Skip to main content
POST
/
api
/
v1
/
extract
/
batch
Batch Extraction
curl --request POST \
  --url https://extraction-api.nanonets.com/api/v1/extract/batch \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'files=<string>' \
  --form output_format=markdown \
  --form files.items='@example-file'
{
  "success": true,
  "message": "<string>",
  "batch_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "total_files": 123,
  "accepted_files": 123,
  "rejected_files": 123,
  "records": [
    {
      "success": true,
      "message": "<string>",
      "record_id": "<string>",
      "status": "completed",
      "result": {
        "markdown": {
          "content": "<string>",
          "metadata": {
            "bounding_boxes": {},
            "confidence_score": {}
          }
        },
        "html": {
          "content": "<string>",
          "metadata": {
            "bounding_boxes": {},
            "confidence_score": {}
          }
        },
        "json": {
          "content": "<string>",
          "metadata": {
            "bounding_boxes": {},
            "confidence_score": {}
          }
        },
        "csv": {
          "content": "<string>",
          "metadata": {
            "bounding_boxes": {},
            "confidence_score": {}
          }
        }
      },
      "processing_time": 123,
      "filename": "<string>",
      "output_format": "<string>",
      "file_size": 123,
      "pages_processed": 123,
      "created_at": "2023-11-07T05:31:56Z"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://docstrange.nanonets.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

API key as Bearer token: Authorization: Bearer YOUR_API_KEY

Body

multipart/form-data
​
files
file[]
required

Files to process (max 50)

Maximum array length: 50
​
output_format
string
required

Output format(s) for all files

Example:

"markdown"

​
custom_instructions
string
Maximum string length: 8000
​
prompt_mode
enum<string>
default:append
Available options:
append,
replace
​
json_options
string
​
csv_options
string
​
include_metadata
string
​
extract_charts
enum<string>

When true, extracts data points from charts, graphs, and labeled technical diagrams as structured tables. Tables are inserted inline after each image in Markdown output.

Available options:
true,
false
Example:

""

​
agentic_mode
enum<string>

When true, runs an agentic post-processing pipeline that refines the JSON extraction. Requires output_format=json. Use agentic_steps to pick which steps to run.

Available options:
true,
false
Example:

""

​
agentic_steps
string

Comma-separated list of agentic steps to run. Requires agentic_mode=true. Available steps:

  • agentic_enhance — Reconciles conflicts that arise when same information is present at multiple places in large documents.
  • validate_json_schema — Validates the extracted JSON against your json_options schema and corrects any violations.
Example:

"agentic_enhance,validate_json_schema"

Response

Batch queued

​
success
boolean
required
​
message
string
required
​
batch_id
string<uuid>
required
​
total_files
integer
required
​
accepted_files
integer
required
​
rejected_files
integer
required
​
records
object[]
required