Skip to content
LionrapidLionrapid Docs

Map Inline Formatting Openai Endpoint

POST
/format/map_inline_formatting_openai
curl --request POST \
  --url https://example.com/format/map_inline_formatting_openai \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "source_text": "example", "target_translation": "example", "source_lang": "example", "target_lang": "example", "spans": [ { "id": "example", "text": "example", "type": "example" } ], "system_prompt": "example", "model": "example" }'

Map inline formatting spans using OpenAI with a custom system prompt and model override.

Same task as /format/map_inline_formatting but accepts:

  • system_prompt: custom system prompt (defaults to the standard formatting mapping prompt)
  • model: OpenAI model name (defaults to “gpt-4o”)

Authorizations

Section titled “Authorizations”

Request Bodyrequired

Section titled “Request Bodyrequired”
Media typeapplication/json
CustomFormattingRequest
object
source_text
required
Source Text

Full source text

string
>= 1 characters
target_translation
required
Target Translation

Full translated text

string
>= 1 characters
source_lang
required
Source Lang

Source language code (e.g. ‘en’)

string
>= 1 characters <= 20 characters
target_lang
required
Target Lang

Target language code (e.g. ‘de’)

string
>= 1 characters <= 20 characters
spans
required
Spans

Formatting spans to map from source to target

Array<object>
>= 1 items
FormattingSpan
object
id
required
Id

UUID of the source formatting span

string
text
required
Text

The formatted text in the source

string
>= 1 characters
type
required
Type

Formatting type: bold, italic, underline, etc.

string
system_prompt
Any of:
string
model
Any of:
string
<= 200 characters
Examplegenerated
{
  "source_text": "example",
  "target_translation": "example",
  "source_lang": "example",
  "target_lang": "example",
  "spans": [
    {
      "id": "example",
      "text": "example",
      "type": "example"
    }
  ],
  "system_prompt": "example",
  "model": "example"
}

Responses

Section titled “Responses”

200

Section titled “200”

Successful Response

Media typeapplication/json
FormattingResponse
object
mappings
required
Mappings

Successfully mapped formatting spans

Array<object>
FormattingMapping
object
source_id
required
Source Id

UUID of the source span this mapping refers to

string
target_text
required
Target Text

Exact substring of the target translation to format

string
confidence
required
Confidence

Model confidence for this mapping

number
<= 1
dropped_count
required
Dropped Count

Spans dropped due to failed self-check or low confidence

integer
processing_time_ms
required
Processing Time Ms

Processing time in milliseconds

number
success
required
Success

Whether the mapping call succeeded

boolean
error_message
Any of:
string
usage
Any of:
TokenUsage
object
prompt_tokens
Any of:
integer
completion_tokens
Any of:
integer
total_tokens
Any of:
integer
quantization
Any of:
string
gpu_mem_allocated_gb
Any of:
number
gpu_mem_reserved_gb
Any of:
number
Examplegenerated
{
  "mappings": [
    {
      "source_id": "example",
      "target_text": "example",
      "confidence": 1
    }
  ],
  "dropped_count": 1,
  "processing_time_ms": 1,
  "success": true,
  "error_message": "example",
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1,
    "quantization": "example",
    "gpu_mem_allocated_gb": 1,
    "gpu_mem_reserved_gb": 1
  }
}

422

Section titled “422”

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{
  "detail": [
    {
      "loc": [
        "example"
      ],
      "msg": "example",
      "type": "example",
      "input": "example",
      "ctx": {}
    }
  ]
}