Loading CSV and Excel files in LangChain - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ component_behavior

intermediate

What does this Langchain CSV loader output?

Given the following Langchain code snippet that loads a CSV file, what will be the output type of documents?

LangChain

from langchain.document_loaders import CSVLoader
loader = CSVLoader(file_path='data/sample.csv')
documents = loader.load()

A A list of Document objects representing each row in the CSV

B A single string containing the entire CSV content

C A dictionary with keys as column names and values as lists of column data

D A pandas DataFrame object

💡 Hint

Think about what Langchain loaders usually return after loading files.

Langchain's CSVLoader returns a list of Document objects, each representing a row or chunk of the CSV file, not raw strings or dataframes.

📝 Syntax

intermediate

Identify the syntax error in this Excel loader code

Which option contains a syntax error when trying to load an Excel file using Langchain's ExcelLoader?

LangChain

from langchain.document_loaders import ExcelLoader
loader = ExcelLoader(file_path='data/sample.xlsx')
documents = loader.load()

A loader = ExcelLoader(file='data/sample.xlsx')

B loader = ExcelLoader('data/sample.xlsx')

C loader = ExcelLoader(file_path='data/sample.xlsx', sheet_name='Sheet1')

D loader = ExcelLoader(file_path='data/sample.xlsx')

💡 Hint

Check the parameter names expected by ExcelLoader constructor.

ExcelLoader expects the parameter file_path, not file. Option A uses an invalid parameter name causing a TypeError.

❓ state_output

advanced

What is the number of documents loaded from a multi-sheet Excel file?

Consider this code loading an Excel file with 3 sheets, each having 5 rows. What is the length of documents after loading all sheets?

LangChain

from langchain.document_loaders import ExcelLoader
loader = ExcelLoader(file_path='data/multi_sheet.xlsx', sheet_name=None)
documents = loader.load()

A 5

B 3

C 1

D 15

💡 Hint

When sheet_name=None, all sheets are loaded and combined.

Setting sheet_name=None loads all sheets. Each sheet has 5 rows, so total documents = 3 sheets * 5 rows = 15.

🔧 Debug

advanced

Why does this CSVLoader code raise a FileNotFoundError?

This code raises a FileNotFoundError. What is the most likely cause?

LangChain

from langchain.document_loaders import CSVLoader
loader = CSVLoader(file_path='data/missing.csv')
documents = loader.load()

A The CSV file is empty, causing the loader to fail

B CSVLoader requires an absolute file path, relative paths cause errors

C The file path 'data/missing.csv' does not exist in the project directory

D The CSVLoader class is deprecated and cannot load files

💡 Hint

Check if the file path is correct and the file exists.

FileNotFoundError means the file path given does not point to an existing file. Relative paths are allowed and empty files do not cause this error.

🧠 Conceptual

expert

Which option best describes how Langchain handles Excel sheets when loading?

When using Langchain's ExcelLoader with sheet_name=None, how does it process the Excel file?

A It loads sheets one by one but requires manual calls for each sheet

B It loads all sheets and returns a combined list of Document objects for every row in all sheets

C It loads all sheets but returns a dictionary with sheet names as keys and Document lists as values

D It loads only the first sheet and ignores the rest

💡 Hint

Think about how Langchain simplifies multi-sheet Excel loading.

Langchain's ExcelLoader with sheet_name=None loads all sheets and merges their rows into a single list of Document objects.