Wire up Llamafile

Author: peteski22

litellm/__init__.py

@@ -72,7 +72,6 @@
 from litellm.litellm_core_utils.logging_callback_manager import LoggingCallbackManager
 import httpx
 import dotenv
-from enum import Enum
 
 litellm_mode = os.getenv("LITELLM_MODE", "DEV")  # "PRODUCTION", "DEV"
 if litellm_mode == "DEV":
@@ -1012,6 +1011,7 @@ def add_known_models():
 from .llms.azure.chat.gpt_transformation import AzureOpenAIConfig
 from .llms.azure.completion.transformation import AzureOpenAITextConfig
 from .llms.hosted_vllm.chat.transformation import HostedVLLMChatConfig
+from .llms.llamafile.chat.transformation import LlamafileChatConfig
 from .llms.litellm_proxy.chat.transformation import LiteLLMProxyChatConfig
 from .llms.vllm.completion.transformation import VLLMConfig
 from .llms.deepseek.chat.transformation import DeepSeekChatConfig

litellm/litellm_core_utils/get_llm_provider_logic.py

@@ -101,7 +101,6 @@ def get_llm_provider(  # noqa: PLR0915
 
     Return model, custom_llm_provider, dynamic_api_key, api_base
     """
-
     try:
         ## IF LITELLM PARAMS GIVEN ##
         if litellm_params is not None:
@@ -477,6 +476,12 @@ def _get_openai_compatible_provider_info(  # noqa: PLR0915
         ) = litellm.HostedVLLMChatConfig()._get_openai_compatible_provider_info(
             api_base, api_key
         )
+    elif custom_llm_provider == "llamafile":
+        # llamafile is OpenAI compatible.
+        (api_base, dynamic_api_key) = litellm.LlamafileChatConfig()._get_openai_compatible_provider_info(
+                api_base,
+                api_key
+            )
     elif custom_llm_provider == "lm_studio":
         # lm_studio is openai compatible, we just need to set this to custom_openai
         (

litellm/main.py

@@ -3578,6 +3578,7 @@ def embedding(  # noqa: PLR0915
             custom_llm_provider == "openai_like"
             or custom_llm_provider == "jina_ai"
             or custom_llm_provider == "hosted_vllm"
+            or custom_llm_provider == "llamafile"
             or custom_llm_provider == "lm_studio"
         ):
             api_base = (

litellm/utils.py

@@ -6455,6 +6455,8 @@ def get_provider_chat_config(  # noqa: PLR0915
             return litellm.AiohttpOpenAIChatConfig()
         elif litellm.LlmProviders.HOSTED_VLLM == provider:
             return litellm.HostedVLLMChatConfig()
+        elif litellm.LlmProviders.LLAMAFILE == provider:
+            return litellm.LlamafileChatConfig()
         elif litellm.LlmProviders.LM_STUDIO == provider:
             return litellm.LMStudioChatConfig()
         elif litellm.LlmProviders.GALADRIEL == provider: