A simple endpoint to check if the Prediction Guard API is healthy.

Check API Health

Generate chat completions based on a conversation history.

example

Retrieve text completions based on the provided input.

Check the factuality of a given text compared to a reference.

Translate text from one language to another.

Replace personal information such as names, SSNs, and emails in a given text.

Detect potential prompt injection attacks in a given prompt.

The role of the sender (user or assistant).

Timestamp of when the chat completion was created.

The chat model used for generating completions.

Timestamp of when the factuality check was created.

The factuality score for a specific statement.

The index of the statement in the provided text.

The status of the factuality check for a specific statement.

Timestamp of when the PII check was created.

The text with replaced personal information.

Timestamp of when the injection check was created.

The probability of a potential injection attack.

Timestamp of when the toxicity check was created.

The toxicity score for the provided text.

The status of the toxicity check for the provided text.

Timestamp of when the completion was created.

The model used for generating the completion.

$	curl https://api.predictionguard.com \
>	-H "x-api-key: <apiKey>"