Hi, I'm Sasmitha. I build cool AI tools.
- Python
- TS/JS
- React
- FastAPI
- Tailwind
- LangChain
- Supabase
- XState
Want to build and ship your MVP fast🚀 Reach me at [email protected]
Accurate answers and instant citations for your documents.
Home Page: https://knowledgegpt.streamlit.app/
License: MIT License
Hi, I'm Sasmitha. I build cool AI tools.
Want to build and ship your MVP fast🚀 Reach me at [email protected]
Now all vector index only temporary. Can we make an options to save it to our local storage or another vector index like pinecone ?
For reviewing confidential documents, we'd prefer to use our own APIs, either view oobabooga or koboldcpp. Is there the possibility of including options for using alternate APIs, including local or Claude?
Hello, I keep getting the following error when running main.py. I forked the app and followed the instructions to install it. I apologize if this is a trivial issue that I shouldn't be posting here.
2024-01-14 10:26:33.229 Uncaught app exception
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script
exec(code, module.dict)
File "/Users/marcionegrao/knowledge_gpt/knowledge_gpt/main.py", line 3, in
from knowledge_gpt.components.sidebar import sidebar
ModuleNotFoundError: No module named 'knowledge_gpt'
During the "poetry install step", there is an error msg:
"Warning: poetry.lock is not consistent with pyproject.toml. You may be getting improper dependencies. Run poetry lock [--no-update]
to fix it."
Afterwards, when I run "streamlit run main.py", there's error msg:
ModuleNotFoundError: No module named 'openai'
Traceback:
File "C:\Users\souler c\knowledge_gpt.venv\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 565, in _run_script
exec(code, module.dict)
File "C:\Users\souler c\knowledge_gpt\knowledge_gpt\main.py", line 3, in
from openai.error import OpenAIError
I'll also attach cmd & streamlit detail for you:
cmd history.txt
Rate limit reached for default-global-with-image-limits in organization org-ks3x7KSLAWTqCJv1Yq9x3FmZ on requests per min. Limit: 60.000000 / min. Current: 80.000000 / min. Contact [email protected] if you continue to have issues.
how can I prevent triggle the limit?
Thanks
Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.
With the release of gpt-4 via the API there can be a parameter passed for model specifying gpt-3.5-turbo or gpt-4; however the current qa.py expects model to be debug or opanai
I recently posted an issue titled "Over resource limits on Streamlit Cloud." but now the website just says, "Oh no. Error running app." Please solve this issue.
Rate limit reached for default-global-with-image-limits in organization org-Yu8pTMWbwQ0jvtsUA1H1py29 on requests per min. Limit: 60.000000 / min. Current: 70.000000 / min. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.
Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.
Hey! Ive tried cloning this repo, installed all dependencies and then deployed it to streamlit, but I get a "please wait" that never ends and then a connection time-out. Maybe Im missing something?
Hi Sasmitha,
I love what you did in this knowledge_gpt. Thank you very much for sharing it!
Thanks a lot!
Leo
Getting an error message
"Error running app. If this keeps happening, please contact support."
Should I change st.cache and st.experimental_memo? When I try with st.cache_data raises an error for an unexpected argument: "allow_output_mutation=True"
What if GPT records the responses in a database and pulls the response from the database instead of sending new requests to OpenAI for similar queries?
After tried to install your app locally I encountered this error on command line OSError: [WinError 10013] An attempt was made to access a socket in a way forbidden by its access permissions
How can I fix this issue to run locally? I tried to disable Antivirus as suggested on stackoverflow but no success
I uploaded a Chinese txt file(zy.txt).
Input chinese prompt: “什么是精气学说”
input english prompt:"What is the concept of Jingqi theory",
Whether inputting Chinese or English, the following errors will always occur:
This model's maximum context length is 4097 tokens, however you requested 7203 tokens (6947 in your prompt; 256 for the completion). Please reduce your prompt; or completion length.
zy.txt
Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.
input : Chinese short article(6000 words)
Ask any question, follow Error:
This model's maximum context length is 4097 tokens, however you requested 5762 tokens (5506 in your prompt; 256 for the completion). Please reduce your prompt; or completion length.
I get this error message while trying to parse the pdf:
IndexError: This app has encountered an error. The original error message is redacted to prevent data leaks. Full error details have been recorded in the logs (if you're on Streamlit Cloud, click on 'Manage app' in the lower right of your app).
Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.
Hi, are you planning to create docker image?
I can provide you dockerfile, if needed.
Thanks for writing this extremely useful project and making it open source.
I was wondering if you have a script for the functions to be used in another python script (without streamlit functions / UI elements). The use case for this is to automate the process by looping through some locally stored files with nested loops for some questions and save the output into csv file. Unfortunately my current python skills are not strong enough to extract these functions from the code you provided (specially that I have not used streamlit before).
also I second the request by others of being able to save the embeddings locally so the script will not have to re calculate them every time the same file is loaded (saves time and saves bandwidth / api tokens).
thanks again.
Hey there 👋 Just wanted to let you know that your app on Streamlit Cloud deployed from this repo has gone over its resource limits. Access to the app is temporarily limited. Visit the app to see more details and possible solutions.
Not sure why I'm getting this error?
ImportError: cannot import name 'faq' from partially initialized module 'knowledge_gpt.components.sidebar' (most likely due to a circular import) (C:\Users\xxx\OneDrive\Documents\GitHub\knowledge_gpt\knowledge_gpt\components\sidebar.py)
Traceback:
File "C:\Users\xxx\OneDrive\Documents\GitHub\knowledge_gpt.venv\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 565, in _run_script
exec(code, module.dict)
File "C:\Users\xxx\OneDrive\Documents\GitHub\knowledge_gpt\knowledge_gpt\main.py", line 4, in
from knowledge_gpt.components.sidebar import sidebar
File "C:\Users\xxx\OneDrive\Documents\GitHub\knowledge_gpt\knowledge_gpt\components\sidebar.py", line 3, in
from knowledge_gpt.components.sidebar import faq
I wonder is it any way that can store for permanently, no need uploade when refreshed.
How to change support to Azure OpenIA?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.