Add Invocation Params (#4509)

### Add Invocation Params to Logged Run


Adds an llm type to each chat model as well as an override of the dict()
method to log the invocation parameters for each call

---------

Co-authored-by: Ankush Gola <ankush.gola@gmail.com>

tests/unit_tests/llms/fake_chat_model.py

@@ -1,5 +1,5 @@
 """Fake Chat Model wrapper for testing purposes."""
-from typing import List, Optional
+from typing import Any, List, Mapping, Optional
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForLLMRun,
@@ -30,3 +30,11 @@ class FakeChatModel(SimpleChatModel):
         message = AIMessage(content=output_str)
         generation = ChatGeneration(message=message)
         return ChatResult(generations=[generation])
+
+    @property
+    def _llm_type(self) -> str:
+        return "fake-chat-model"
+
+    @property
+    def _identifying_params(self) -> Mapping[str, Any]:
+        return {"key": "fake"}