Class: LLM::LlamaCpp

Inherits:
OpenAI show all
Defined in:
lib/llm/providers/llamacpp.rb

Overview

The LlamaCpp class implements a provider for llama.cpp through the OpenAI-compatible API provided by the llama-server binary.

Constant Summary

Constants inherited from OpenAI

OpenAI::HOST

Instance Method Summary collapse

Methods inherited from OpenAI

#assistant_role, #complete, #embed, #models

Methods inherited from Provider

#assistant_role, #chat, #chat!, #complete, #embed, #inspect, #models, #respond, #respond!, #schema, #with

Constructor Details

#initialize(host: "localhost", port: 8080, ssl: false) ⇒ LLM::LlamaCpp

Parameters:

  • key (String, nil) —

    The secret key for authentication

  • host (String) (defaults to: "localhost") —

    The host address of the LLM provider

  • port (Integer) (defaults to: 8080) —

    The port number

  • timeout (Integer) —

    The number of seconds to wait for a response

  • ssl (Boolean) (defaults to: false) —

    Whether to use SSL for the connection



15
16
17
 
# File 'lib/llm/providers/llamacpp.rb', line 15

def initialize(host: "localhost", port: 8080, ssl: false, **)
  super
end

Instance Method Details

#audio ⇒ Object

Raises:

  • (NotImplementedError) 


33
34
35
 
# File 'lib/llm/providers/llamacpp.rb', line 33

def audio
  raise NotImplementedError
end

#files ⇒ Object

Raises:

  • (NotImplementedError) 


21
22
23
 
# File 'lib/llm/providers/llamacpp.rb', line 21

def files
  raise NotImplementedError
end

#images ⇒ Object

Raises:

  • (NotImplementedError) 


27
28
29
 
# File 'lib/llm/providers/llamacpp.rb', line 27

def images
  raise NotImplementedError
end

#moderations ⇒ Object

Raises:

  • (NotImplementedError) 


39
40
41
 
# File 'lib/llm/providers/llamacpp.rb', line 39

def moderations
  raise NotImplementedError
end

#responses ⇒ Object

Raises:

  • (NotImplementedError) 


45
46
47
 
# File 'lib/llm/providers/llamacpp.rb', line 45

def responses
  raise NotImplementedError
end

#default_model ⇒ String

Returns the default model for chat completions

Returns:

  • (String)

See Also:



53
54
55
 
# File 'lib/llm/providers/llamacpp.rb', line 53

def default_model
  "qwen3"
end