: ocr | hybrid,
force_url_result?: boolean,
force_file_extension?: string | null,
return_ocr_data?: boolean,
return_images?: (figure | table | page)[],
embed_pdf_metadata?: boolean,
extract_document_properties?: boolean,
embed_pdf_metadata_dpi?: number,
persist_results?: boolean,
timeout?: number | null,
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null,
document_password?: string | null,
model?: string | null
}
async full type
async full type
{
metadata?: Record<string, any> | null,
priority?: boolean,
webhook?: {
mode: direct,
url: string
} | {
mode: svix,
channels?: string[]
} | {
mode: disabled,
channels?: string[]
} | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
Pipeline
run
pipeline.run
Run a Studio pipeline against a document
Risk: write
await corsair.reducto.api.pipeline.run({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
pipeline_id | string | Yes | — |
settings | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
settings full type
settings full type
{
document_password?: string | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
usage | object | Yes | — |
result | any | Yes | — |
usage full type
usage full type
{
num_pages: number,
credits?: number | null
}
runAsync
pipeline.runAsync
Start a Studio pipeline job and return its job id
Risk: write
await corsair.reducto.api.pipeline.runAsync({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
pipeline_id | string | Yes | — |
settings | object | No | — |
async | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
settings full type
settings full type
{
document_password?: string | null
}
async full type
async full type
{
metadata?: Record<string, any> | null,
priority?: boolean,
webhook?: {
mode: direct,
url: string
} | {
mode: svix,
channels?: string[]
} | {
mode: disabled,
channels?: string[]
} | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |
Split
split
split.split
Split a document into named sections by page
Risk: write
await corsair.reducto.api.split.split({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
parsing | object | No | — |
split_description | object[] | Yes | — |
split_rules | string | No | — |
settings | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
parsing full type
parsing full type
{
enhance?: {
agentic?: {
scope: text | table | figure,
prompt?: string | null,
mode?: default | auto | max,
advanced_chart_agent?: boolean,
return_overlays?: boolean
}[],
advanced_chart_agent?: boolean,
summarize_figures?: boolean,
intelligent_ordering?: boolean
},
retrieval?: {
chunking?: {
chunk_mode?: variable | section | page | disabled | block | page_sections,
chunk_size?: number | null,
chunk_overlap?: number
},
filter_blocks?: (Header | Footer | Title | Section Header | Page Number | List Item | Figure | Table | Key Value | Text | Comment | Signature)[],
embedding_optimized?: boolean
},
formatting?: {
add_page_markers?: boolean,
table_output_format?: html | json | md | jsonbbox | dynamic | csv,
merge_tables?: boolean,
include?: (change_tracking | highlight | comments | hyperlinks | signatures | ignore_watermarks)[]
},
spreadsheet?: {
split_large_tables?: {
enabled?: boolean,
size?: number
},
include?: (cell_colors | formula | dropdowns)[],
clustering?: accurate | fast | disabled,
exclude?: string[],
max_cell_count?: number | null
},
settings?: {
ocr_system?: standard | legacy,
extraction_mode?: ocr | hybrid,
force_url_result?: boolean,
force_file_extension?: string | null,
return_ocr_data?: boolean,
return_images?: (figure | table | page)[],
embed_pdf_metadata?: boolean,
extract_document_properties?: boolean,
embed_pdf_metadata_dpi?: number,
persist_results?: boolean,
timeout?: number | null,
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null,
document_password?: string | null,
model?: string | null
}
}
split_description full type
split_description full type
{
name: string,
description: string,
partition_key?: string | null
}[]
settings full type
settings full type
{
table_cutoff?: truncate | preserve,
allow_page_overlap?: boolean,
auto_partition?: boolean,
deep_split?: boolean,
force_url_result?: boolean
}
| Name | Type | Required | Description |
|---|---|---|---|
usage | object | Yes | — |
result | object | Record<string, any> | Yes | — |
job_id | string | null | No | — |
duration | number | null | No | — |
usage full type
usage full type
{
num_pages: number,
credits?: number | null
}
result full type
result full type
{
splits: {
name: string,
pages: number[]
}[]
} | {
type: url,
url: string,
result_id: string
} | Record<string, any>
splitAsync
split.splitAsync
Start a split job and return its job id
Risk: write
await corsair.reducto.api.split.splitAsync({});
| Name | Type | Required | Description |
|---|---|---|---|
input | string | string[] | object | Yes | — |
parsing | object | No | — |
split_description | object[] | Yes | — |
split_rules | string | No | — |
settings | object | No | — |
async | object | No | — |
input full type
input full type
string | string[] | {
file_id: string,
presigned_url?: string | null
}
parsing full type
parsing full type
{
enhance?: {
agentic?: {
scope: text | table | figure,
prompt?: string | null,
mode?: default | auto | max,
advanced_chart_agent?: boolean,
return_overlays?: boolean
}[],
advanced_chart_agent?: boolean,
summarize_figures?: boolean,
intelligent_ordering?: boolean
},
retrieval?: {
chunking?: {
chunk_mode?: variable | section | page | disabled | block | page_sections,
chunk_size?: number | null,
chunk_overlap?: number
},
filter_blocks?: (Header | Footer | Title | Section Header | Page Number | List Item | Figure | Table | Key Value | Text | Comment | Signature)[],
embedding_optimized?: boolean
},
formatting?: {
add_page_markers?: boolean,
table_output_format?: html | json | md | jsonbbox | dynamic | csv,
merge_tables?: boolean,
include?: (change_tracking | highlight | comments | hyperlinks | signatures | ignore_watermarks)[]
},
spreadsheet?: {
split_large_tables?: {
enabled?: boolean,
size?: number
},
include?: (cell_colors | formula | dropdowns)[],
clustering?: accurate | fast | disabled,
exclude?: string[],
max_cell_count?: number | null
},
settings?: {
ocr_system?: standard | legacy,
extraction_mode?: ocr | hybrid,
force_url_result?: boolean,
force_file_extension?: string | null,
return_ocr_data?: boolean,
return_images?: (figure | table | page)[],
embed_pdf_metadata?: boolean,
extract_document_properties?: boolean,
embed_pdf_metadata_dpi?: number,
persist_results?: boolean,
timeout?: number | null,
page_range?: {
start?: number | null,
end?: number | null
} | {
start?: number | null,
end?: number | null
}[] | number[] | null,
document_password?: string | null,
model?: string | null
}
}
split_description full type
split_description full type
{
name: string,
description: string,
partition_key?: string | null
}[]
settings full type
settings full type
{
table_cutoff?: truncate | preserve,
allow_page_overlap?: boolean,
auto_partition?: boolean,
deep_split?: boolean,
force_url_result?: boolean
}
async full type
async full type
{
metadata?: Record<string, any> | null,
priority?: boolean,
webhook?: {
mode: direct,
url: string
} | {
mode: svix,
channels?: string[]
} | {
mode: disabled,
channels?: string[]
} | null
}
| Name | Type | Required | Description |
|---|---|---|---|
job_id | string | Yes | — |