Class: Telnyx::Models::AI::ChatCreateCompletionParams

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• Telnyx::Models::AI::ChatCreateCompletionParams

Extended by:

Internal::Type::RequestParameters::Converter

Includes:

Internal::Type::RequestParameters

Defined in:

lib/telnyx/models/ai/chat_create_completion_params.rb

Overview

See Also:

• Resources::AI::Chat#create_completion

Defined Under Namespace

Modules: Tool, ToolChoice Classes: Message, ResponseFormat

Instance Attribute Summary

• #api_key_ref ⇒ String^?

  If you are using an external inference provider like xAI or OpenAI, this field allows you to pass along a reference to your API key.

• #best_of ⇒ Integer^?

  This is used with ‘use_beam_search` to determine how many candidate beams to explore.

• #early_stopping ⇒ Boolean^?

  This is used with ‘use_beam_search`.

• #enable_thinking ⇒ Boolean^?

  Whether to enable the thinking/reasoning phase for models that support it (e.g., QwQ, Qwen3).

• #frequency_penalty ⇒ Float^?

  Higher values will penalize the model from repeating the same output tokens.

• #guided_choice ⇒ Array<String>^?

  If specified, the output will be exactly one of the choices.

• #guided_json ⇒ Hash{Symbol=>Object}^?

  Must be a valid JSON schema.

• #guided_regex ⇒ String^?

  If specified, the output will follow the regex pattern.

• #length_penalty ⇒ Float^?

  This is used with ‘use_beam_search` to prefer shorter or longer completions.

• #logprobs ⇒ Boolean^?

  Whether to return log probabilities of the output tokens or not.

• #max_tokens ⇒ Integer^?

  Maximum number of completion tokens the model should generate.

• #messages ⇒ Array<Telnyx::Models::AI::ChatCreateCompletionParams::Message>

  A list of the previous chat messages for context.

• #min_p ⇒ Float^?

  This is an alternative to ‘top_p` that [many prefer](github.com/huggingface/transformers/issues/27670).

• #model ⇒ String^?

  The language model to chat with.

• #n ⇒ Float^?

  This will return multiple choices for you instead of a single chat completion.

• #presence_penalty ⇒ Float^?

  Higher values will penalize the model from repeating the same output tokens.

• #response_format ⇒ Telnyx::Models::AI::ChatCreateCompletionParams::ResponseFormat^?

  Use this is you want to guarantee a JSON output without defining a schema.

• #stream ⇒ Boolean^?

  Whether or not to stream data-only server-sent events as they become available.

• #temperature ⇒ Float^?

  Adjusts the “creativity” of the model.

• #tool_choice ⇒ Symbol, ...
• #tools ⇒ Array<Telnyx::Models::AI::ChatCreateCompletionParams::Tool::Function, Telnyx::Models::AI::ChatCreateCompletionParams::Tool::Retrieval>^?

  The ‘function` tool type follows the same schema as the [OpenAI Chat Completions API](platform.openai.com/docs/api-reference/chat).

• #top_logprobs ⇒ Integer^?

  This is used with ‘logprobs`.

• #top_p ⇒ Float^?

  An alternative or complement to ‘temperature`.

• #use_beam_search ⇒ Boolean^?

  Setting this to ‘true` will allow the model to [explore more completion options](huggingface.co/blog/how-to-generate#beam-search).

Attributes included from Internal::Type::RequestParameters

#request_options

Class Method Summary

• .values ⇒ Array<Symbol>

Methods included from Internal::Type::RequestParameters::Converter

dump_request

Methods included from Internal::Type::RequestParameters

included

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, #initialize, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

This class inherits a constructor from Telnyx::Internal::Type::BaseModel

Instance Attribute Details

#api_key_ref ⇒ String^?

If you are using an external inference provider like xAI or OpenAI, this field allows you to pass along a reference to your API key. After creating an [integration secret](developers.telnyx.com/api-reference/integration-secrets/create-a-secret) for you API key, pass the secret’s ‘identifier` in this field.

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 25

optional :api_key_ref, String

#best_of ⇒ Integer^?

This is used with ‘use_beam_search` to determine how many candidate beams to explore.

Returns:

• (Integer, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 32

optional :best_of, Integer

#early_stopping ⇒ 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.

Returns:

• (Boolean, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 40

optional :early_stopping, Telnyx::Internal::Type::Boolean

#enable_thinking ⇒ Boolean^?

Whether to enable the thinking/reasoning phase for models that support it (e.g., QwQ, Qwen3). When set to false, the model will skip the internal reasoning step and respond directly, which can reduce latency. Defaults to true.

Returns:

• (Boolean, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 48

optional :enable_thinking, Telnyx::Internal::Type::Boolean

#frequency_penalty ⇒ Float^?

Higher values will penalize the model from repeating the same output tokens.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 54

optional :frequency_penalty, Float

#guided_choice ⇒ Array<String>^?

