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/llms/deepsparse.py

@@ -92,7 +92,7 @@ class DeepSparse(LLM):
             .. code-block:: python
                 from langchain_community.llms import DeepSparse
                 llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
-                llm("Tell me a joke.")
+                llm.invoke("Tell me a joke.")
         """
         if self.streaming:
             combined_output = ""
@@ -130,7 +130,7 @@ class DeepSparse(LLM):
             .. code-block:: python
                 from langchain_community.llms import DeepSparse
                 llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
-                llm("Tell me a joke.")
+                llm.invoke("Tell me a joke.")
         """
         if self.streaming:
             combined_output = ""