fix: langchain integration input/output format

[desaxce]

Changes:

• added process_content to get content according to language
• applied it to input / output / variables

To test:

• run the cookbook https://github.com/Chainlit/cookbook/tree/main/langchain-ask-human
  Use the version from this PR because it fixes an LC import.

Had to remove process content on output because of error:

2024-07-04 10:01:24 - An output parsing error occurred. In order to pass this error back to the agent and have it try again, pass `handle_parsing_errors=True` to the AgentExecutor. This is the error: Could not parse LLM output: Question: I need to order pizza for a hackathon. How many should I order?
Thought: To determine how many pizzas to order, I need to know the number of people attending the hackathon and the average number of pizza slices each person is expected to eat. Additionally, I need to know how many slices are in each pizza.
Action:

{
"action": human,
"action_input": How many people are attending the hackathon, how many slices does each person typically eat, and how many slices are in each pizza?
}

Traceback (most recent call last):
  File "/Users/desaxce/miniconda3/envs/chainlit/lib/python3.12/site-packages/langchain/agents/chat/output_parser.py", line 35, in parse
    response = json.loads(action.strip())
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/desaxce/miniconda3/envs/chainlit/lib/python3.12/json/__init__.py", line 346, in loads
    return _default_decoder.decode(s)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/desaxce/miniconda3/envs/chainlit/lib/python3.12/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/desaxce/miniconda3/envs/chainlit/lib/python3.12/json/decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 2 column 13 (char 14)