A Human-in-the-Loop retriever for LangChain that pauses execution to wait for a Telegram reply.
Project description
telegram-retriever
telegram-retriever is a lightweight Python library designed to integrate "Human-in-the-Loop" capabilities into LangChain workflows.
Unlike standard retrievers that search databases, this tool allows an LLM agent to pause execution, send a query to a specific Telegram user, and synchronously wait for a text-based reply. The user's reply is returned to the agent as the retrieved context.
Key Features
- Interactive Retrieval: The
invoke()method blocks until a human replies. - Strict Threading: Validates that the incoming message is an explicit "Reply To" the bot's question.
- Zero Infrastructure: Uses Long Polling. No webhooks, public IPs, or databases required.
- Text-Only: Filters out stickers, photos, and voice notes to ensure clean LLM input.
Installation
pip install telegram-retriever
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file telegram_retriever-0.1.1.tar.gz.
File metadata
- Download URL: telegram_retriever-0.1.1.tar.gz
- Upload date:
- Size: 10.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
635bad6f0ec9547f159d8e7b702737819e393f935de41443b22d9628e6442d46
|
|
| MD5 |
f93ff91f2a968c27be485b66797122c1
|
|
| BLAKE2b-256 |
0ac27303734984f0caf8cdce52fd7addbd93e9d7b2562c3952ba0457a352a379
|
File details
Details for the file telegram_retriever-0.1.1-py3-none-any.whl.
File metadata
- Download URL: telegram_retriever-0.1.1-py3-none-any.whl
- Upload date:
- Size: 6.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
545f265b5f533f057c6745beb6fdd7c9674f29b80ff6bea84b1fe50765046a6a
|
|
| MD5 |
f16d252a3c9775b2efa9fff201ce6b91
|
|
| BLAKE2b-256 |
a3c0f6ace10e33d4b30fd56d0f1df75b076dbbd2a3926ce5d12752ae56b55fa6
|
