Class: Telnyx::Models::AI::InferenceEmbedding

Inherits:

Internal::Type::BaseModel

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

Defined in:

lib/telnyx/models/ai/inference_embedding.rb,
sig/telnyx/models/ai/inference_embedding.rbs

Overview

See Also:

• Telnyx::Resources::AI::Assistants#create

Defined Under Namespace

Classes: ConversationFlow

Instance Attribute Summary

• #conversation_flow ⇒ Telnyx::Models::AI::InferenceEmbedding::ConversationFlow^?

  Conversation flow as returned by the API.

• #created_at ⇒ Time
• #description ⇒ String^?
• #dynamic_variables ⇒ Hash{Symbol=>Object}^?

  Map of dynamic variables and their values.

• #dynamic_variables_webhook_timeout_ms ⇒ Integer^?

  Timeout in milliseconds for the dynamic variables webhook.

• #dynamic_variables_webhook_url ⇒ String^?

  If dynamic_variables_webhook_url is set, Telnyx sends a POST request to this URL at the start of the conversation to resolve dynamic variables.

• #enabled_features ⇒ Array<Symbol, Telnyx::Models::AI::EnabledFeatures>^?
• #external_llm ⇒ Telnyx::Models::AI::ExternalLlm^?
• #fallback_config ⇒ Telnyx::Models::AI::FallbackConfig^?
• #greeting ⇒ String^?

  Text that the assistant will use to start the conversation.

• #id ⇒ String
• #import_metadata ⇒ Telnyx::Models::AI::ImportMetadata^?
• #insight_settings ⇒ Telnyx::Models::AI::InsightSettings^?
• #instructions ⇒ String

  System instructions for the assistant.

• #integrations ⇒ Array<Telnyx::Models::AI::AssistantIntegration>^?

  Connected integrations attached to the assistant.

• #interruption_settings ⇒ Telnyx::Models::AI::InferenceEmbeddingInterruptionSettings^?

  Settings for interruptions and how the assistant decides the user has finished speaking.

• #llm_api_key_ref ⇒ String^?

  This is only needed when using third-party inference providers selected by model.

• #mcp_servers ⇒ Array<Telnyx::Models::AI::AssistantMcpServer>^?

  MCP servers attached to the assistant.

• #messaging_settings ⇒ Telnyx::Models::AI::MessagingSettings^?
• #model ⇒ String

  ID of the model to use when external_llm is not set.

• #name ⇒ String
• #observability_settings ⇒ Telnyx::Models::AI::Observability^?
• #post_conversation_settings ⇒ Telnyx::Models::AI::PostConversationSettings^?

  Configuration for post-conversation processing.

• #privacy_settings ⇒ Telnyx::Models::AI::PrivacySettings^?
• #related_mission_ids ⇒ Array<String>^?

  IDs of missions related to this assistant.

• #tags ⇒ Array<String>^?

  Tags associated with the assistant.

• #telephony_settings ⇒ Telnyx::Models::AI::TelephonySettings^?
• #tools ⇒ Array<Telnyx::Models::AI::InferenceEmbeddingWebhookToolParams, Telnyx::Models::AI::RetrievalTool, Telnyx::Models::AI::AssistantTool::Handoff, Telnyx::Models::AI::HangupTool, Telnyx::Models::AI::AssistantTool::Transfer, Telnyx::Models::AI::AssistantTool::Invite, Telnyx::Models::AI::AssistantTool::Refer, Telnyx::Models::AI::AssistantTool::SendDtmf, Telnyx::Models::AI::AssistantTool::SendMessage, Telnyx::Models::AI::AssistantTool::SkipTurn>^?

  Deprecated for new integrations.

• #transcription ⇒ Telnyx::Models::AI::TranscriptionSettings^?
• #version_created_at ⇒ Time^?

  Timestamp when this assistant version was created.

• #version_id ⇒ String^?

  Identifier for the assistant version returned by version-aware assistant endpoints.

• #version_name ⇒ String^?

  Human-readable name for the assistant version.

• #voice_settings ⇒ Telnyx::Models::AI::VoiceSettings^?
• #widget_settings ⇒ Telnyx::Models::AI::WidgetSettings^?

  Configuration settings for the assistant's web widget.

