Class: LlmConductor::Clients::GroqClient

Inherits:
BaseClient
  • Object
show all
Defined in:
lib/llm_conductor/clients/groq_client.rb

Overview

Groq client implementation for accessing Groq models via Groq API.

The groq gem defaults to a 1024-token output cap and a 5s request timeout (Groq::Configuration::DEFAULT_MAX_TOKENS / DEFAULT_REQUEST_TIMEOUT), which silently truncate longer structured outputs mid-response. We raise both to sane defaults and honor per-call params (e.g. max_tokens, temperature).

Constant Summary collapse

DEFAULT_MAX_TOKENS = 
8192
DEFAULT_REQUEST_TIMEOUT = 
120

Constants included from Concerns::Retryable

Concerns::Retryable::JITTER_RATIO, Concerns::Retryable::MAX_BACKOFF_SECONDS, Concerns::Retryable::MAX_RETRY_AFTER_SECONDS, Concerns::Retryable::RETRYABLE_STATUSES, Concerns::Retryable::TRANSPORT_ERRORS

Instance Attribute Summary

Attributes inherited from BaseClient

#model, #params, #type

Method Summary

Methods inherited from BaseClient

#generate, #generate_simple, #initialize

Methods included from Concerns::Retryable

sleep_for

Methods included from Prompts

#prompt_analyze_content, #prompt_classify_content, #prompt_custom, #prompt_extract_links, #prompt_summarize_text

Constructor Details

This class inherits a constructor from LlmConductor::Clients::BaseClient