Sha256: 675dcd5c7e93c855b9562fd5c7bd4302652c3699f41f70980fa1c97090593be8
Contents?: true
Size: 2 KB
Versions: 11
Compression:
Stored size: 2 KB
Contents
#!/usr/bin/env ruby
require 'ollama'
include Ollama
include Ollama::Utils::FileArgument
require 'tins'
include Tins::GO
require 'json'
def usage
puts <<~EOT
Usage: #{File.basename($0)} [OPTIONS]
-u URL the ollama base url, OLLAMA_URL
-m MODEL the ollama model to chat with, OLLAMA_MODEL
-M OPTIONS the ollama model options to use, OLLAMA_MODEL_OPTIONS
-s SYSTEM the system prompt to use as a file, OLLAMA_SYSTEM
-p PROMPT the user prompt to use as a file, OLLAMA_PROMPT
if it contains %{stdin} it is substituted by stdin input
-P VARIABLE sets prompt var %{foo} to "bar" if VARIABLE is foo=bar
-H HANDLER the handler to use for the response, defaults to Print
-S use streaming for generation
-h this help
EOT
exit 0
end
opts = go 'u:m:M:s:p:P:H:Sh', defaults: { ?H => 'Print', ?M => '{}' }
opts[?h] and usage
base_url = opts[?u] || ENV['OLLAMA_URL'] || 'http://%s' % ENV.fetch('OLLAMA_HOST')
model = opts[?m] || ENV.fetch('OLLAMA_MODEL', 'llama3.1')
options = Ollama::Options.from_hash(JSON(
get_file_argument(opts[?M], default: ENV['OLLAMA_MODEL_OPTIONS'])
))
system = get_file_argument(opts[?s], default: ENV['OLLAMA_SYSTEM'])
prompt = get_file_argument(opts[?p], default: ENV['OLLAMA_PROMPT'])
if prompt.nil?
prompt = STDIN.read
else
vars = prompt.scan(/%\{([^}]+)\}/).inject([], &:concat).uniq.map(&:to_sym)
stdin = (STDIN.read if vars.include?(:stdin)).to_s
values = opts[?P].to_a.inject({ stdin: }) { |h, pair|
n, v = pair.split(?=, 2)
h.merge(n.to_sym => v)
}
prompt = prompt % values
end
if ENV['DEBUG'].to_i == 1
puts <<~EOT
base_url = #{base_url.inspect}
model = #{model.inspect}
system = #{system.inspect}
prompt = #{prompt.inspect}
options = #{options.to_json}
EOT
end
Client.new(base_url:, read_timeout: 120).generate(
model:,
system:,
prompt:,
options:,
stream: !!opts[?S],
&Object.const_get(opts[?H])
)
Version data entries
11 entries across 11 versions & 1 rubygems