Class: Legion::Extensions::Llm::Ollama::Actor::OllamaCallable

Inherits:
Object
  • Object
show all
Defined in:
lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb

Overview

Callable wrapper for an Ollama provider instance. Implements the fleet dispatch ops (chat/stream_chat/embed/count_tokens) by delegating to a per-instance Ollama::Provider, plus the disconnect and normalize_dispatch_error contracts required by Inventory::CallableHandle and Routing::ProviderOutcome. Dispatch errors propagate untouched so normalize_dispatch_error can classify them.

Instance Method Summary collapse

Constructor Details

#initialize(instance_cfg:, logger:, provider: nil) ⇒ OllamaCallable

Returns a new instance of OllamaCallable.



991
992
993
994
995
996
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 991

def initialize(instance_cfg:, logger:, provider: nil)
  @instance_cfg = instance_cfg
  @logger = logger
  @provider = provider
  @disconnected = false
end

Instance Method Details

#chat(messages:, model:, **rest) ⇒ Object

Fleet and SelectionDispatch pass model as a RAW STRING (the offering's model id). Ollama's render path is string-tolerant (model.respond_to?(:id) ? model.id : model) for chat and embed, embed places the model verbatim in the Embedding response object, and count_tokens ignores it — so the model passes through UNWRAPPED on every op. Wrapping a raw string in Model::Info here would serialize a Data object into the wire payload or the response object (D15 per-op rule); Model::Info instances pass through unchanged as well.



1015
1016
1017
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 1015

def chat(messages:, model:, **rest)
  provider.chat(messages: messages, model: model, **rest)
end

#count_tokens(messages:, model:, **rest) ⇒ Object 



1027
1028
1029
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 1027

def count_tokens(messages:, model:, **rest)
  provider.count_tokens(messages: messages, model: model, **rest)
end

#disconnect ⇒ Object 



1000
1001
1002
1003
1004
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 1000

def disconnect
  @disconnected = true
  @provider&.disconnect
  @logger.debug { '[ollama][callable] disconnected' }
end

#disconnected? ⇒ Boolean

Returns:

  • (Boolean) 


998
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 998

def disconnected? = @disconnected

#embed(text:, model:, **rest) ⇒ Object 



1023
1024
1025
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 1023

def embed(text:, model:, **rest)
  provider.embed(text: text, model: model, **rest)
end

#normalize_dispatch_error(error:) ⇒ Object 



1031
1032
1033
1034
1035
1036
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 1031

def normalize_dispatch_error(error:)
  Legion::Extensions::Llm::Routing::ProviderOutcome.new(
    kind: classify_dispatch_error(error: error),
    reason: dispatch_reason(error)
  )
end

#stream_chat(messages:, model:, **rest) ⇒ Object 



1019
1020
1021
 
# File 'lib/legion/extensions/llm/ollama/actors/discovery_refresh.rb', line 1019

def stream_chat(messages:, model:, **rest, &)
  provider.stream_chat(messages: messages, model: model, **rest, &)
end