patch: remove usage of llm, chat model __call__ (#20788)

- `llm(prompt)` -> `llm.invoke(prompt)`
- `llm(prompt=prompt` -> `llm.invoke(prompt)` (same with `messages=`)
- `llm(prompt, callbacks=callbacks)` -> `llm.invoke(prompt,
config={"callbacks": callbacks})`
- `llm(prompt, **kwargs)` -> `llm.invoke(prompt, **kwargs)`

libs/community/langchain_community/callbacks/context_callback.py

@@ -58,7 +58,7 @@ class ContextCallbackHandler(BaseCallbackHandler):
         ...     SystemMessage(content="You translate English to French."),
         ...     HumanMessage(content="I love programming with LangChain."),
         ... ]
-        >>> chat(messages)
+        >>> chat.invoke(messages)
 
     Chain Example:
         >>> from langchain.chains import LLMChain