Instance Method Summary

• #initialize(id:, created_at:, instructions:, model:, name:, conversation_flow: nil, description: nil, dynamic_variables: nil, dynamic_variables_webhook_timeout_ms: nil, dynamic_variables_webhook_url: nil, enabled_features: nil, external_llm: nil, fallback_config: nil, greeting: nil, import_metadata: nil, insight_settings: nil, integrations: nil, interruption_settings: nil, llm_api_key_ref: nil, mcp_servers: nil, messaging_settings: nil, observability_settings: nil, post_conversation_settings: nil, privacy_settings: nil, related_mission_ids: nil, tags: nil, telephony_settings: nil, tools: nil, transcription: nil, version_created_at: nil, version_id: nil, version_name: nil, voice_settings: nil, widget_settings: nil) ⇒ Object constructor

  Some parameter documentations has been truncated, see InferenceEmbedding for more details.

• #to_hash ⇒ {

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, 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

#initialize(id:, created_at:, instructions:, model:, name:, conversation_flow: nil, description: nil, dynamic_variables: nil, dynamic_variables_webhook_timeout_ms: nil, dynamic_variables_webhook_url: nil, enabled_features: nil, external_llm: nil, fallback_config: nil, greeting: nil, import_metadata: nil, insight_settings: nil, integrations: nil, interruption_settings: nil, llm_api_key_ref: nil, mcp_servers: nil, messaging_settings: nil, observability_settings: nil, post_conversation_settings: nil, privacy_settings: nil, related_mission_ids: nil, tags: nil, telephony_settings: nil, tools: nil, transcription: nil, version_created_at: nil, version_id: nil, version_name: nil, voice_settings: nil, widget_settings: nil) ⇒ Object

Some parameter documentations has been truncated, see Telnyx::Models::AI::InferenceEmbedding for more details.

Parameters:

• id (String)
• created_at (Time)
• instructions (String) —

  System instructions for the assistant. These may be templated with [dynamic vari

• model (String) —

  ID of the model to use when external_llm is not set. You can use the [Get mode

• name (String)
• conversation_flow (Telnyx::Models::AI::InferenceEmbedding::ConversationFlow) (defaults to: nil) —

  Conversation flow as returned by the API.

• description (String) (defaults to: nil)
• dynamic_variables (Hash{Symbol=>Object}) (defaults to: nil) —

  Map of dynamic variables and their values

• dynamic_variables_webhook_timeout_ms (Integer) (defaults to: nil) —

  Timeout in milliseconds for the dynamic variables webhook. Must be between 1 and

• dynamic_variables_webhook_url (String) (defaults to: nil) —

  If dynamic_variables_webhook_url is set, Telnyx sends a POST request to this U

• enabled_features (Array<Symbol, Telnyx::Models::AI::EnabledFeatures>) (defaults to: nil)
• external_llm (Telnyx::Models::AI::ExternalLlm) (defaults to: nil)
• fallback_config (Telnyx::Models::AI::FallbackConfig) (defaults to: nil)
• greeting (String) (defaults to: nil) —

  Text that the assistant will use to start the conversation. This may be template

• import_metadata (Telnyx::Models::AI::ImportMetadata) (defaults to: nil)
• insight_settings (Telnyx::Models::AI::InsightSettings) (defaults to: nil)
• integrations (Array<Telnyx::Models::AI::AssistantIntegration>) (defaults to: nil) —

  Connected integrations attached to the assistant. The catalog of available integ

• interruption_settings (Telnyx::Models::AI::InferenceEmbeddingInterruptionSettings) (defaults to: nil) —

  Settings for interruptions and how the assistant decides the user has finished s

• llm_api_key_ref (String) (defaults to: nil) —

  This is only needed when using third-party inference providers selected by `mode

• mcp_servers (Array<Telnyx::Models::AI::AssistantMcpServer>) (defaults to: nil) —

  MCP servers attached to the assistant. Create MCP servers with /ai/mcp_servers

• messaging_settings (Telnyx::Models::AI::MessagingSettings) (defaults to: nil)
• observability_settings (Telnyx::Models::AI::Observability) (defaults to: nil)
• post_conversation_settings (Telnyx::Models::AI::PostConversationSettings) (defaults to: nil) —

  Configuration for post-conversation processing. When enabled, the assistant rece

• privacy_settings (Telnyx::Models::AI::PrivacySettings) (defaults to: nil)
• related_mission_ids (Array<String>) (defaults to: nil) —

  IDs of missions related to this assistant.

