Generate

This endpoint generates realistic text conditioned on a given input.

Usage

cURL

curl --location --request POST 'https://api.cohere.ai/baseline-shark/generate' \
  --header 'Authorization: BEARER {api_key}' \
  --header 'Content-Type: application/json' \
  --data-raw '{
      "prompt": "Once upon a time in a magical land called",
      "max_tokens": 50,
      "temperature": 1,
      "k": 0,
      "p": 0.75
    }'

Python

import cohere
co = cohere.CohereClient('API_KEY')
prediction = co.generate(
  model='baseline-shark',
  prompt='Once upon a time in a magical land called',
  max_tokens=50,
  temperature=1,
  k=0,
  p=0.75)
print('Prediction: {}'.format(prediction.text))

Node.js

const cohere = require('cohere-ai');
cohere.init('API_KEY');
(async () => {
  const response = await cohere.generate('baseline-shark', {
    prompt: 'Once upon a time in a magical land called',
    max_tokens: 50,
    temperature: 1,
    k: 0,
    p: 0.75
  });
  console.log(`Prediction: ${response.body.text}`);
})();

CLI

co: model generate baseline-shark 'Once upon a time in a magical land called' --max-tokens=50 --temperature=1 --k=0 --p=0.75

Sample Response

{
  "text": " Brumana, lived the country folk. Among them was Zhulan Noyan, an adventurer and immortal, one who possesses an innate power of changing forms and abilities, just like a person. His goal was to hunt down"
}

Request

prompt

string

Represents the prompt or text to be completed.

max_tokens

integer

Denotes the number of tokens to predict per generation. See BPE Tokens for more details.

temperature

float

A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations. See Temperature for more details.

k (optional)

integer

Defaults to 0 (disabled). If set to a positive integer, it ensures only the top k most likely tokens are considered for generation at each step.

p (optional)

float

Defaults to 0.75. Set to 1.0 to disable. If set to a probability 0.0 < p < 1.0, it ensures that only the most likely tokens, with total probability mass of p, are considered for generation at each step. If both k and p are enabled, p acts after k.

frequency_penalty (optional)

float

Defaults to 0.0, max value of 1.0. Can be used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.

presence_penalty (optional)

float

Defaults to 0.0, max value of 1.0. Can be used to reduce repetitiveness of generated tokens. Similar to frequency_penalty, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.

stop_sequences (optional)

array of string

A stop sequence will cut off your generation at the end of the sequence. Providing multiple stop sequences in the array will cut the generation at the first stop sequence in the generation, if applicable.

return_likelihoods (optional)

One of GENERATION|ALL|NONE to specify how and if the token likelihoods are returns with the response. Defaults to NONE.

If GENERATION is selected, the token likelihoods will only be provided for generated text

If ALL is selected, the token likelihoods will be provided both for the prompt and the generated text.

Response

text

array of strings

Contains the generated text.

token_likelihoods

array of objects

Only returned if return_likelihoods is not set to NONE.

An array of objects with the following shape:

{

"token": string,

"likelihood": float

}

The likelihood refers to the log-likelihood of the token. The first token of a context will not have a likelihood.