My application is running when I run it locally. But it is not getting deployed on Streamlit Cloud.
Link to the Github Repo is apurbanand/knowledge_gpt_authorized
I am getting the following error.
Blockquote
Collecting pytz-deprecation-shim==0.1.0.post0
Downloading pytz_deprecation_shim-0.1.0.post0-py2.py3-none-any.whl (15 kB)
ERROR: Could not find a version that satisfies the requirement pywin32>=300 (from versions: none)
ERROR: No matching distribution found for pywin32>=300
WARNING: You are using pip version 22.0.3; however, version 23.2.1 is available.
You should consider upgrading via the β/home/adminuser/venv/bin/python -m pip install --upgrade pipβ command.
Checking if Streamlit is installed
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
[15:32:54]installer returned a non-zero exit code
[15:32:54]
[15:34:31]
[15:34:31]
Blockquote
The main.py file - knowledge_gpt_authorized/knowledge_gpt
/main.py
import streamlit as st
import toml
import os
# Set the working directory to the script's directory
script_directory = os.path.dirname(os.path.abspath(__file__))
os.chdir(script_directory)
# Load authorized email IDs from secrets.toml
secrets = toml.load("secrets.toml")
authorized_emails = secrets["auth"]["authorized_emails"]
# Initialize user_email as None
user_email = None
# Set Streamlit page configuration
st.set_page_config(page_title="KnowledgeGPT", page_icon="π", layout="wide")
# Define the login page function
def login_page():
global user_email
st.title("Login")
email = st.text_input("Email:")
password = st.text_input("Password:", type="password")
login_button = st.button("Log In")
if login_button:
if email in authorized_emails:
st.success("Login successful!")
user_email = email # Assign the email
else:
st.error("Unauthorized email. Please try again.")
# Call the login page function
login_page()
# Check if user_email is set and authorized
if user_email is None:
st.warning("Unauthorized access. Please log in with an authorized email.")
st.stop()
# st.write(authorized_emails)
# st.write(user_email)
# The rest of your Streamlit application code goes here...
def main():
if "user_email" in st.session_state:
user_email = st.session_state.user_email
# Check if the user's email is authorized
if user_email not in authorized_emails:
st.warning("Unauthorized access. Please log in with an authorized email.")
st.stop()
# The rest of your Streamlit application code goes here
if __name__ == "__main__":
main()
from knowledge_gpt.components.sidebar import sidebar
from knowledge_gpt.ui import (
wrap_doc_in_html,
is_query_valid,
is_file_valid,
is_open_ai_key_valid,
display_file_read_error,
)
from knowledge_gpt.core.caching import bootstrap_caching
from knowledge_gpt.core.parsing import read_file
from knowledge_gpt.core.chunking import chunk_file
from knowledge_gpt.core.embedding import embed_files
from knowledge_gpt.core.qa import query_folder
from knowledge_gpt.core.utils import get_llm
EMBEDDING = "openai"
VECTOR_STORE = "faiss"
MODEL_LIST = ["gpt-3.5-turbo", "gpt-4"]
# Uncomment to enable debug mode
# MODEL_LIST.insert(0, "debug")
st.header("πKnowledgeGPT")
# Enable caching for expensive functions
bootstrap_caching()
sidebar()
openai_api_key = st.session_state.get("OPENAI_API_KEY")
if not openai_api_key:
st.warning(
"Enter your OpenAI API key in the sidebar. You can get a key at"
" https://platform.openai.com/account/api-keys."
