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_edenai.py

@@ -14,7 +14,7 @@ from langchain_community.llms import EdenAI
 def test_edenai_call() -> None:
     """Test simple call to edenai."""
     llm = EdenAI(provider="openai", temperature=0.2, max_tokens=250)
-    output = llm("Say foo:")
+    output = llm.invoke("Say foo:")
 
     assert llm._llm_type == "edenai"
     assert llm.feature == "text"
@@ -38,7 +38,7 @@ def test_edenai_call_with_old_params() -> None:
     to pass optional parameters to api
     """
     llm = EdenAI(provider="openai", params={"temperature": 0.2, "max_tokens": 250})
-    output = llm("Say foo:")
+    output = llm.invoke("Say foo:")
 
     assert llm._llm_type == "edenai"
     assert llm.feature == "text"