Skip to content

Commit 70871c1

Browse files
ayanokojix21ayanokojix21
committed
docs: add Google Classroom document loader integration
1 parent e1d10e0 commit 70871c1

2 files changed

Lines changed: 277 additions & 0 deletions

File tree

‎src/oss/python/integrations/document_loaders/google_classroom.mdx‎

Lines changed: 275 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,275 @@
1+
---
2+
title: "Google Classroom integration"
3+
description: "Integrate with the Google Classroom document loader using LangChain Python."
4+
---
5+
6+
> [Google Classroom](https://edu.google.com/workspace-for-education/classroom/) is a free learning management system developed by Google as part of Google Workspace for Education. It helps educators manage coursework, assignments, and communication.
7+
8+
This page covers how to load data from Google Classroom using the `GoogleClassroomLoader`. The loader fetches courses, assignments (courseWork), announcements, course materials, student submissions, rubrics, topics, and class rosters from the [Classroom API](https://developers.google.com/classroom) and converts each item into a LangChain `Document`.
9+
10+
When file attachments are present on classroom items, the loader automatically downloads and parses them from Google Drive—supporting PDF, DOCX, CSV, plain text, Google Docs, Sheets, Slides, and images.
11+
12+
Learn more about the package on [GitHub](https://github.com/ayanokojix21/langchain-google-classroom).
13+
14+
## Overview
15+
16+
| Class | Package | Serializable |
17+
|:------|:--------|:-------------|
18+
| `GoogleClassroomLoader` | [`langchain-google-classroom`](https://pypi.org/project/langchain-google-classroom/) | ✅ |
19+
20+
### Integration details
21+
22+
| Source | Document Lazy Loading | Async Support |
23+
|:-------|:---------------------:|:-------------:|
24+
| `GoogleClassroomLoader` | ✅ | ✅ |
25+
26+
## Prerequisites
27+
28+
To use this loader, you will need:
29+
30+
1. A [Google Cloud project](https://developers.google.com/workspace/guides/create-project)
31+
2. The [Classroom API](https://console.cloud.google.com/apis/library/classroom.googleapis.com) enabled
32+
3. The [Drive API](https://console.cloud.google.com/apis/library/drive.googleapis.com) enabled (for file attachments)
33+
4. One of the following authentication methods:
34+
- **OAuth 2.0 credentials**—for personal Google accounts or testing
35+
- **Service Account credentials**—for Google Workspace domains (production)
36+
37+
## Installation
38+
39+
Install the integration package:
40+
41+
```bash
42+
pip install -qU langchain-google-classroom
43+
```
44+
45+
To enable parsing of PDF and DOCX attachments, install with the optional `parsers` extra:
46+
47+
```bash
48+
pip install -qU "langchain-google-classroom[parsers]"
49+
```
50+
51+
## Credentials
52+
53+
### Option A: OAuth 2.0 (personal accounts)
54+
55+
1. In the [Google Cloud Console](https://console.cloud.google.com/apis/credentials), create an **OAuth 2.0 Client ID** (Desktop application).
56+
2. Download the client secrets file and save it as `credentials.json` in your working directory.
57+
3. On first run, a browser window will open for user consent. The resulting token is cached to `token.json` for subsequent runs.
58+
59+
```python
60+
from langchain_google_classroom import GoogleClassroomLoader
61+
62+
loader = GoogleClassroomLoader()
63+
# Opens browser for OAuth consent on first run
64+
docs = loader.load()
65+
```
66+
67+
### Option B: Service Account (Google Workspace)
68+
69+
1. In the [Google Cloud Console](https://console.cloud.google.com/iam-admin/serviceaccounts), create a Service Account.
70+
2. Enable [Domain-Wide Delegation](https://developers.google.com/identity/protocols/oauth2/service-account#delegatingauthority) for the service account.
71+
3. Download the key file and save it as `service_account.json`.
72+
73+
```python
74+
from langchain_google_classroom import GoogleClassroomLoader
75+
76+
loader = GoogleClassroomLoader(
77+
service_account_file="service_account.json",
78+
)
79+
docs = loader.load()
80+
```
81+
82+
## Instantiation
83+
84+
```python
85+
from langchain_google_classroom import GoogleClassroomLoader
86+
87+
loader = GoogleClassroomLoader(
88+
course_ids=["123456789"], # Optional: specific courses. Loads all if omitted.
89+
load_assignments=True, # courseWork items (default: True)
90+
load_announcements=True, # announcements (default: True)
91+
load_materials=True, # courseWorkMaterials (default: True)
92+
load_attachments=True, # resolve Drive file attachments (default: True)
93+
)
94+
```
95+
96+
### Constructor parameters
97+
98+
| Parameter | Type | Default | Description |
99+
|:----------|:-----|:--------|:------------|
100+
| `course_ids` | `list[str]` or `None` | `None` | Course IDs to load. Loads all accessible courses when `None`. |
101+
| `load_assignments` | `bool` | `True` | Load courseWork items. |
102+
| `load_announcements` | `bool` | `True` | Load announcements. |
103+
| `load_materials` | `bool` | `True` | Load courseWork materials. |
104+
| `load_attachments` | `bool` | `True` | Download and yield Drive file attachments. |
105+
| `parse_attachments` | `bool` | `True` | Parse attachment content using built-in parsers (install `langchain-google-classroom[parsers]` for PDF/DOCX support, or set `parse_attachments=False` to skip parsing). |
106+
| `file_parser_cls` | `type[BaseBlobParser]` or `None` | `None` | Custom parser class to use for attachments (replaces built-in parsers). |
107+
