LangWatch home page

langwatch/langwatch
Support
Dashboard
langwatch/langwatch

API Endpoints

Language Detection

Documentation

Introduction
Evaluators
Unit Tests
API Example
How to Choose Your Evaluator Guide
Modular Architecture

Tutorials

Extensive Unit Testing
RAG Evaluation
Evaluate on CI/CD Pipeline

API Endpoints

POST
Language Detection
POST
OpenAI Moderation
POST
PII Detection
POST
Content Safety
POST
Jailbreak Detection
POST
Prompt Injection Detection
POST
Competitor Detection with LLM
POST
Prompt Injection Detection
POST
Off-Topic Detection
POST
Answer Relevancy
POST
Context Precision
POST
Context Recall
POST
Context Relevancy
POST
Context Utilization
POST
Faithfulness
POST
Haystack Faithfulness
POST
LLM Boolean Evaluator
POST
LLM Score Evaluator
POST
LLM Basic Evaluator
POST
LLM Similarity Evaluator
POST
Llama Guard

API Endpoints

Language Detection

This evaluator detects the language of the input and output text to check for example if the generated answer is in the same language as the prompt, or if it’s in a specific expected language.

Docs: https://github.com/pemistahl/lingua-py

POST

lingua

language_detection

evaluate

object

data

array

data

Required

array

List of entries to be evaluated, check the field type for the necessary keys

settings

object

settings

object

Evaluator settings, check the field type for what settings this evaluator supports

check_for

enum<string>

check_for

enum<string>

What should be checked

expected_language

enum<string>

expected_language

enum<string>

The specific language that the output is expected to be

min_words

integer

min_words

integer

Minimum number of words to check, as the language detection can be unreliable for very short texts. Inputs shorter than the minimum will be skipped.

threshold

number

threshold

number

Minimum confidence threshold for the language detection. If the confidence is lower than this, the evaluation will be skipped.

env

object

env

object

Optional environment variables to override the server ones

Add Example Value

Body

application/json

data

object[]

required

List of entries to be evaluated, check the field type for the necessary keys

data.input

string

required

data.output

string

required

settings

object | null

Evaluator settings, check the field type for what settings this evaluator supports

settings.check_for

enum<string>

default: input_matches_output

What should be checked

Available options:

input_matches_output,

output_matches_language

settings.expected_language

enum<string> | null

The specific language that the output is expected to be

Available options:

AF,

AR,

AZ,

BE,

BG,

BN,

BS,

CA,

CS,

CY,

DA,

DE,

EL,

EN,

EO,

ES,

ET,

EU,

FA,

FI,

FR,

GA,

GU,

HE,

HI,

HR,

HU,

HY,

ID,

IS,

IT,

JA,

KA,

KK,

KO,

LA,

LG,

LT,

LV,

MI,

MK,

MN,

MR,

MS,

NB,

NL,

NN,

PA,

PL,

PT,

RO,

RU,

SK,

SL,

SN,

SO,

SQ,

SR,

ST,

SV,

SW,

TA,

TE,

TH,

TL,

TN,

TR,

TS,

UK,

UR,

VI,

XH,

YO,

ZH,

ZU

settings.min_words

integer

default: 7

Minimum number of words to check, as the language detection can be unreliable for very short texts. Inputs shorter than the minimum will be skipped.

settings.threshold

number

default: 0.25

Minimum confidence threshold for the language detection. If the confidence is lower than this, the evaluation will be skipped.

env

object | null

Optional environment variables to override the server ones

env.{key}

string

Response

200 - application/json

status

enum<string>

default: processed

Available options:

processed

score

number

required

How many languages were detected

passed

boolean | null

required

Passes if the detected language on the output matches the detected language on the input, or if the output matches the expected language

details

string | null

Short human-readable description of the result

cost

object | null

cost.currency

string

required

cost.amount

number

required

raw_response

object

required

raw_response.output

object

required

raw_response.output.{key}

number

raw_response.input

object | null

raw_response.input.{key}

number

Evaluate on CI/CD Pipeline OpenAI Moderation

github linkedin