/v1/completion/regex
This endpoint provides LLM completions that match specified regex patterns. It is an enhanced way of generating completions based on regular expression constraints.
Request: POST /v1/completion/regex
Headers
Content-Type: application/jsonAuthorization: Bearer <your_api_key>
Body
The request accepts a JSON body with the following properties:
| Field | Type | Description | Required |
|---|---|---|---|
prompt | string | The prompt to generate from. | Yes |
pattern | string or string[] | A single regex pattern to match. | Yes |
max_new_tokens | integer | The maximum number of tokens to generate. Defaults to 5. | No |
stop_after_match | boolean | Whether to stop generating after a match is found. Defaults to True. | No |
top_k | integer | The number of highest probability vocabulary tokens to keep for top-k-filtering. Defaults to 50. | No |
top_p | float | If set to float < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation. Defaults to 1.0. | No |
temperature | float | The value used to modulate the next token probabilities. Defaults to 1.0. | No |
repetition_penalty | float | The parameter for repetition penalty. 1.0 means no penalty. See this paper (opens in a new tab) for more details. Defaults to 1.0. | No |
Example
{
"prompt": "This is a sample prompt",
"pattern": ".*prompt$",
"max_new_tokens": 10,
"stop_after_match": false,
"top_k": 50,
"top_p": 0.9,
"temperature": 0.8,
"repetition_penalty": 1.2
}Response
The response from the server includes the completion data which matches the given patterns.
If there was a problem with the request, you will receive an error message instead.
Fields
| Field | Type | Description |
|---|---|---|
completion | string | The generated text that matches the pattern. |
tokens_generated | integer | Number of tokens generated in the response. |
stop_reason | string | The reason the generation was stopped, if applicable. Either pattern_match or token_limit. |
Example
{
"completion": "sample response matching prompt",
"tokens_generated": 5,
"stop_reason": "pattern_match"
}Error Handling
In case of a bad request or authentication error, you will receive an HTTP status code other than 200, and a descriptive error message.
{
"error": "Invalid API Key provided.",
"code": 401
}