Remove persist directory

app.py

@@ -34,13 +34,34 @@ async def on_chat_start():
         [
             Select(
                 id="Model",
-                label="Open Source Model",
+                label="Choose your favorite LLM:",
                 values=["llama3-8b-8192", "llama3-70b-8192", "mixtral-8x7b-32768", "gemma-7b-it"],
                 initial_index=0,
             )
         ]
     ).send()
 
+    await setup_agent(settings)
+    
+
+@cl.on_settings_update
+async def setup_agent(settings):
+
+    user_env = cl.user_session.get("env")
+    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")
+
+    # embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    # embeddings = SentenceTransformerEmbeddings(model_name = "sentence-transformers/all-MiniLM-L6-v2")
+    # memory=get_memory()
+    
+    # docsearch = await cl.make_async(Chroma)(
+    #     persist_directory="./chroma_db",
+    #     embedding_function=embeddings
+    # )
+
+    msg = cl.Message(content = f"You are using '{settings['Model']}' as LLM.")
+    await msg.send()
+
     files = None #Initialize variable to store uploaded files
 
     # Wait for the user to upload a file
@@ -77,32 +98,14 @@ async def on_chat_start():
     embeddings = SentenceTransformerEmbeddings(model_name = "sentence-transformers/all-MiniLM-L6-v2")
     #embeddings = OllamaEmbeddings(model="llama2:7b")
     docsearch = await cl.make_async(Chroma.from_texts)(
-        texts, embeddings, metadatas=metadatas, persist_directory='./chroma_db'
+        texts, embeddings, metadatas=metadatas
     )
-    docsearch.persist()
 
     # Let the user know that the system is ready
     msg.content = f"Processing `{file.name}` done. You can now ask questions!"
     await msg.update()
 
-    await setup_agent(settings)
-    
-
-@cl.on_settings_update
-async def setup_agent(settings):
-    print("Setup agent with settings:", settings)
-
-    user_env = cl.user_session.get("env")
-    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")
-
-    # embeddings = OllamaEmbeddings(model="nomic-embed-text")
-    embeddings = SentenceTransformerEmbeddings(model_name = "sentence-transformers/all-MiniLM-L6-v2")
     memory=get_memory()
-    
-    docsearch = await cl.make_async(Chroma)(
-        persist_directory="./chroma_db",
-        embedding_function=embeddings
-    )
 
 
     # Create a chain that uses the Chroma vector store