mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-03-08 18:29:32 +00:00
e0bf6adb5b
This PR adds tool support to available LLMs. We'll buffer tool invocations and return them instead of making users of this service parse the response. It also adds support for conversation context in the generic prompt. It includes bot messages, user messages, and tool invocations, which we'll trim to make sure it doesn't exceed the prompt limit, then translate them to the correct dialect. Finally, It adds some buffering when reading chunks to handle cases when streaming is extremely slow.:M
81 lines
2.3 KiB
Ruby
81 lines
2.3 KiB
Ruby
# frozen_String_literal: true
|
|
|
|
require_relative "endpoint_examples"
|
|
|
|
RSpec.describe DiscourseAi::Completions::Endpoints::Anthropic do
|
|
subject(:model) { described_class.new(model_name, DiscourseAi::Tokenizer::AnthropicTokenizer) }
|
|
|
|
let(:model_name) { "claude-2" }
|
|
let(:generic_prompt) { { insts: "write 3 words" } }
|
|
let(:dialect) { DiscourseAi::Completions::Dialects::Claude.new(generic_prompt, model_name) }
|
|
let(:prompt) { dialect.translate }
|
|
|
|
let(:request_body) { model.default_options.merge(prompt: prompt).to_json }
|
|
let(:stream_request_body) { model.default_options.merge(prompt: prompt, stream: true).to_json }
|
|
|
|
def response(content)
|
|
{
|
|
completion: content,
|
|
stop: "\n\nHuman:",
|
|
stop_reason: "stop_sequence",
|
|
truncated: false,
|
|
log_id: "12dcc7feafbee4a394e0de9dffde3ac5",
|
|
model: model_name,
|
|
exception: nil,
|
|
}
|
|
end
|
|
|
|
def stub_response(prompt, response_text, tool_call: false)
|
|
WebMock
|
|
.stub_request(:post, "https://api.anthropic.com/v1/complete")
|
|
.with(body: request_body)
|
|
.to_return(status: 200, body: JSON.dump(response(response_text)))
|
|
end
|
|
|
|
def stream_line(delta, finish_reason: nil)
|
|
+"data: " << {
|
|
completion: delta,
|
|
stop: finish_reason ? "\n\nHuman:" : nil,
|
|
stop_reason: finish_reason,
|
|
truncated: false,
|
|
log_id: "12b029451c6d18094d868bc04ce83f63",
|
|
model: "claude-2",
|
|
exception: nil,
|
|
}.to_json
|
|
end
|
|
|
|
def stub_streamed_response(prompt, deltas, tool_call: false)
|
|
chunks =
|
|
deltas.each_with_index.map do |_, index|
|
|
if index == (deltas.length - 1)
|
|
stream_line(deltas[index], finish_reason: "stop_sequence")
|
|
else
|
|
stream_line(deltas[index])
|
|
end
|
|
end
|
|
|
|
chunks = chunks.join("\n\n").split("")
|
|
|
|
WebMock
|
|
.stub_request(:post, "https://api.anthropic.com/v1/complete")
|
|
.with(body: stream_request_body)
|
|
.to_return(status: 200, body: chunks)
|
|
end
|
|
|
|
let(:tool_deltas) { ["<function", <<~REPLY] }
|
|
_calls>
|
|
<invoke>
|
|
<tool_name>get_weather</tool_name>
|
|
<parameters>
|
|
<location>Sydney</location>
|
|
<unit>c</unit>
|
|
</parameters>
|
|
</invoke>
|
|
</function_calls>
|
|
REPLY
|
|
|
|
let(:tool_call) { invocation }
|
|
|
|
it_behaves_like "an endpoint that can communicate with a completion service"
|
|
end
|