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/tests/integration_tests/llms/test_openllm.py

@@ -4,7 +4,7 @@ from langchain_community.llms.openllm import OpenLLM
 
 def test_openllm_llm_local() -> None:
     llm = OpenLLM(model_name="flan-t5", model_id="google/flan-t5-small")
-    output = llm("Say foo:")
+    output = llm.invoke("Say foo:")
     assert isinstance(output, str)
 
 
@@ -12,5 +12,5 @@ def test_openllm_with_kwargs() -> None:
     llm = OpenLLM(
         model_name="flan-t5", model_id="google/flan-t5-small", temperature=0.84
     )
-    output = llm("Say bar:")
+    output = llm.invoke("Say bar:")
     assert isinstance(output, str)