A LangChain-compatible chat model that extracts responses via UI automation
Project description
UI Chat Model (ChatUIBridge)
A LangChain-compatible chat model that extracts responses by automating a web UI via Playwright.
Installation
pip install ui-chat-model
playwright install chromium
Usage
from ui_chat_model import ChatUIBridge
# Initialize the model pointing to your hosted UI
model = ChatUIBridge(
url="https://your-frontend-url.com",
model_name="llama-3.1-8b-instant"
)
# Use it like any other LangChain chat model
response = model.invoke("Hello, how are you?")
print(response.content)
How it works
This library uses Playwright to open a browser, navigate to a specified UI, type the prompt into a textarea, and extract the resulting text from the UI. It's designed to bridge web-only AI interfaces into LangChain workflows.
Project details
Release history Release notifications | RSS feed
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 ui_chat_model-0.1.0.tar.gz.
File metadata
- Download URL: ui_chat_model-0.1.0.tar.gz
- Upload date:
- Size: 2.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d775d933134ae83fa61e52b851f89ed510467228a3851c3511dc83f8877fc4ff
|
|
| MD5 |
c2d64025dd60233aa4ef781b1e53d0c4
|
|
| BLAKE2b-256 |
58e107ef6550daea23ba05d45f96e093ada3ec085d049b63cb98dcacfa4cd64d
|
File details
Details for the file ui_chat_model-0.1.0-py3-none-any.whl.
File metadata
- Download URL: ui_chat_model-0.1.0-py3-none-any.whl
- Upload date:
- Size: 2.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4b540c38b0cf0a61576e2f67ef1982558615f2441e37d6b62d4b7e0489912af1
|
|
| MD5 |
9a4e43b9f56ac841f8c929a9b65e0c48
|
|
| BLAKE2b-256 |
4b1620f3533fa86fbdafb652d11b7e1dcb2e78b3d71b75344fcf8b9423bff948
|