Reformated code; updated linting

app.py

@@ -1,14 +1,8 @@
 import json
-import os
 
 import streamlit as st
-from gdown import download_folder
-from llama_index import ServiceContext
-from llama_index import SimpleDirectoryReader
-from llama_index import VectorStoreIndex
-from llama_index import set_global_service_context
-from llama_index.embeddings import OpenAIEmbedding
-from llama_index.llms import AzureOpenAI
+from src.utils import download_test_data
+from src.utils import load_data
 
 # Initialize message history
 st.header("Chat with André's research 💬 📚")
@@ -21,47 +15,10 @@ with open(r"config.json") as config_file:
     config_details = json.load(config_file)
 
 
-def download_test_data():
-    url = "https://drive.google.com/drive/folders/1uDSAWtLvp1YPzfXUsK_v6DeWta16pq6y"
-    with st.spinner(text="Downloading test data. Might take a few seconds."):
-        download_folder(url, quiet=True, use_cookies=False, output="./data/")
-
-
-@st.cache_resource(show_spinner=False)
-def load_data():
-    with st.spinner(text="Loading and indexing the provided dataset – hang tight! This may take a few seconds."):
-        documents = SimpleDirectoryReader(input_dir="./data", recursive=True).load_data()
-        llm = AzureOpenAI(
-            model="gpt-3.5-turbo",
-            engine=config_details["ENGINE"],
-            temperature=0.5,
-            api_key=os.getenv("OPENAI_API_KEY"),
-            api_base=config_details["OPENAI_API_BASE"],
-            api_type="azure",
-            api_version=config_details["OPENAI_API_VERSION"],
-            system_prompt="You are an expert on André's research and your job is to answer"
-            "technical questions. Assume that all questions are related to"
-            "André's research. Keep your answers technical and based on facts"
-            " – do not hallucinate features.",
-        )
-        # You need to deploy your own embedding model as well as your own chat completion model
-        embed_model = OpenAIEmbedding(
-            model="text-embedding-ada-002",
-            deployment_name=config_details["ENGINE_EMBEDDING"],
-            api_key=os.getenv("OPENAI_API_KEY"),
-            api_base=config_details["OPENAI_API_BASE"],
-            api_type="azure",
-            api_version=config_details["OPENAI_API_VERSION"],
-        )
-        service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)
-        set_global_service_context(service_context)
-        index = VectorStoreIndex.from_documents(documents)  # , service_context=service_context)
-        return index
-
-
 def main():
+    # setup dataset
     download_test_data()
-    index = load_data()
+    index = load_data(config_details)
     chat_engine = index.as_chat_engine(chat_mode="condense_question", verbose=True)
 
     if prompt := st.chat_input("Your question"):  # Prompt for user input and save to chat history

chatbot/utils.py

@@ -0,0 +1,50 @@
+import os
+
+import streamlit as st
+from gdown import download_folder
+from llama_index import ServiceContext
+from llama_index import SimpleDirectoryReader
+from llama_index import VectorStoreIndex
+from llama_index import set_global_service_context
+from llama_index.embeddings import OpenAIEmbedding
+from llama_index.llms import AzureOpenAI
+
+
+@st.cache_resource(show_spinner=False)
+def download_test_data():
+    # url = f"https://drive.google.com/drive/folders/uc?export=download&confirm=pbef&id={file_id}"
+    url = "https://drive.google.com/drive/folders/1uDSAWtLvp1YPzfXUsK_v6DeWta16pq6y"
+    with st.spinner(text="Downloading test data. Might take a few seconds."):
+        download_folder(url=url, quiet=False, use_cookies=False, output="./data/")
+
+
+@st.cache_resource(show_spinner=False)
+def load_data(config_details):
+    with st.spinner(text="Loading and indexing the provided dataset – hang tight! This may take a few seconds."):
+        documents = SimpleDirectoryReader(input_dir="./data", recursive=True).load_data()
+        llm = AzureOpenAI(
+            model="gpt-3.5-turbo",
+            engine=config_details["ENGINE"],
+            temperature=0.5,
+            api_key=os.getenv("OPENAI_API_KEY"),
+            api_base=config_details["OPENAI_API_BASE"],
+            api_type="azure",
+            api_version=config_details["OPENAI_API_VERSION"],
+            system_prompt="You are an expert on André's research and your job is to answer"
+            "technical questions. Assume that all questions are related to"
+            "André's research. Keep your answers technical and based on facts"
+            " – do not hallucinate features.",
+        )
+        # You need to deploy your own embedding model as well as your own chat completion model
+        embed_model = OpenAIEmbedding(
+            model="text-embedding-ada-002",
+            deployment_name=config_details["ENGINE_EMBEDDING"],
+            api_key=os.getenv("OPENAI_API_KEY"),
+            api_base=config_details["OPENAI_API_BASE"],
+            api_type="azure",
+            api_version=config_details["OPENAI_API_VERSION"],
+        )
+        service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)
+        set_global_service_context(service_context)
+        index = VectorStoreIndex.from_documents(documents)  # , service_context=service_context)
+        return index

setup.cfg

@@ -3,7 +3,7 @@ description-file = README.md
 
 [isort]
 force_single_line=True
-known_first_party=gradient_accumulator
+known_first_party=chatbot
 line_length=120
 profile=black
 
@@ -12,3 +12,4 @@ profile=black
 per-file-ignores=*__init__.py:F401
 ignore=E203,W503,W605,F632,E266,E731,E712,E741
 max-line-length=120
+exclude=venv/

shell/format.sh

@@ -1,4 +1,4 @@
 #!/bin/bash
-isort --sl app.py
-black --line-length 120 app.py
-flake8 app.py
+isort --sl .
+black --line-length 120 .
+flake8 .

shell/lint.sh

@@ -1,19 +1,19 @@
 #!/bin/bash
-isort --check --sl -c app.py
+isort --check --sl -c .
 if ! [ $? -eq 0 ]
 then
   echo "Please run \"sh shell/format.sh\" to format the code."
   exit 1
 fi
 echo "no issues with isort"
-flake8 app.py
+flake8 .
 if ! [ $? -eq 0 ]
 then
   echo "Please fix the code style issue."
   exit 1
 fi
 echo "no issues with flake8"
-black --check --line-length 120 app.py
+black --check --line-length 120 .
 if ! [ $? -eq 0 ]
 then
   echo "Please run \"sh shell/format.sh\" to format the code."