Class: Boxcars::Groq
- Includes:
- UnifiedObservability
- Defined in:
- lib/boxcars/engine/groq.rb
Overview
A engine that uses Groq’s API.
Constant Summary collapse
- DEFAULT_PARAMS =
{ model: "llama3-70b-8192", temperature: 0.1, max_tokens: 4096 # Groq API might have specific limits or naming for this }.freeze
- DEFAULT_NAME =
Groq API might have specific limits or naming for this
"Groq engine"- DEFAULT_DESCRIPTION =
"useful for when you need to use Groq AI to answer questions. " \ "You should ask targeted questions"
Instance Attribute Summary collapse
-
#batch_size ⇒ Object
readonly
Returns the value of attribute batch_size.
-
#groq_params ⇒ Object
readonly
Returns the value of attribute groq_params.
-
#model_kwargs ⇒ Object
readonly
Returns the value of attribute model_kwargs.
-
#prompts ⇒ Object
readonly
Returns the value of attribute prompts.
Attributes inherited from Engine
Class Method Summary collapse
-
.groq_client(groq_api_key: nil) ⇒ Object
Renamed from open_ai_client to groq_client for clarity.
Instance Method Summary collapse
- #client(prompt:, inputs: {}, groq_api_key: nil, **kwargs) ⇒ Object
-
#conversation_model?(_model_name) ⇒ Boolean
Groq models are typically conversational.
-
#initialize(name: DEFAULT_NAME, description: DEFAULT_DESCRIPTION, prompts: [], batch_size: 20, **kwargs) ⇒ Groq
constructor
A new instance of Groq.
- #run(question) ⇒ Object
Methods inherited from Engine
#extract_answer, #generate, #generation_info, #get_num_tokens
Constructor Details
#initialize(name: DEFAULT_NAME, description: DEFAULT_DESCRIPTION, prompts: [], batch_size: 20, **kwargs) ⇒ Groq
Returns a new instance of Groq.
22 23 24 25 26 27 28 |
# File 'lib/boxcars/engine/groq.rb', line 22 def initialize(name: DEFAULT_NAME, description: DEFAULT_DESCRIPTION, prompts: [], batch_size: 20, **kwargs) user_id = kwargs.delete(:user_id) @groq_params = DEFAULT_PARAMS.merge(kwargs) # Corrected typo here @prompts = prompts @batch_size = batch_size super(description:, name:, user_id:) end |
Instance Attribute Details
#batch_size ⇒ Object (readonly)
Returns the value of attribute batch_size.
11 12 13 |
# File 'lib/boxcars/engine/groq.rb', line 11 def batch_size @batch_size end |
#groq_params ⇒ Object (readonly)
Returns the value of attribute groq_params.
11 12 13 |
# File 'lib/boxcars/engine/groq.rb', line 11 def groq_params @groq_params end |
#model_kwargs ⇒ Object (readonly)
Returns the value of attribute model_kwargs.
11 12 13 |
# File 'lib/boxcars/engine/groq.rb', line 11 def model_kwargs @model_kwargs end |
#prompts ⇒ Object (readonly)
Returns the value of attribute prompts.
11 12 13 |
# File 'lib/boxcars/engine/groq.rb', line 11 def prompts @prompts end |
Class Method Details
.groq_client(groq_api_key: nil) ⇒ Object
Renamed from open_ai_client to groq_client for clarity
31 32 33 34 35 |
# File 'lib/boxcars/engine/groq.rb', line 31 def self.groq_client(groq_api_key: nil) access_token = Boxcars.configuration.groq_api_key(groq_api_key:) ::OpenAI::Client.new(access_token:, uri_base: "https://api.groq.com/openai/v1") # Adjusted uri_base to include /v1 as is common for OpenAI-compatible APIs end |
Instance Method Details
#client(prompt:, inputs: {}, groq_api_key: nil, **kwargs) ⇒ Object
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
# File 'lib/boxcars/engine/groq.rb', line 42 def client(prompt:, inputs: {}, groq_api_key: nil, **kwargs) start_time = Time.now response_data = { response_obj: nil, parsed_json: nil, success: false, error: nil, status_code: nil } current_params = @groq_params.merge(kwargs) current_prompt_object = prompt.is_a?(Array) ? prompt.first : prompt api_request_params = nil # Initialize begin clnt = Groq.groq_client(groq_api_key:) api_request_params = _prepare_groq_request_params(current_prompt_object, inputs, current_params) (api_request_params[:messages]) if Boxcars.configuration.log_prompts && api_request_params[:messages] _execute_and_process_groq_call(clnt, api_request_params, response_data) rescue ::OpenAI::Error => e _handle_openai_error_for_groq(e, response_data) rescue StandardError => e _handle_standard_error_for_groq(e, response_data) ensure duration_ms = ((Time.now - start_time) * 1000).round request_context = { prompt: current_prompt_object, inputs:, conversation_for_api: api_request_params&.dig(:messages), user_id: } track_ai_generation( duration_ms:, current_params:, request_context:, response_data:, provider: :groq ) end # If there's an error, raise it to maintain backward compatibility with existing tests raise response_data[:error] if response_data[:error] response_data[:parsed_json] end |
#conversation_model?(_model_name) ⇒ Boolean
Groq models are typically conversational.
38 39 40 |
# File 'lib/boxcars/engine/groq.rb', line 38 def conversation_model?(_model_name) true end |
#run(question) ⇒ Object
83 84 85 86 87 88 89 |
# File 'lib/boxcars/engine/groq.rb', line 83 def run(question, **) prompt = Prompt.new(template: question) response = client(prompt:, inputs: {}, **) answer = extract_answer(response) Boxcars.debug("Answer: #{answer}", :cyan) answer end |