Update app_streamlit.py

app_streamlit.py

@@ -8,6 +8,7 @@ from langchain.vectorstores import Chroma
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_groq import ChatGroq
 from langchain.chains import RetrievalQA
+import zipfile
 
 # Load the .env file (if using it)
 load_dotenv()
@@ -16,6 +17,21 @@ groq_api_key = os.getenv("GROQ_API_KEY")
 # Load embeddings, model, and vector store
 @st.cache_resource  # Singleton, prevent multiple initializations
 def init_chain():
+    
+    # Specify the path to the .zip file
+    zip_file_path = "cspc_db.zip"
+    
+    # Specify the directory where you want to extract the files
+    extract_to_path = "cspc_db"
+    
+    # Check if the destination directory exists, and if not, create it
+    if not os.path.exists(extract_to_path):
+        os.makedirs(extract_to_path)
+    
+    # Unzip the file
+    with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
+        zip_ref.extractall(extract_to_path)
+    
     model_kwargs = {'trust_remote_code': True}
     embedding = HuggingFaceEmbeddings(model_name='nomic-ai/nomic-embed-text-v1.5', model_kwargs=model_kwargs)
     llm = ChatGroq(groq_api_key=groq_api_key, model_name="llama3-70b-8192", temperature=0.2)