Rodrigo Rodriguez (Pragmatismo)
f299dc4dbf
Added support for selecting an LLM model based on configuration and processing the raw response. The execute_llm_generation function now: 1. Fetches the configured model using ConfigManager 2. Gets the appropriate handler for the model 3. Processes the raw response through the handler before returning This provides more flexibility in model selection and allows for model-specific response handling. |
||
|---|---|---|
| .. | ||
| compiler | ||
| keywords | ||
| mod.rs | ||