commit

app.py

@@ -43,6 +43,7 @@ target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
 # MODEL_N_CTX=1000
 # TARGET_SOURCE_CHUNKS=4
 
+import psutil
 
 from constants import CHROMA_SETTINGS
 # embeddings_model_name = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
@@ -179,6 +180,13 @@ def predict(
     #     chatbot = [(history[i], history[i + 1]) for i in range(0, len(history), 2)]
     #     return chatbot, history
 
+def get_system_memory():
+    memory = psutil.virtual_memory()
+    memory_percent = memory.percent
+    memory_used = memory.used / (1024.0 ** 3)
+    memory_total = memory.total / (1024.0 ** 3)
+    return {"percent": f"{memory_percent}%", "used": f"{memory_used:.3f}GB", "total": f"{memory_total:.3f}GB"}
+
 def reset_textbox():
     return gr.update(value="")
 
@@ -249,7 +257,10 @@ with gr.Blocks(
                     submit_btn = gr.Button(value="🚀 Send")
                 with gr.Column():
                     clear_btn = gr.Button(value="🗑️ Clear history")
-                
+
+        with gr.Column():
+            gr.JSON(get_system_memory, every=1)
+
     question.submit(
         predict,
         # [question, system_content, embeddings_model_name, persist_directory, model_type, model_path, model_n_ctx, target_source_chunks, chatbot, state],
@@ -278,4 +289,4 @@ with gr.Blocks(
     #demo.launch(server_name=args.server_name, server_port=args.server_port, share=args.share, debug=args.debug)
     # demo.queue(concurrency_count=5).launch()
 
-demo.launch(debug=True)
+demo.queue().launch(debug=True)