Custom document loaders in LangChain - Step-by-Step Execution

Concept Flow - Custom document loaders

Define Custom Loader Class

↓

Implement load() Method

↓

Instantiate Loader Object

↓

Call load() to Read Documents

↓

Return List of Document Objects

↓

Use Documents in LangChain Pipeline

The flow shows creating a custom loader class with a load method, then using it to read and return documents for LangChain.

Execution Sample

LangChain

from langchain.schema import Document

class MyLoader:
    def __init__(self, path):
        self.path = path
    def load(self):
        with open(self.path, 'r') as f:
            text = f.read()
        return [Document(page_content=text)]

This code defines a custom loader that reads a file and returns its content wrapped in a Document object.

Execution Table

Step	Action	Evaluation	Result
1	Create MyLoader instance with path 'file.txt'	path='file.txt'	MyLoader object created with path='file.txt'
2	Call load() method	Open 'file.txt' for reading	File opened successfully
3	Read file content	Read all text from file	Text content stored in variable
4	Create Document object	Wrap text in Document(page_content=text)	List with one Document returned
5	Return documents list	Return [Document]	Documents ready for LangChain use

💡 load() completes after returning list of Document objects

Variable Tracker

Variable	Start	After Step 2	After Step 3	After Step 4	Final
self.path	N/A	'file.txt'	'file.txt'	'file.txt'	'file.txt'
f (file handle)	N/A	open file.txt	open file.txt	closed	closed
text	N/A	N/A	'file content string'	'file content string'	'file content string'
documents	N/A	N/A	N/A	[Document(page_content=text)]	[Document(page_content=text)]

Key Moments - 3 Insights

Why do we return a list with Document objects instead of just the text?

LangChain expects a list of Document objects to handle metadata and text uniformly, as shown in execution_table step 4.

What happens if the file path is wrong or file can't be opened?

An error occurs at step 2 when trying to open the file; this stops load() and must be handled outside or with try-except.

Can load() return multiple documents?

Yes, load() can return a list with many Document objects if the source has multiple parts, but here it returns one as in step 4.

Visual Quiz - 3 Questions

Look at the execution table, what is the value of 'text' after step 3?

A File handle object

B 'file content string'

C List of Document objects

D None

💡 Hint

Check the 'text' variable column in variable_tracker after step 3

At which step does the load() method create the Document object?

A Step 2

B Step 3

C Step 4

D Step 5

💡 Hint

See the 'Action' and 'Result' columns in execution_table for step 4

If the file path was invalid, what would happen during execution?

A Error occurs at step 2 opening file

B load() returns empty list

C Document created with empty content

D Execution continues normally

💡 Hint

Refer to key_moments about file opening errors and execution_table step 2

Concept Snapshot

Custom document loaders in LangChain:
- Define a class with a load() method
- load() reads source data (e.g., file)
- Wrap text in Document objects
- Return a list of Documents
- Used to feed data into LangChain pipelines

Full Transcript

This visual execution trace shows how to create and use a custom document loader in LangChain. First, you define a class with an __init__ method to store the file path. Then, the load() method opens the file, reads its content, and wraps it in a Document object. The method returns a list containing this Document. The execution table traces each step from creating the loader instance, opening the file, reading text, creating the Document, and returning the list. The variable tracker shows how variables like path, file handle, text, and documents change during execution. Key moments clarify why we return Document objects, what happens if the file can't be opened, and that load() can return multiple documents. The quiz tests understanding of variable values at steps, when Document is created, and error handling. The snapshot summarizes the pattern for custom loaders in LangChain.