Skip to content

Latest commit

 

History

History
38 lines (26 loc) · 3.21 KB

ChatCompletionRequest.md

File metadata and controls

38 lines (26 loc) · 3.21 KB

ChatCompletionRequest

Properties

Name Type Description Notes
messages List<ChatCompletionSystemMessageParam> A list of the previous chat messages for context.
model String The language model to chat with. If you are optimizing for speed, try mistralai/Mistral-7B-Instruct-v0.1. For quality, try NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO [optional]
stream Boolean Whether or not to stream data-only server-sent events as they become available. [optional]
maxTokens Integer Maximum number of completion tokens the model should generate. [optional]
temperature BigDecimal Adjusts the &quot;creativity&quot; of the model. Lower values make the model more deterministic and repetitive, while higher values make the model more random and creative. [optional]
minP BigDecimal This is an alternative to `temperature` that many prefer. Must be in [0, 1]. [optional]
n BigDecimal This will return multiple choices for you instead of a single chat completion. [optional]
tools List<ChatCompletionRequestToolsInner> The `retrieval` tool type is unique to Telnyx. You may pass a list of embedded storage buckets for retrieval-augmented generation. [optional]
toolChoice ToolChoiceEnum [optional]
useBeamSearch Boolean Setting this to `true` will allow the model to explore more completion options. This is not supported by OpenAI. [optional]
bestOf Integer This is used with `use_beam_search` to determine how many candidate beams to explore. [optional]
lengthPenalty BigDecimal This is used with `use_beam_search` to prefer shorter or longer completions. [optional]
earlyStopping Boolean This is used with `use_beam_search`. If `true`, generation stops as soon as there are `best_of` complete candidates; if `false`, a heuristic is applied and the generation stops when is it very unlikely to find better candidates. [optional]
frequencyPenalty BigDecimal Higher values will penalize the model from repeating the same output tokens. [optional]
presencePenalty BigDecimal Higher values will penalize the model from repeating the same output tokens. [optional]
topP BigDecimal An alternative to `temperature`. [optional]
openaiApiKey String If you are using OpenAI models using our API, this is how you pass along your OpenAI API key. [optional]

Enum: ToolChoiceEnum

Name Value
NONE "none"
AUTO "auto"