llama-stack-mirror/llama_stack/providers/utils/inference
Ashwin Bharambe 05e73d12b3 introduce openai_compat with the completions (not chat-completions) API
This keeps the prompt encoding layer in our control (see
`chat_completion_request_to_prompt()` method)
2024-10-08 17:23:42 -07:00
..
__init__.py Use inference APIs for executing Llama Guard (#121) 2024-09-28 15:40:06 -07:00
augment_messages.py introduce openai_compat with the completions (not chat-completions) API 2024-10-08 17:23:42 -07:00
model_registry.py Introduce model_store, shield_store, memory_bank_store 2024-10-08 17:23:02 -07:00
openai_compat.py introduce openai_compat with the completions (not chat-completions) API 2024-10-08 17:23:42 -07:00