CSV Agent seems not to be compatible with utf8

[flefevre]

Bug Description

When uploading a basic CVS file in a flow with a CSV agent, the execution raises an exception due to UTF-8 encoding

Error building Component CSVAgent: 'utf-8' codec can't decode byte 0xe9 in position 7: invalid continuation byte

`
Error building Component CSVAgent:

'utf-8' codec can't decode byte 0xe9 in position 7: invalid continuation byte

Traceback (most recent call last):
File "/app/.venv/lib/python3.12/site-packages/langflow/graph/vertex/base.py", line 709, in _build_results
result = await initialize.loading.get_instance_results(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langflow/interface/initialize/loading.py", line 68, in get_instance_results
return await build_component(params=custom_params, custom_component=custom_component)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langflow/interface/initialize/loading.py", line 145, in build_component
build_results, artifacts = await custom_component.build_results()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langflow/custom/custom_component/component.py", line 837, in build_results
return await self._build_with_tracing()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langflow/custom/custom_component/component.py", line 819, in _build_with_tracing
_results, _artifacts = await self._build_results()
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langflow/custom/custom_component/component.py", line 885, in _build_results
result = await asyncio.to_thread(method)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/asyncio/threads.py", line 25, in to_thread
return await loop.run_in_executor(None, func_call)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 65, in build_agent_response
File "/app/.venv/lib/python3.12/site-packages/langchain_experimental/agents/agent_toolkits/csv/base.py", line 57, in create_csv_agent
df = pd.read_csv(path, **_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/pandas/io/parsers/readers.py", line 1026, in read_csv
return _read(filepath_or_buffer, kwds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/pandas/io/parsers/readers.py", line 620, in _read
parser = TextFileReader(filepath_or_buffer, **kwds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/pandas/io/parsers/readers.py", line 1620, in init
self._engine = self._make_engine(f, self.engine)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/pandas/io/parsers/readers.py", line 1898, in _make_engine
return mapping[engine](f, **self.options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/pandas/io/parsers/c_parser_wrapper.py", line 93, in init
self._reader = parsers.TextReader(src, **kwds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "parsers.pyx", line 574, in pandas._libs.parsers.TextReader.cinit
File "parsers.pyx", line 663, in pandas._libs.parsers.TextReader._get_header
File "parsers.pyx", line 874, in pandas._libs.parsers.TextReader._tokenize_rows
File "parsers.pyx", line 891, in pandas._libs.parsers.TextReader._check_tokenize_status
File "parsers.pyx", line 2053, in pandas._libs.parsers.raise_parser_error
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 7: invalid continuation byte

`

Reproduction

Create a basic flow
Add a CSV agent
Add a language llm such as mistral small
Add a csv file generated from excel

Expected behavior

A basic CVS agent should be able to take of a basic csv file

Who can help?

No response

Operating System

Ubuntu 22.04

Langflow Version

1.1.1

Python Version

None

Screenshot

No response

Flow File

CSVAgent.json

[dosubot]

The error you're encountering is due to the CSV file not being encoded in UTF-8, which is the default encoding used by the CSVAgent in Langflow. To resolve this issue, you can specify the correct encoding of your CSV file using the pandas_kwargs parameter when initializing the CSVAgent. This allows you to pass additional keyword arguments to the pandas.read_csv function, including the encoding argument.

Here's how you can specify a different encoding:

CSVAgent.from_toolkit_and_llm(
    path="your_file.csv",
    llm=your_llm_instance,
    pandas_kwargs={"encoding": "latin1"}  # or another appropriate encoding
)

Replace "your_file.csv" with the path to your CSV file, your_llm_instance with your language model instance, and "latin1" with the correct encoding for your file. Common encodings include "utf-8", "latin1", "iso-8859-1", etc. ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[flefevre]

The pandas_kwargs is not accessible from the user interface.
it will be usefull if this was the case.
Dear Langflow team, could you expose the pandas_kwargs as parameter in the CVS agent?

[Cristhianzl]

hi @flefevre how are you?

Thanks for your suggestion.
You can follow up this improvement on this PR: #5372

This field will be available on Controls panel of the Component.