Class: Vapi::GhlToolWithToolCall

Inherits:
Object
  • Object
show all
Defined in:
lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb

Constant Summary collapse

OMIT = 
Object.new

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(tool_call:, metadata:, async: OMIT, messages: OMIT, function: OMIT, server: OMIT, additional_properties: nil) ⇒ Vapi::GhlToolWithToolCall

Parameters:

  • async (Boolean) (defaults to: OMIT) —

    This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (‘false`).

  • messages (Array<Vapi::GhlToolWithToolCallMessagesItem>) (defaults to: OMIT) —

    These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like ‘tool.destinations`. For others like the function tool, these can be custom configured.

  • tool_call (Vapi::ToolCall)
  • metadata (Vapi::GhlToolMetadata)
  • function (Vapi::OpenAiFunction) (defaults to: OMIT) —

    This is the function definition of the tool. For ‘endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that’s spoken for ‘endCall` tool. You can specify a function where it returns an argument “reason”. Then, in `messages` array, you can have many “request-complete” messages. One of these messages will be triggered if the `messages[].conditions` matches the “reason” argument.

  • server (Vapi::Server) (defaults to: OMIT) —

    This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl.

  • additional_properties (OpenStruct) (defaults to: nil) —

    Additional properties unmapped to the current class definition



83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 83

def initialize(tool_call:, metadata:, async: OMIT, messages: OMIT, function: OMIT, server: OMIT,
               additional_properties: nil)
  @async = async if async != OMIT
  @messages = messages if messages != OMIT
  @tool_call = tool_call
  @metadata = metadata
  @function = function if function != OMIT
  @server = server if server != OMIT
  @additional_properties = additional_properties
  @_field_set = {
    "async": async,
    "messages": messages,
    "toolCall": tool_call,
    "metadata": metadata,
    "function": function,
    "server": server
  }.reject do |_k, v|
    v == OMIT
  end
end

Instance Attribute Details

#additional_properties ⇒ OpenStruct (readonly)

Returns Additional properties unmapped to the current class definition.

Returns:

  • (OpenStruct) —

    Additional properties unmapped to the current class definition



47
48
49
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 47

def additional_properties
  @additional_properties
end

#async ⇒ Boolean (readonly)

Returns This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (‘false`).

Returns:

  • (Boolean) —

    This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (‘false`).



19
20
21
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 19

def async
  @async
end

#function ⇒ Vapi::OpenAiFunction (readonly)

Returns This is the function definition of the tool. For ‘endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that’s spoken for ‘endCall` tool. You can specify a function where it returns an argument “reason”. Then, in `messages` array, you can have many “request-complete” messages. One of these messages will be triggered if the `messages[].conditions` matches the “reason” argument.

Returns:

  • (Vapi::OpenAiFunction) —

    This is the function definition of the tool. For ‘endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that’s spoken for ‘endCall` tool. You can specify a function where it returns an argument “reason”. Then, in `messages` array, you can have many “request-complete” messages. One of these messages will be triggered if the `messages[].conditions` matches the “reason” argument.



38
39
40
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 38

def function
  @function
end

#messages ⇒ Array<Vapi::GhlToolWithToolCallMessagesItem> (readonly)

Returns These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like ‘tool.destinations`. For others like the function tool, these can be custom configured.

Returns:

  • (Array<Vapi::GhlToolWithToolCallMessagesItem>) —

    These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like ‘tool.destinations`. For others like the function tool, these can be custom configured.



24
25
26
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 24

def messages
  @messages
end

#metadata ⇒ Vapi::GhlToolMetadata (readonly)

Returns:



28
29
30
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 28

def metadata
  @metadata
end

#server ⇒ Vapi::Server (readonly)

Returns This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl.

Returns:

  • (Vapi::Server) —

    This is the server that will be hit when this tool is requested by the model. All requests will be sent with the call object among other things. You can find more details in the Server URL documentation. This overrides the serverUrl set on the org and the phoneNumber. Order of precedence: highest tool.server.url, then assistant.serverUrl, then phoneNumber.serverUrl, then org.serverUrl.



45
46
47
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 45

def server
  @server
end

#tool_call ⇒ Vapi::ToolCall (readonly)

Returns:



26
27
28
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 26

def tool_call
  @tool_call
end

Class Method Details

.from_json(json_object:) ⇒ Vapi::GhlToolWithToolCall

Deserialize a JSON object to an instance of GhlToolWithToolCall

Parameters:

  • json_object (String)

Returns:



108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 108

def self.from_json(json_object:)
  struct = JSON.parse(json_object, object_class: OpenStruct)
  parsed_json = JSON.parse(json_object)
  async = parsed_json["async"]
  messages = parsed_json["messages"]&.map do |item|
    item = item.to_json
    Vapi::GhlToolWithToolCallMessagesItem.from_json(json_object: item)
  end
  if parsed_json["toolCall"].nil?
    tool_call = nil
  else
    tool_call = parsed_json["toolCall"].to_json
    tool_call = Vapi::ToolCall.from_json(json_object: tool_call)
  end
  if parsed_json["metadata"].nil?
    metadata = nil
  else
    metadata = parsed_json["metadata"].to_json
    metadata = Vapi::GhlToolMetadata.from_json(json_object: metadata)
  end
  if parsed_json["function"].nil?
    function = nil
  else
    function = parsed_json["function"].to_json
    function = Vapi::OpenAiFunction.from_json(json_object: function)
  end
  if parsed_json["server"].nil?
    server = nil
  else
    server = parsed_json["server"].to_json
    server = Vapi::Server.from_json(json_object: server)
  end
  new(
    async: async,
    messages: messages,
    tool_call: tool_call,
    metadata: metadata,
    function: function,
    server: server,
    additional_properties: struct
  )
end

.validate_raw(obj:) ⇒ Void

Leveraged for Union-type generation, validate_raw attempts to parse the given

hash and check each fields type against the current object's property
definitions.

Parameters:

  • obj (Object)

Returns:

  • (Void) 


164
165
166
167
168
169
170
171
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 164

def self.validate_raw(obj:)
  obj.async&.is_a?(Boolean) != false || raise("Passed value for field obj.async is not the expected type, validation failed.")
  obj.messages&.is_a?(Array) != false || raise("Passed value for field obj.messages is not the expected type, validation failed.")
  Vapi::ToolCall.validate_raw(obj: obj.tool_call)
  Vapi::GhlToolMetadata.validate_raw(obj: obj.metadata)
  obj.function.nil? || Vapi::OpenAiFunction.validate_raw(obj: obj.function)
  obj.server.nil? || Vapi::Server.validate_raw(obj: obj.server)
end

Instance Method Details

#to_json(*_args) ⇒ String

Serialize an instance of GhlToolWithToolCall to a JSON object

Returns:

  • (String) 


154
155
156
 
# File 'lib/vapi_server_sdk/types/ghl_tool_with_tool_call.rb', line 154

def to_json(*_args)
  @_field_set&.to_json
end