)
uploaded_file = st.file_uploader(
"Upload a pdf, docx, or txt file",
type=["pdf", "docx", "txt"],
help="Scanned documents are not supported yet!",
)
model: str = st.selectbox("Model", options=MODEL_LIST) # type: ignore
with st.expander("Advanced Options"):
return_all_chunks = st.checkbox("Show all chunks retrieved from vector search")
show_full_doc = st.checkbox("Show parsed contents of the document")
if not uploaded_file:
st.stop()
try:
file = read_file(uploaded_file)
except Exception as e:
display_file_read_error(e, file_name=uploaded_file.name)
chunked_file = chunk_file(file, chunk_size=300, chunk_overlap=0)
if not is_file_valid(file):
st.stop()
if not is_open_ai_key_valid(openai_api_key, model):
st.stop()
with st.spinner("Indexing document... This may take a whileβ³"):
folder_index = embed_files(
files=[chunked_file],
embedding=EMBEDDING if model != "debug" else "debug",
vector_store=VECTOR_STORE if model != "debug" else "debug",
openai_api_key=openai_api_key,
)
with st.form(key="qa_form"):
query = st.text_area("Ask a question about the document")
submit = st.form_submit_button("Submit")
if show_full_doc:
with st.expander("Document"):
# Hack to get around st.markdown rendering LaTeX
st.markdown(f"<p>{wrap_doc_in_html(file.docs)}</p>", unsafe_allow_html=True)
if submit:
if not is_query_valid(query):
st.stop()
# Output Columns
answer_col, sources_col = st.columns(2)
llm = get_llm(model=model, openai_api_key=openai_api_key, temperature=0)
result = query_folder(
folder_index=folder_index,
query=query,
return_all=return_all_chunks,
llm=llm,
)
with answer_col:
st.markdown("#### Answer")
st.markdown(result.answer)
with sources_col:
st.markdown("#### Sources")
for source in result.sources:
st.markdown(source.page_content)
st.markdown(source.metadata["source"])
st.markdown("---")**strong text**
Blockquote
The requirements.txt file is as below
Blockquote
ο»Ώaiohttp==3.8.5
aiosignal==1.3.1
altair==5.0.1
asttokens==2.2.1
async-timeout==4.0.2
attrs==23.1.0
backcall==0.2.0
black==23.7.0
blinker==1.6.2
cachetools==5.3.1
certifi==2023.7.22
charset-normalizer==3.2.0
click==8.1.6
cohere==3.10.0
colorama==0.4.6
comm==0.1.3
dataclasses-json==0.5.9
debugpy==1.6.7
decorator==5.1.1
docx2txt==0.8
executing==1.2.0
faiss-cpu==1.7.4
filelock==3.12.3
flake8==6.0.0
frozenlist==1.4.0
fsspec==2023.9.0
gitdb==4.0.10
GitPython==3.1.32
greenlet==2.0.2
huggingface-hub==0.16.4
idna==3.4
importlib-metadata==6.8.0
iniconfig==2.0.0
ipykernel==6.25.1
ipython==8.14.0
ipywidgets==8.0.7
isort==5.12.0
jedi==0.18.2
Jinja2==3.1.2
jsonschema==4.18.4
jsonschema-specifications==2023.7.1
jupyter_client==8.3.0
jupyter_core==5.3.1
jupyterlab-widgets==3.0.8
-e git+https://github.com/mmz-001/knowledge_gpt@6002862f69489a81f1bc39d0eb265a6960362f48#egg=knowledge_gpt
langchain==0.0.220
langchainplus-sdk==0.0.20
markdown-it-py==3.0.0
MarkupSafe==2.1.3
marshmallow==3.20.1
marshmallow-enum==1.5.1
matplotlib-inline==0.1.6
mccabe==0.7.0
mdurl==0.1.2
multidict==6.0.4
mypy-extensions==1.0.0
nest-asyncio==1.5.6
numexpr==2.8.4
numpy==1.25.1
openai==0.27.8
openapi-schema-pydantic==1.2.4
packaging==23.1
pandas==2.0.3
parso==0.8.3
pathspec==0.11.1
pickleshare==0.7.5
Pillow==9.5.0
platformdirs==3.9.1
pluggy==1.2.0
prompt-toolkit==3.0.39
protobuf==4.23.4
psutil==5.9.5
pure-eval==0.2.2
pyarrow==12.0.1
pycodestyle==2.10.0
pycryptodome==3.18.0
pydantic==1.10.11
pydeck==0.8.0
pyflakes==3.0.1
Pygments==2.15.1
Pympler==1.0.1
PyMuPDF==1.22.5
pytest==7.4.0
python-dateutil==2.8.2
python-dotenv==0.21.1
pytz==2023.3
pytz-deprecation-shim==0.1.0.post0
pywin32==306
PyYAML==6.0.1
pyzmq==25.1.0
referencing==0.30.0
regex==2023.6.3
requests==2.31.0
rich==13.4.2
rpds-py==0.9.2
safetensors==0.3.3
six==1.16.0
smmap==5.0.0
SQLAlchemy==2.0.19
stack-data==0.6.2
streamlit==1.25.0
tenacity==8.2.2
tiktoken==0.4.0
tokenizers==0.13.3
toml==0.10.2
toolz==0.12.0
tornado==6.3.2
tqdm==4.65.0
traitlets==5.9.0
transformers==4.33.1
typing-inspect==0.9.0
typing_extensions==4.7.1
tzdata==2023.3
tzlocal==4.3.14
urllib3==1.26.16
validators==0.20.0
watchdog==3.0.0
wcwidth==0.2.6
widgetsnbextension==4.0.8
yarl==1.9.2
zipp==3.16.2