| `load_submissions` | `bool` | `False` | Load student submissions. Adds the required scope automatically. |
108+
| `load_topics` | `bool` | `False` | Load course topics. Adds the required scope automatically. |
109+
| `load_roster` | `bool` | `False` | Load student and teacher roster. Adds the required scope automatically. |
110+
| `load_images` | `bool` | `False` | Process image attachments (requires a `vision_model`). |
111+
| `vision_model` | `BaseChatModel` or `None` | `None` | Vision-capable LLM for image understanding in PDFs and images. |
112+
| `max_file_size` | `int` | `50000000` | Maximum attachment file size in bytes. Files larger than this are skipped. |
113+
| `service_account_file` | `str` or `None` | `None` | Path to a service-account key JSON file. |
114+
| `token_file` | `str` or `None` | `None` | Path to a cached OAuth token JSON file. |
115+
| `client_secrets_file` | `str` or `None` | `None` | Path to an OAuth client-secrets JSON file. |
116+
117+
## Load documents
118+
119+
Use `load()` to fetch all documents at once:
120+
121+
```python
122+
from langchain_google_classroom import GoogleClassroomLoader
123+
124+
loader = GoogleClassroomLoader(
125+
course_ids=["123456789"],
126+
)
127+
docs = loader.load()
128+
print(f"Loaded {len(docs)} documents")
129+
```
130+
131+
Each `Document` has structured `page_content` and rich `metadata`:
132+
133+
```python
134+
doc = docs[0]
135+
print(doc.page_content[:200])
136+
print(doc.metadata)
137+
```
138+
139+
```python
140+
# Example metadata
141+
{
142+
"source": "google_classroom",
143+
"content_type": "assignment",
144+
"course_id": "123456789",
145+
"course_name": "Introduction to Computer Science",
146+
"title": "Week 3: Data Structures",
147+
"created_time": "2025-03-15T10:30:00.000Z",
148+
"updated_time": "2025-03-15T10:30:00.000Z",
149+
"alternate_link": "https://classroom.google.com/...",
150+
}
151+
```
152+
153+
## Lazy loading
154+
155+
For large courses or memory-constrained environments, use `lazy_load()` to stream documents one at a time:
156+
157+
```python
158+
from langchain_google_classroom import GoogleClassroomLoader
159+
160+
loader = GoogleClassroomLoader(
161+
course_ids=["123456789"],
162+
)
163+
164+
for doc in loader.lazy_load():
165+
print(f"[{doc.metadata['content_type']}] {doc.metadata.get('title', '')}")
166+
```
167+
168+
## Async loading
169+
170+
The loader supports async iteration via `alazy_load()`:
171+
172+
```python
173+
import asyncio
174+
from langchain_google_classroom import GoogleClassroomLoader
175+
176+
177+
async def main():
178+
loader = GoogleClassroomLoader(
179+
course_ids=["123456789"],
180+
)
181+
docs = []
182+
async for doc in loader.alazy_load():
183+
docs.append(doc)
184+
return docs
185+
186+
187+
docs = asyncio.run(main())
188+
```
189+
190+
## Loading additional data types
191+
192+
### Student submissions
193+
194+
```python
195+
loader = GoogleClassroomLoader(
196+
course_ids=["123456789"],
197+
load_submissions=True,
198+
)
199+
docs = loader.load()
200+
# Includes documents with content_type="submission"
201+
```
202+
203+
### Topics
204+
205+
```python
206+
loader = GoogleClassroomLoader(
207+
course_ids=["123456789"],
208+
load_topics=True,
209+
)
210+
docs = loader.load()
211+
# Includes documents with content_type="topic"
212+
```
213+
214+
### Class roster (students and teachers)
215+
216+
```python
217+
loader = GoogleClassroomLoader(
218+
course_ids=["123456789"],
219+
load_roster=True,
220+
)
221+
docs = loader.load()
222+
# Includes documents with content_type="student" and content_type="teacher"
223+
```
224+
225+
## File attachment parsing
226+
227+
When `load_attachments=True` (the default), the loader resolves Google Drive file attachments on each classroom item and parses them into additional `Document` objects.
228+
229+
### Supported formats
230+
231+
| Format | Parser | Notes |
232+
|:-------|:-------|:------|
233+
| PDF | `PDFParser` | Extracts text; optional vision LLM for embedded images |
234+
| DOCX | `DocxParser` | Extracts text and tables |
235+
| CSV | `CSVParser` | One document per row with header-aware formatting |
236+
| Plain text | `TextParser` | UTF-8 decoding |
237+
| Images (PNG, JPEG, etc.) | `ImageParser` | Requires `vision_model` and `load_images=True` |
238+
| Google Docs/Sheets/Slides | Exported then parsed | Auto-exported to PDF/CSV/plain text via Drive API |
239+
240+
### Using a vision LLM for images
241+
242+
To process image attachments and extract visual context from PDF pages, provide a vision-capable model:
243+
244+
```python
245+
from langchain_google_genai import ChatGoogleGenerativeAI
246+
from langchain_google_classroom import GoogleClassroomLoader
247+
248+
loader = GoogleClassroomLoader(
249+
course_ids=["123456789"],
250+
load_attachments=True,
251+
load_images=True,
252+
vision_model=ChatGoogleGenerativeAI(model="gemini-2.0-flash"),
253+
)
254+
docs = loader.load()
255+
```
256+
257+
### Using a custom file parser
258+
259+
You can replace the built-in parsers with any `BaseBlobParser` subclass:
260+
261+
```python
262+
from langchain_community.document_loaders.parsers.pdf import PyMuPDFParser
263+
from langchain_google_classroom import GoogleClassroomLoader
264+
265+
loader = GoogleClassroomLoader(
266+
course_ids=["123456789"],
267+
file_parser_cls=PyMuPDFParser,
268+
)
269+
docs = loader.load()
270+
```
271+
272+
## API reference
273+
274+
- **PyPI:** [`langchain-google-classroom`](https://pypi.org/project/langchain-google-classroom/)
275+
- **Source:** [GitHub](https://github.com/ayanokojix21/langchain-google-classroom)