If specified, the output will be exactly one of the choices.

Returns:

• (Array<String>, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 60

optional :guided_choice, Telnyx::Internal::Type::ArrayOf[String]

#guided_json ⇒ Hash{Symbol=>Object}^?

Must be a valid JSON schema. If specified, the output will follow the JSON schema.

Returns:

• (Hash{Symbol=>Object}, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 67

optional :guided_json, Telnyx::Internal::Type::HashOf[Telnyx::Internal::Type::Unknown]

#guided_regex ⇒ String^?

If specified, the output will follow the regex pattern.

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 73

optional :guided_regex, String

#length_penalty ⇒ Float^?

This is used with ‘use_beam_search` to prefer shorter or longer completions.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 79

optional :length_penalty, Float

#logprobs ⇒ Boolean^?

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the ‘content` of `message`.

Returns:

• (Boolean, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 87

optional :logprobs, Telnyx::Internal::Type::Boolean

#max_tokens ⇒ Integer^?

Maximum number of completion tokens the model should generate.

Returns:

• (Integer, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 93

optional :max_tokens, Integer

#messages ⇒ Array<Telnyx::Models::AI::ChatCreateCompletionParams::Message>

A list of the previous chat messages for context.

Returns:

• (Array<Telnyx::Models::AI::ChatCreateCompletionParams::Message>)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 15

required :messages,
-> { Telnyx::Internal::Type::ArrayOf[Telnyx::AI::ChatCreateCompletionParams::Message] }

#min_p ⇒ Float^?

This is an alternative to ‘top_p` that [many prefer](github.com/huggingface/transformers/issues/27670). Must be in [0, 1].

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 101

optional :min_p, Float

#model ⇒ String^?

The language model to chat with.

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 107

optional :model, String

#n ⇒ Float^?

This will return multiple choices for you instead of a single chat completion.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 113

optional :n, Float

#presence_penalty ⇒ Float^?

Higher values will penalize the model from repeating the same output tokens.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 119

optional :presence_penalty, Float

#response_format ⇒ Telnyx::Models::AI::ChatCreateCompletionParams::ResponseFormat^?

Use this is you want to guarantee a JSON output without defining a schema. For control over the schema, use ‘guided_json`.

Returns:

• (Telnyx::Models::AI::ChatCreateCompletionParams::ResponseFormat, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 126

optional :response_format, -> { Telnyx::AI::ChatCreateCompletionParams::ResponseFormat }

#stream ⇒ Boolean^?

Whether or not to stream data-only server-sent events as they become available.

Returns:

• (Boolean, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 132

optional :stream, Telnyx::Internal::Type::Boolean

#temperature ⇒ Float^?

Adjusts the “creativity” of the model. Lower values make the model more deterministic and repetitive, while higher values make the model more random and creative.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 140

optional :temperature, Float

#tool_choice ⇒ Symbol, ...

Returns:

• (Symbol, Telnyx::Models::AI::ChatCreateCompletionParams::ToolChoice, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 145

optional :tool_choice, enum: -> { Telnyx::AI::ChatCreateCompletionParams::ToolChoice }

#tools ⇒ Array<Telnyx::Models::AI::ChatCreateCompletionParams::Tool::Function, Telnyx::Models::AI::ChatCreateCompletionParams::Tool::Retrieval>^?

The ‘function` tool type follows the same schema as the [OpenAI Chat Completions API](platform.openai.com/docs/api-reference/chat). The `retrieval` tool type is unique to Telnyx. You may pass a list of [embedded storage buckets](developers.telnyx.com/api-reference/embeddings/embed-documents) for retrieval-augmented generation.

Returns:

• (Array<Telnyx::Models::AI::ChatCreateCompletionParams::Tool::Function, Telnyx::Models::AI::ChatCreateCompletionParams::Tool::Retrieval>, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 155

optional :tools,
-> { Telnyx::Internal::Type::ArrayOf[union: Telnyx::AI::ChatCreateCompletionParams::Tool] }

#top_logprobs ⇒ Integer^?

This is used with ‘logprobs`. An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.

Returns:

• (Integer, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 164

optional :top_logprobs, Integer

#top_p ⇒ Float^?

An alternative or complement to ‘temperature`. This adjusts how many of the top possibilities to consider.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 171

optional :top_p, Float

#use_beam_search ⇒ Boolean^?

Setting this to ‘true` will allow the model to [explore more completion options](huggingface.co/blog/how-to-generate#beam-search). This is not supported by OpenAI.

Returns:

• (Boolean, nil)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 179

optional :use_beam_search, Telnyx::Internal::Type::Boolean

Class Method Details

.values ⇒ Array<Symbol>

Returns:

• (Array<Symbol>)

# File 'lib/telnyx/models/ai/chat_create_completion_params.rb', line 311