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_replicate.py

@@ -11,7 +11,7 @@ TEST_MODEL = "replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899
 def test_replicate_call() -> None:
     """Test simple non-streaming call to Replicate."""
     llm = Replicate(model=TEST_MODEL)
-    output = llm("What is LangChain")
+    output = llm.invoke("What is LangChain")
     assert output
     assert isinstance(output, str)
 
@@ -22,7 +22,7 @@ def test_replicate_streaming_call() -> None:
     callback_manager = CallbackManager([callback_handler])
 
     llm = Replicate(streaming=True, callback_manager=callback_manager, model=TEST_MODEL)
-    output = llm("What is LangChain")
+    output = llm.invoke("What is LangChain")
     assert output
     assert isinstance(output, str)
 
@@ -32,11 +32,11 @@ def test_replicate_model_kwargs() -> None:
     llm = Replicate(
         model=TEST_MODEL, model_kwargs={"max_length": 100, "temperature": 0.01}
     )
-    long_output = llm("What is LangChain")
+    long_output = llm.invoke("What is LangChain")
     llm = Replicate(
         model=TEST_MODEL, model_kwargs={"max_length": 10, "temperature": 0.01}
     )
-    short_output = llm("What is LangChain")
+    short_output = llm.invoke("What is LangChain")
     assert len(short_output) < len(long_output)
     assert llm.model_kwargs == {"max_length": 10, "temperature": 0.01}