feat(custom_llm.py): initial working commit for writing your own custom LLM handler

Fixes https://github.com/BerriAI/litellm/issues/4675

 Also Addresses https://github.com/BerriAI/litellm/discussions/4677

litellm/llms/custom_llm.py

@@ -0,0 +1,70 @@
+# What is this?
+## Handler file for a Custom Chat LLM
+
+"""
+- completion
+- acompletion
+- streaming
+- async_streaming
+"""
+
+import copy
+import json
+import os
+import time
+import types
+from enum import Enum
+from functools import partial
+from typing import Callable, List, Literal, Optional, Tuple, Union
+
+import httpx  # type: ignore
+import requests  # type: ignore
+
+import litellm
+from litellm.litellm_core_utils.core_helpers import map_finish_reason
+from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
+from litellm.types.llms.databricks import GenericStreamingChunk
+from litellm.types.utils import ProviderField
+from litellm.utils import CustomStreamWrapper, EmbeddingResponse, ModelResponse, Usage
+
+from .base import BaseLLM
+from .prompt_templates.factory import custom_prompt, prompt_factory
+
+
+class CustomLLMError(Exception):  # use this for all your exceptions
+    def __init__(
+        self,
+        status_code,
+        message,
+    ):
+        self.status_code = status_code
+        self.message = message
+        super().__init__(
+            self.message
+        )  # Call the base class constructor with the parameters it needs
+
+
+def custom_chat_llm_router():
+    """
+    Routes call to CustomLLM completion/acompletion/streaming/astreaming functions, based on call type
+
+    Validates if response is in expected format
+    """
+    pass
+
+
+class CustomLLM(BaseLLM):
+    def __init__(self) -> None:
+        super().__init__()
+
+    def completion(self, *args, **kwargs) -> ModelResponse:
+        raise CustomLLMError(status_code=500, message="Not implemented yet!")
+
+    def streaming(self, *args, **kwargs):
+        raise CustomLLMError(status_code=500, message="Not implemented yet!")
+
+    async def acompletion(self, *args, **kwargs) -> ModelResponse:
+        raise CustomLLMError(status_code=500, message="Not implemented yet!")
+
+    async def astreaming(self, *args, **kwargs):
+        raise CustomLLMError(status_code=500, message="Not implemented yet!")