• tags (Array<String>) (defaults to: nil) —

  Tags associated with the assistant. Tags can also be managed with the assistant

• telephony_settings (Telnyx::Models::AI::TelephonySettings) (defaults to: nil)
• tools (Array<Telnyx::Models::AI::InferenceEmbeddingWebhookToolParams, Telnyx::Models::AI::RetrievalTool, Telnyx::Models::AI::AssistantTool::Handoff, Telnyx::Models::AI::HangupTool, Telnyx::Models::AI::AssistantTool::Transfer, Telnyx::Models::AI::AssistantTool::Invite, Telnyx::Models::AI::AssistantTool::Refer, Telnyx::Models::AI::AssistantTool::SendDtmf, Telnyx::Models::AI::AssistantTool::SendMessage, Telnyx::Models::AI::AssistantTool::SkipTurn>) (defaults to: nil) —

  Deprecated for new integrations. Inline tool definitions available to the assist

• transcription (Telnyx::Models::AI::TranscriptionSettings) (defaults to: nil)
• version_created_at (Time) (defaults to: nil) —

  Timestamp when this assistant version was created.

• version_id (String) (defaults to: nil) —

  Identifier for the assistant version returned by version-aware assistant endpoin

• version_name (String) (defaults to: nil) —

  Human-readable name for the assistant version.

• voice_settings (Telnyx::Models::AI::VoiceSettings) (defaults to: nil)
• widget_settings (Telnyx::Models::AI::WidgetSettings) (defaults to: nil) —

  Configuration settings for the assistant's web widget.

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 240

Instance Attribute Details

#conversation_flow ⇒ Telnyx::Models::AI::InferenceEmbedding::ConversationFlow^?

Conversation flow as returned by the API.

Returns:

• (Telnyx::Models::AI::InferenceEmbedding::ConversationFlow, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 44

optional :conversation_flow, -> { Telnyx::AI::InferenceEmbedding::ConversationFlow }

#created_at ⇒ Time

Parameters:

• value (Time)

Returns:

• (Time)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 16

required :created_at, Time

#description ⇒ String^?

Parameters:

• (String)

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 49

optional :description, String

#dynamic_variables ⇒ Hash{Symbol=>Object}^?

Map of dynamic variables and their values

Parameters:

• (::Hash[Symbol, top])

Returns:

• (Hash{Symbol=>Object}, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 55

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

#dynamic_variables_webhook_timeout_ms ⇒ Integer^?

Timeout in milliseconds for the dynamic variables webhook. Must be between 1 and 10000 ms. If the webhook does not respond within this timeout, the call proceeds with default values. See the dynamic variables guide.

Parameters:

• (Integer)

Returns:

• (Integer, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 64

optional :dynamic_variables_webhook_timeout_ms, Integer

#dynamic_variables_webhook_url ⇒ String^?

If dynamic_variables_webhook_url is set, Telnyx sends a POST request to this URL at the start of the conversation to resolve dynamic variables. Gotcha: the webhook response must wrap variables under a top-level dynamic_variables object, e.g. {"dynamic_variables": {"customer_name": "Jane"}}. Returning a flat object will be ignored and variables will fall back to their defaults. See the dynamic variables guide for the full request/response format and timeout behavior.

Parameters:

• (String)

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 77

optional :dynamic_variables_webhook_url, String

#enabled_features ⇒ Array<Symbol, Telnyx::Models::AI::EnabledFeatures>^?

Returns:

• (Array<Symbol, Telnyx::Models::AI::EnabledFeatures>, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 82

optional :enabled_features, -> { Telnyx::Internal::Type::ArrayOf[enum: Telnyx::AI::EnabledFeatures] }

#external_llm ⇒ Telnyx::Models::AI::ExternalLlm^?

Parameters:

• (Telnyx::AI::ExternalLlm)

Returns:

• (Telnyx::Models::AI::ExternalLlm, nil)

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

optional :external_llm, -> { Telnyx::AI::ExternalLlm }

#fallback_config ⇒ Telnyx::Models::AI::FallbackConfig^?

Returns:

• (Telnyx::Models::AI::FallbackConfig, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 92

optional :fallback_config, -> { Telnyx::AI::FallbackConfig }

#greeting ⇒ String^?

Text that the assistant will use to start the conversation. This may be templated with dynamic variables. Use an empty string to have the assistant wait for the user to speak first. Use the special value <assistant-speaks-first-with-model-generated-message> to have the assistant generate the greeting based on the system instructions.

Parameters:

• (String)

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 103

optional :greeting, String

#id ⇒ String

Parameters:

• value (String)

Returns:

• (String)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 11

required :id, String

#import_metadata ⇒ Telnyx::Models::AI::ImportMetadata^?

Returns:

• (Telnyx::Models::AI::ImportMetadata, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 108

optional :import_metadata, -> { Telnyx::AI::ImportMetadata }

#insight_settings ⇒ Telnyx::Models::AI::InsightSettings^?

Returns:

• (Telnyx::Models::AI::InsightSettings, nil)

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

optional :insight_settings, -> { Telnyx::AI::InsightSettings }

#instructions ⇒ String

System instructions for the assistant. These may be templated with dynamic variables

Parameters:

• value (String)

Returns:

• (String)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 23

required :instructions, String

#integrations ⇒ Array<Telnyx::Models::AI::AssistantIntegration>^?

Connected integrations attached to the assistant. The catalog of available integrations is at /ai/integrations; the user's connected integrations are at /ai/integrations/connections. Each item references a catalog integration by integration_id.

Returns:

• (Array<Telnyx::Models::AI::AssistantIntegration>, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 122

optional :integrations, -> { Telnyx::Internal::Type::ArrayOf[Telnyx::AI::AssistantIntegration] }

#interruption_settings ⇒ Telnyx::Models::AI::InferenceEmbeddingInterruptionSettings^?

Settings for interruptions and how the assistant decides the user has finished speaking. These timings are most relevant when using non turn-taking transcription models. For turn-taking models like deepgram/flux, end-of-turn behavior is controlled by the transcription end-of-turn settings under transcription.settings (eot_threshold, eot_timeout_ms, eager_eot_threshold).

Returns:

• (Telnyx::Models::AI::InferenceEmbeddingInterruptionSettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 133

optional :interruption_settings, -> { Telnyx::AI::InferenceEmbeddingInterruptionSettings }

#llm_api_key_ref ⇒ String^?

This is only needed when using third-party inference providers selected by model. The identifier for an integration secret /v2/integration_secrets that refers to your LLM provider's API key. For bring-your-own endpoint authentication, use external_llm.llm_api_key_ref instead. Warning: Free plans are unlikely to work with this integration.

Parameters:

• (String)

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 144

optional :llm_api_key_ref, String

#mcp_servers ⇒ Array<Telnyx::Models::AI::AssistantMcpServer>^?

MCP servers attached to the assistant. Create MCP servers with /ai/mcp_servers, then reference them by id here.

Returns:

• (Array<Telnyx::Models::AI::AssistantMcpServer>, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 151

optional :mcp_servers, -> { Telnyx::Internal::Type::ArrayOf[Telnyx::AI::AssistantMcpServer] }

#messaging_settings ⇒ Telnyx::Models::AI::MessagingSettings^?

Returns:

• (Telnyx::Models::AI::MessagingSettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 156

optional :messaging_settings, -> { Telnyx::AI::MessagingSettings }

#model ⇒ String

ID of the model to use when external_llm is not set. You can use the Get models API to see available models. If external_llm is provided, the assistant uses external_llm instead of this field. If neither model nor external_llm is provided, Telnyx applies the default model.

Parameters:

• value (String)

Returns:

• (String)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 33

required :model, String

#name ⇒ String

Parameters:

• value (String)

Returns:

• (String)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 38

required :name, String

#observability_settings ⇒ Telnyx::Models::AI::Observability^?

Returns:

• (Telnyx::Models::AI::Observability, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 161

optional :observability_settings, -> { Telnyx::AI::Observability }

#post_conversation_settings ⇒ Telnyx::Models::AI::PostConversationSettings^?

