langchain/docs/extras/integrations/document_loaders/telegram.ipynb

Telegram

Telegram Messenger is a globally accessible freemium, cross-platform, encrypted, cloud-based and centralized instant messaging service. The application also provides optional end-to-end encrypted chats and video calling, VoIP, file sharing and several other features.

This notebook covers how to load data from Telegram into a format that can be ingested into LangChain.

In [1]:

from langchain.document_loaders import TelegramChatFileLoader, TelegramChatApiLoader

In [2]:

loader = TelegramChatFileLoader("example_data/telegram.json")

In [3]:

loader.load()

Out [3]:

[Document(page_content="Henry on 2020-01-01T00:00:02: It's 2020...\n\nHenry on 2020-01-01T00:00:04: Fireworks!\n\nGrace 🧤 ðŸ\x8d’ on 2020-01-01T00:00:05: You're a minute late!\n\n", metadata={'source': 'example_data/telegram.json'})]

TelegramChatApiLoader loads data directly from any specified chat from Telegram. In order to export the data, you will need to authenticate your Telegram account.

You can get the API_HASH and API_ID from https://my.telegram.org/auth?to=apps

chat_entity – recommended to be the entity of a channel.

In [ ]:

loader = TelegramChatApiLoader(
    chat_entity="<CHAT_URL>",  # recommended to use Entity here
    api_hash="<API HASH >",
    api_id="<API_ID>",
    user_name="",  # needed only for caching the session.
)

In [ ]:

loader.load()

In [ ]: