Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 
 import gradio as gr
 
-from openai import AzureOpenAI
+from openai import OpenAI
 
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
@@ -10,37 +10,19 @@ from langchain_community.document_loaders import PyPDFLoader
 from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
 from langchain_community.vectorstores import Chroma
 
-client = AzureOpenAI(
-    azure_endpoint=os.environ['AZURE_OPENAI_ENDPOINT'],
-    api_key=os.environ['AZURE_OPENAI_KEY'],
-    api_version="2023-05-15"
-)
-
-chat_model_deployment_name = "gpt-35-turbo"
+client = OpenAI(api_key=os.environ['OPENAI_API_KEY'])
 
 embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-small')
 
-text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
-    encoding_name='cl100k_base',
-    chunk_size=512,
-    chunk_overlap=16
-)
-
-pdf_file = "tsla-20221231-gen.pdf"
-
-pdf_loader = PyPDFLoader(pdf_file)
-
-tesla_10k_chunks_ada = pdf_loader.load_and_split(text_splitter)
-
-tesla_10k_collection = 'tesla-10k-2022'
+tesla_10k_collection = 'tesla-10k-2019-to-2023'
 
-vectorstore = Chroma.from_documents(
-    tesla_10k_chunks_ada,
-    embedding_model,
-    collection_name=tesla_10k_collection
+vectorstore_persisted = Chroma(
+    collection_name=tesla_10k_collection,
+    persist_directory='./tesla_db',
+    embedding_function=embedding_model
 )
 
-retriever = vectorstore.as_retriever(
+retriever = vectorstore__persisted.as_retriever(
     search_type='similarity',
     search_kwargs={'k': 5}
 )