friendli api chat-completions create
Usage
friendli api chat-completions create [OPTIONS]
Summary
Creates chat completions.
Options
| Option | Type | Summary | Default | Required |
|---|---|---|---|---|
--message, -g | TEXT | A message in ROLE CONTENT format. Repeat this option to add multiple messages. | - | ✅ |
--model, -m | TEXT | The model to use for chat completions. See https://docs.friendli.ai/guides/serverless_endpoints/pricing for more about available models and pricing. | None | ❌ |
--endpoint-id, -e | TEXT | Dedicated endpoint ID to send request. | None | ❌ |
--n, -n | INTEGER RANGE | The number of results to generate. | None | ❌ |
--max-tokens, -M | INTEGER RANGE | The maximum number of tokens to generate. | None | ❌ |
--stop, -S | TEXT | When one of the stop phrases appears in the generation result, the API will stop generation. The stop phrases are excluded from the result. Repeat this option to use multiple stop phrases. | None | ❌ |
--temperature, -T | FLOAT RANGE | Sampling temperature. non-zero positive numbers are allowed. | None | ❌ |
--top-p, -P | FLOAT RANGE | Tokens comprising the top top_p probability mass are kept for sampling. | None | ❌ |
--frequency-penalty, -fp | FLOAT RANGE | Positive values penalizes tokens that have been sampled, taking into account their frequency in the preceding text. This penalization diminishes the model's tendency to reproduce identical lines verbatim. | None | ❌ |
--presence-penalty, -pp | FLOAT RANGE | Positive values penalizes tokens that have been sampled at least once in the existing text. | None | ❌ |
--stream, -s | BOOLEAN | Whether to stream generation result. | False | ❌ |
--token, -t | TEXT | Personal access token for auth. | None | ❌ |
--team-id | TEXT | ID of team to run as. | None | ❌ |