streamlit-ai-chatbot
Adds the Asyntai AI chat assistant to a Streamlit app. The assistant answers visitor questions from your own content, day and night, in more than 80 languages.
Free and open source. Works on every Asyntai plan, including the free plan.
- Requires Streamlit 1.28 or newer and Python 3.10 or newer
- Documentation: https://asyntai.com/documentation/integrations/streamlit/
Install
pip install streamlit-ai-chatbot
Use
Call chatbot() once near the top of your app:
import streamlit as st
from streamlit_ai_chatbot import chatbot
chatbot("asyntai_ab12cd34")
st.title("My app")
You get the ID from the Install page of your Asyntai dashboard. You can paste the whole snippet; the package keeps only the ID.
The chat button appears in the corner of the page. It stays open when the app reruns, and it loads only once per browser tab.
Keep the ID out of your code
Leave out the ID, and the package reads ASYNTAI_WIDGET_ID from
st.secrets or from the environment:
# .streamlit/secrets.toml
ASYNTAI_WIDGET_ID = "asyntai_ab12cd34"
chatbot()
This also works on Streamlit Community Cloud: add the line in the app's Secrets settings.
Multipage apps
With st.navigation, call chatbot() in the main file, before
pg.run(). With a pages/ folder, call it at the top of each page.
Options
chatbot(
"asyntai_ab12cd34",
script_url="https://widget.asyntai.com/static/js/chat-widget.js", # optional
)
chatbot() returns True when the chat is on the page. With an ID that is
not valid it shows nothing, returns False and logs a warning.
How it works
On Streamlit 1.52 and newer, the package uses st.html to add the widget
script to the page. On older versions it uses a hidden component. Either way,
the empty block is hidden, so your layout does not change.
What the assistant does
- Answers visitor questions from your website, documents and FAQ
- Collects leads and hands the chat to a person when needed
- Works in more than 80 languages
Set it up and train it in your Asyntai dashboard.
License
MIT
Metadata
Release files for streamlit-ai-chatbot 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| streamlit_ai_chatbot-1.0.0.tar.gz | 8.6 kB | Without provenance | Details for streamlit_ai_chatbot-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| streamlit_ai_chatbot-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for streamlit_ai_chatbot-1.0.0-py3-none-any.whl |
Total release size: 15.5 kB
Release files / streamlit_ai_chatbot-1.0.0.tar.gz
| Download URL | streamlit_ai_chatbot-1.0.0.tar.gz |
|---|---|
| Size | 8.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
98e9484f37dfa4fb32d0669616ca6013c54a2b0275f5824ed059a2e47dea28fe
|
|
BLAKE2b-256 checksum How to use checksums |
085153ba7a2e7c31b25d29de6f7fb5f74016292e62d96e72c548ce4fbd5dd0bc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / streamlit_ai_chatbot-1.0.0-py3-none-any.whl
| Download URL | streamlit_ai_chatbot-1.0.0-py3-none-any.whl |
|---|---|
| Size | 6.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4eedd2d967560cb25932445aafb5902681f75d412eb88429ced96b063121c34f
|
|
BLAKE2b-256 checksum How to use checksums |
0a8b60ec0c2080832aa2258c57c820d1fe123861ce1ae39f2f045c18148530cd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Security for streamlit-ai-chatbot 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.