Greetings,
I’m developing a new page for my app that will use LangChain to interact with my Database via OpenAI - it’s working great for the most part!
However, during some submissions of the st.chat_input field and the st.chat_message, the page is acting funny… as soon as I hit submit the message I just typed will overwrite the last message that was in the thread, and you don’t see a RUNNING indicator for streamlit. If you wait a little bit and reload the page (by clicking the navigation, not refreshing) the question and answer will render property. It almost seems that as the chat starts to get towards the bottom of the page and the input control it acts funny…
Anyone have any thoughts on where to look or what might be wrong?
Video of Behavior
Community Cloud: https://deadpool.streamlit.app
There are no error messages to share
Repo and Actual File Versions:
Note: Please don’t flag this as an advertisement - you didnt’ read this if you think that…
1 Like
I found that this is an issue with the cookie manager used by streamlit-authenticator - i’ll keep an eye on that thread and issue:
opened 12:33PM - 14 Nov 23 UTC
duplicate
I created a minimum wrapper for the openai chat completion api. It runs locally … and on the Streamlit cloud without issue. When I add authentication, the local version still works fine but if I deploy to the streamlit community cloud, the chat stops working after one or two user inputs. Below is the code that includes the authentication.
```
import openai
import streamlit as st
import streamlit_authenticator as stauth
st.title("ChatGPT-like clone")
openai.api_key = st.secrets["OPENAI_API_KEY"]
authenticator = stauth.Authenticate(
dict(st.secrets['credentials']),
st.secrets['cookie']['name'],
st.secrets['cookie']['key'],
st.secrets['cookie']['expiry_days'],
st.secrets['preauthorized']
)
name, authentication_status, username = authenticator.login('Login', 'sidebar') # location is 'sidebar' or 'main'
if authentication_status:
if "openai_model" not in st.session_state:
st.session_state["openai_model"] = "gpt-3.5-turbo"
if "messages" not in st.session_state:
st.session_state.messages = []
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
if prompt := st.chat_input("What is up?"):
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.markdown(prompt)
with st.chat_message("assistant"):
message_placeholder = st.empty()
full_response = ""
response = openai.chat.completions.create(
model=st.session_state["openai_model"],
messages=st.session_state.messages,
stream=True,
)
for part in response:
full_response += (part.choices[0].delta.content or "")
message_placeholder.markdown(full_response + "▌")
message_placeholder.markdown(full_response)
st.session_state.messages.append({"role": "assistant", "content": full_response})
elif authentication_status == False:
st.error('Username/password is incorrect')
elif authentication_status == None:
st.warning('Please enter your username and password')
```
If I comment out the authentication, I can deploy to the Streamlit cloud and it works fine. See below
```
import openai
import streamlit as st
import streamlit_authenticator as stauth
st.title("ChatGPT-like clone")
openai.api_key = st.secrets["OPENAI_API_KEY"]
# authenticator = stauth.Authenticate(
# dict(st.secrets['credentials']),
# st.secrets['cookie']['name'],
# st.secrets['cookie']['key'],
# st.secrets['cookie']['expiry_days'],
# st.secrets['preauthorized']
# )
# name, authentication_status, username = authenticator.login('Login', 'sidebar') # location is 'sidebar' or 'main'
# if authentication_status:
if "openai_model" not in st.session_state:
st.session_state["openai_model"] = "gpt-3.5-turbo"
if "messages" not in st.session_state:
st.session_state.messages = []
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
if prompt := st.chat_input("What is up?"):
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.markdown(prompt)
with st.chat_message("assistant"):
message_placeholder = st.empty()
full_response = ""
response = openai.chat.completions.create(
model=st.session_state["openai_model"],
messages=st.session_state.messages,
stream=True,
)
for part in response:
full_response += (part.choices[0].delta.content or "")
message_placeholder.markdown(full_response + "▌")
message_placeholder.markdown(full_response)
st.session_state.messages.append({"role": "assistant", "content": full_response})
# elif authentication_status == False:
# st.error('Username/password is incorrect')
# elif authentication_status == None:
# st.warning('Please enter your username and password')
```
I have tried a few variations. As soon as the code
```
# authenticator = stauth.Authenticate(
# dict(st.secrets['credentials']),
# st.secrets['cookie']['name'],
# st.secrets['cookie']['key'],
# st.secrets['cookie']['expiry_days'],
# st.secrets['preauthorized']
# )
```
is uncommented (even if I don't check the authentication status), chat stops working after one or two user inputs
Note: Please don’t flag this as an advertisement - you didnt’ read this if you think that…
2 Likes
Hello @brian-dka ,
Here’s how you can manage a chat application in Streamlit using session state:
import streamlit as st
if 'chat_history' not in st.session_state:
st.session_state.chat_history = []
for message in st.session_state.chat_history:
st.chat_message(message['role'], message['content'])
user_input = st.chat_input("Say something...")
if user_input:
st.session_state.chat_history.append({'role': 'user', 'content': user_input})
response = "This is a response to your message."
st.session_state.chat_history.append({'role': 'bot', 'content': response})
Kind Regards,
P.S. Lets connect on LinkedIn !
➤ Website: https://sahirmaharaj.com sahir@sahirmaharaj.com Lets chat about how I can assist! Sharing my knowledge about data science and AI Download Now
1 Like
Thank you @sahirmaharaj ! This results in the same behaviour - looks like this is a common bug from the streamlit-authentication. The author is working on it.
1 Like
It’s my pleasure @brian-dka . Feel free to let me know if you might have any further questions!
1 Like
system
August 4, 2024, 4:40pm
6
This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.
