Method: Langchain::LLM::Ollama#complete

Defined in:
lib/langchain/llm/ollama.rb

#complete(prompt:, model: defaults[:completion_model], images: nil, format: nil, system: nil, template: nil, context: nil, raw: nil, mirostat: nil, mirostat_eta: nil, mirostat_tau: nil, num_ctx: nil, num_gqa: nil, num_gpu: nil, num_thread: nil, repeat_last_n: nil, repeat_penalty: nil, temperature: defaults[:temperature], seed: nil, stop: nil, tfs_z: nil, num_predict: nil, top_k: nil, top_p: nil, stop_sequences: nil, &block) ⇒ Langchain::LLM::OllamaResponse

Generate the completion for a given prompt

Example:

final_resp = ollama.complete(prompt:) { |resp| print resp.completion }
final_resp.total_tokens

Parameters:

Returns:

[View source]

81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
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
150
151
152
153
154
155
156
 
# File 'lib/langchain/llm/ollama.rb', line 81

def complete(
  prompt:,
  model: defaults[:completion_model],
  images: nil,
  format: nil,
  system: nil,
  template: nil,
  context: nil,
  raw: nil,
  mirostat: nil,
  mirostat_eta: nil,
  mirostat_tau: nil,
  num_ctx: nil,
  num_gqa: nil,
  num_gpu: nil,
  num_thread: nil,
  repeat_last_n: nil,
  repeat_penalty: nil,
  temperature: defaults[:temperature],
  seed: nil,
  stop: nil,
  tfs_z: nil,
  num_predict: nil,
  top_k: nil,
  top_p: nil,
  stop_sequences: nil,
  &block
)
  if stop_sequences
    stop = stop_sequences
  end

  parameters = {
    prompt: prompt,
    model: model,
    images: images,
    format: format,
    system: system,
    template: template,
    context: context,
    stream: block_given?, # rubocop:disable Performance/BlockGivenWithExplicitBlock
    raw: raw
  }.compact

  llm_parameters = {
    mirostat: mirostat,
    mirostat_eta: mirostat_eta,
    mirostat_tau: mirostat_tau,
    num_ctx: num_ctx,
    num_gqa: num_gqa,
    num_gpu: num_gpu,
    num_thread: num_thread,
    repeat_last_n: repeat_last_n,
    repeat_penalty: repeat_penalty,
    temperature: temperature,
    seed: seed,
    stop: stop,
    tfs_z: tfs_z,
    num_predict: num_predict,
    top_k: top_k,
    top_p: top_p
  }

  parameters[:options] = llm_parameters.compact
  responses_stream = []

  client.post("api/generate", parameters) do |req|
    req.options.on_data = json_responses_chunk_handler do |parsed_chunk|
      responses_stream << parsed_chunk

      block&.call(OllamaResponse.new(parsed_chunk, model: parameters[:model]))
    end
  end

  generate_final_completion_response(responses_stream, parameters[:model])
end