feat(proxy_server.py): support custom llm handler on proxy

docs/my-website/docs/providers/custom_llm_server.md

@@ -35,6 +35,101 @@ resp = completion(
 assert resp.choices[0].message.content == "Hi!"
 ```
 
+## OpenAI Proxy Usage
+
+1. Setup your `custom_handler.py` file 
+
+```python
+import litellm
+from litellm import CustomLLM, completion, get_llm_provider
+
+
+class MyCustomLLM(CustomLLM):
+    def completion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+    async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+
+my_custom_llm = MyCustomLLM()
+```
+
+2. Add to `config.yaml` 
+
+In the config below, we pass
+
+python_filename: `custom_handler.py`
+custom_handler_instance_name: `my_custom_llm`. This is defined in Step 1
+
+custom_handler: `custom_handler.my_custom_llm`
+
+```yaml
+model_list:
+  - model_name: "test-model"             
+    litellm_params:
+      model: "openai/text-embedding-ada-002"
+  - model_name: "my-custom-model"
+    litellm_params:
+      model: "my-custom-llm/my-model"
+
+litellm_settings:
+  custom_provider_map:
+  - {"provider": "my-custom-llm", "custom_handler": custom_handler.my_custom_llm}
+```
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+```bash
+curl -X POST 'http://0.0.0.0:4000/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-d '{
+    "model": "my-custom-model",
+    "messages": [{"role": "user", "content": "Say \"this is a test\" in JSON!"}],
+}'
+```
+
+Expected Response
+
+```
+{
+    "id": "chatcmpl-06f1b9cd-08bc-43f7-9814-a69173921216",
+    "choices": [
+        {
+            "finish_reason": "stop",
+            "index": 0,
+            "message": {
+                "content": "Hi!",
+                "role": "assistant",
+                "tool_calls": null,
+                "function_call": null
+            }
+        }
+    ],
+    "created": 1721955063,
+    "model": "gpt-3.5-turbo",
+    "object": "chat.completion",
+    "system_fingerprint": null,
+    "usage": {
+        "prompt_tokens": 10,
+        "completion_tokens": 20,
+        "total_tokens": 30
+    }
+}
+```
 
 ## Custom Handler Spec
 
@@ -70,4 +165,4 @@ class CustomLLM(BaseLLM):
 
     async def astreaming(self, *args, **kwargs) -> AsyncIterator[GenericStreamingChunk]:
         raise CustomLLMError(status_code=500, message="Not implemented yet!")
-```
+```

litellm/proxy/_new_secret_config.yaml

@@ -1,4 +1,11 @@
 model_list:
   - model_name: "test-model"             
     litellm_params:
-      model: "openai/text-embedding-ada-002"
+      model: "openai/text-embedding-ada-002"
+  - model_name: "my-custom-model"
+    litellm_params:
+      model: "my-custom-llm/my-model"
+
+litellm_settings:
+  custom_provider_map:
+  - {"provider": "my-custom-llm", "custom_handler": custom_handler.my_custom_llm}

litellm/proxy/custom_handler.py

@@ -0,0 +1,21 @@
+import litellm
+from litellm import CustomLLM, completion, get_llm_provider
+
+
+class MyCustomLLM(CustomLLM):
+    def completion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+    async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+
+my_custom_llm = MyCustomLLM()

litellm/proxy/proxy_server.py

@@ -1507,6 +1507,21 @@ class ProxyConfig:
                     verbose_proxy_logger.debug(
                         f"litellm.post_call_rules: {litellm.post_call_rules}"
                     )
+                elif key == "custom_provider_map":
+                    from litellm.utils import custom_llm_setup
+
+                    litellm.custom_provider_map = [
+                        {
+                            "provider": item["provider"],
+                            "custom_handler": get_instance_fn(
+                                value=item["custom_handler"],
+                                config_file_path=config_file_path,
+                            ),
+                        }
+                        for item in value
+                    ]
+
+                    custom_llm_setup()
                 elif key == "success_callback":
                     litellm.success_callback = []