‎src/oss/python/integrations/document_loaders/index.mdx‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -45,6 +45,7 @@ The below document loaders allow you to load data from commonly used productivit
4545
| Document Loader | API reference |
4646
|----------------|---------------|
4747
| [AgentMail](/oss/integrations/document_loaders/agentmail) | [`AgentMailLoader`](https://github.com/agentmail-to/langchain-agentmail) |
48+
| [Google Classroom](/oss/integrations/document_loaders/google_classroom) | [`GoogleClassroomLoader`](https://pypi.org/project/langchain-google-classroom/) |
4849

4950
### Webpages
5051

@@ -113,6 +114,7 @@ The below document loaders allow you to load data from common data formats.
113114
<Card title="Google Cloud SQL for PostgreSQL" icon="link" href="/oss/integrations/document_loaders/google_cloud_sql_pg" arrow="true" cta="View guide" />
114115
<Card title="Google Cloud Storage Directory" icon="link" href="/oss/integrations/document_loaders/google_cloud_storage_directory" arrow="true" cta="View guide" />
115116
<Card title="Google Cloud Storage File" icon="link" href="/oss/integrations/document_loaders/google_cloud_storage_file" arrow="true" cta="View guide" />
117+
<Card title="Google Classroom" icon="link" href="/oss/integrations/document_loaders/google_classroom" arrow="true" cta="View guide" />
116118
<Card title="Google Firestore in Datastore Mode" icon="link" href="/oss/integrations/document_loaders/google_datastore" arrow="true" cta="View guide" />
117119
<Card title="Google Drive" icon="link" href="/oss/integrations/document_loaders/google_drive" arrow="true" cta="View guide" />
118120
<Card title="Google El Carro for Oracle Workloads" icon="link" href="/oss/integrations/document_loaders/google_el_carro" arrow="true" cta="View guide" />

0 commit comments

Comments
 (0)