| Agent | Agent Class for LLM Interactions |
| AgentAction | AgentAction S3 Class |
| cache_llm_call | Cache LLM API Calls |
| call_llm | Call LLM API |
| call_llm_broadcast | Mode 2: Message Broadcast - Fixed Config, Multiple Messages |
| call_llm_compare | Mode 3: Model Comparison - Multiple Configs, Fixed Message |
| call_llm_par | Mode 4: Parallel Processing - List of Config-Message Pairs |
| call_llm_robust | Robustly Call LLM API (Simple Retry) |
| call_llm_sweep | Mode 1: Parameter Sweep - Vary One Parameter, Fixed Message |
| get_batched_embeddings | Generate Embeddings in Batches |
| LLMConversation | LLMConversation Class for Coordinating Agents |
| llm_config | Create LLM Configuration |
| log_llm_error | Log LLMR Errors |
| parse_embeddings | Parse Embedding Response into a Numeric Matrix |
| reset_llm_parallel | Reset Parallel Environment |
| setup_llm_parallel | Setup Parallel Environment for LLM Processing |