Skip to content
LionrapidLionRapid Docs

Openai Quality Assessment

POST
/openai_qa
curl --request POST \
  --url https://example.com/openai_qa \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "source_text": "example", "translated_text": "example", "source_lang": "example", "target_lang": "example" }'

Evaluate translation quality using OpenAI GPT-4o.

This endpoint provides direct access to the same OpenAI-based quality assessment used in the batch evaluation workflow. It returns a quality score (0-100) and improvement suggestions for machine translations.

Requires OpenAI API key to be configured in environment variables.

Authorizations

Section titled “Authorizations”

Request Bodyrequired

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

Original text to evaluate

string
>= 1 characters
translated_text
required
Translated Text

Machine translation to evaluate

string
>= 1 characters
source_lang
required
Source Lang

Source language code (e.g., ‘en’, ‘de’)

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

Target language code (e.g., ‘de’, ‘fr’)

string
>= 1 characters <= 20 characters
Examplegenerated
{
  "source_text": "example",
  "translated_text": "example",
  "source_lang": "example",
  "target_lang": "example"
}

Responses

Section titled “Responses”

200

Section titled “200”

Successful Response

Media typeapplication/json
OpenAIQAResponse
object
score
Any of:
number
suggestion
Any of:
string
processing_time_ms
required
Processing Time Ms

Processing time in milliseconds

number
success
required
Success

Whether the quality assessment 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
{
  "score": 1,
  "suggestion": "example",
  "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": {}
    }
  ]
}