Configuration for post-conversation processing. When enabled, the assistant receives one additional LLM turn after the conversation ends, allowing it to execute tool calls such as logging to a CRM or sending a summary. The assistant can execute multiple parallel or sequential tools during this phase. Telephony-control tools (e.g. hangup, transfer) are unavailable post-conversation. Beta feature.

Returns:

• (Telnyx::Models::AI::PostConversationSettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 172

optional :post_conversation_settings, -> { Telnyx::AI::PostConversationSettings }

#privacy_settings ⇒ Telnyx::Models::AI::PrivacySettings^?

Returns:

• (Telnyx::Models::AI::PrivacySettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 177

optional :privacy_settings, -> { Telnyx::AI::PrivacySettings }

#related_mission_ids ⇒ Array<String>^?

IDs of missions related to this assistant.

Parameters:

• (::Array[String])

Returns:

• (Array<String>, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 183

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

#tags ⇒ Array<String>^?

Tags associated with the assistant. Tags can also be managed with the assistant tag endpoints.

Parameters:

• (::Array[String])

Returns:

• (Array<String>, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 190

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

#telephony_settings ⇒ Telnyx::Models::AI::TelephonySettings^?

Returns:

• (Telnyx::Models::AI::TelephonySettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 195

optional :telephony_settings, -> { Telnyx::AI::TelephonySettings }

#tools ⇒ Array<Telnyx::Models::AI::InferenceEmbeddingWebhookToolParams, Telnyx::Models::AI::RetrievalTool, Telnyx::Models::AI::AssistantTool::Handoff, Telnyx::Models::AI::HangupTool, Telnyx::Models::AI::AssistantTool::Transfer, Telnyx::Models::AI::AssistantTool::Invite, Telnyx::Models::AI::AssistantTool::Refer, Telnyx::Models::AI::AssistantTool::SendDtmf, Telnyx::Models::AI::AssistantTool::SendMessage, Telnyx::Models::AI::AssistantTool::SkipTurn>^?

Deprecated for new integrations. Inline tool definitions available to the assistant. Prefer tool_ids to attach shared tools created with the AI Tools endpoints.

Returns:

• (Array<Telnyx::Models::AI::InferenceEmbeddingWebhookToolParams, Telnyx::Models::AI::RetrievalTool, Telnyx::Models::AI::AssistantTool::Handoff, Telnyx::Models::AI::HangupTool, Telnyx::Models::AI::AssistantTool::Transfer, Telnyx::Models::AI::AssistantTool::Invite, Telnyx::Models::AI::AssistantTool::Refer, Telnyx::Models::AI::AssistantTool::SendDtmf, Telnyx::Models::AI::AssistantTool::SendMessage, Telnyx::Models::AI::AssistantTool::SkipTurn>, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 203

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

#transcription ⇒ Telnyx::Models::AI::TranscriptionSettings^?

Returns:

• (Telnyx::Models::AI::TranscriptionSettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 208

optional :transcription, -> { Telnyx::AI::TranscriptionSettings }

#version_created_at ⇒ Time^?

Timestamp when this assistant version was created.

Parameters:

• (Time)

Returns:

• (Time, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 214

optional :version_created_at, Time

#version_id ⇒ String^?

Identifier for the assistant version returned by version-aware assistant endpoints.

Parameters:

• (String)

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 221

optional :version_id, String

#version_name ⇒ String^?

Human-readable name for the assistant version.

Parameters:

• (String)

Returns:

• (String, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 227

optional :version_name, String

#voice_settings ⇒ Telnyx::Models::AI::VoiceSettings^?

Returns:

• (Telnyx::Models::AI::VoiceSettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 232

optional :voice_settings, -> { Telnyx::AI::VoiceSettings }

#widget_settings ⇒ Telnyx::Models::AI::WidgetSettings^?

Configuration settings for the assistant's web widget.

Returns:

• (Telnyx::Models::AI::WidgetSettings, nil)

# File 'lib/telnyx/models/ai/inference_embedding.rb', line 238

optional :widget_settings, -> { Telnyx::AI::WidgetSettings }

Instance Method Details

#to_hash ⇒ {

Returns:

• ({)

# File 'sig/telnyx/models/ai/inference_embedding.rbs', line 240

def to_hash: -> {