allow openai api key to be stored in streamlit secrets as well

.gitignore

@@ -1,4 +1,3 @@
 data
 __pycache__
-.streamlit/secrets.toml
 .env

README.md

@@ -15,6 +15,6 @@ This is an app that let's you ask questions about any data source by leveraging
 ## Good to know
 
 - As default context this git repository is taken so you can directly start asking question about its functionality without chosing an own data source.
-- To run locally or deploy somewhere, execute `cp .env.template .env` and set necessary keys in the newly created secrets file. Other options are manually setting of environment variables, or creating a `.streamlit/secrets.toml` file and storing credentials there.
+- To run locally or deploy somewhere, execute `cp .env.template .env` and set credentials in the newly created .env file. Other options are manually setting of system environment variables, or storing them into `.streamlit/secrets.toml`.
 - Your data won't load? Feel free to open an Issue or PR and contribute!
 - Yes, Chad in `DataChad` refers to the well-known [meme](https://www.google.com/search?q=chad+meme)

app.py

@@ -21,7 +21,7 @@ from utils import (
 )
 
 # Page options and header
-st.set_option("client.showErrorDetails", True)
+st.set_option("client.showErrorDetails", False)
 st.set_page_config(
     page_title=APP_NAME, page_icon=PAGE_ICON, initial_sidebar_state="expanded"
 )

constants.py

@@ -1,10 +1,5 @@
 from pathlib import Path
 
-from dotenv import load_dotenv
-
-# loads environment variables
-load_dotenv()
-
 APP_NAME = "DataChad"
 MODEL = "gpt-3.5-turbo"
 PAGE_ICON = "🤖"

utils.py

@@ -7,6 +7,7 @@ import sys
 import deeplake
 import openai
 import streamlit as st
+from dotenv import load_dotenv
 from langchain.callbacks import get_openai_callback
 from langchain.chains import ConversationalRetrievalChain
 from langchain.chat_models import ChatOpenAI
@@ -30,6 +31,9 @@ from langchain.vectorstores import DeepLake
 
 from constants import APP_NAME, DATA_PATH, MODEL, PAGE_ICON
 
+# loads environment variables
+load_dotenv()
+
 logger = logging.getLogger(APP_NAME)
 
 
@@ -55,7 +59,11 @@ configure_logger(0)
 def authenticate(openai_api_key, activeloop_token, activeloop_org_name):
     # Validate all credentials are set and correct
     # Check for env variables to enable local dev and deployments with shared credentials
-    openai_api_key = openai_api_key or os.environ.get("OPENAI_API_KEY")
+    openai_api_key = (
+        openai_api_key
+        or os.environ.get("OPENAI_API_KEY")
+        or st.secrets.get("OPENAI_API_KEY")
+    )
     activeloop_token = (
         activeloop_token
         or os.environ.get("ACTIVELOOP_TOKEN")
@@ -238,7 +246,7 @@ def get_chain(data_source):
     vector_store = setup_vector_store(data_source)
     retriever = vector_store.as_retriever()
     # Search params "fetch_k" and "k" define how many documents are pulled from the hub
-    # and selected after the document matching to build the context 
+    # and selected after the document matching to build the context
     # that is fed to the model together with your prompt
     search_kwargs = {
         "maximal_marginal_relevance": True,