Update app.py

app.py

@@ -8,7 +8,6 @@ from huggingface_hub import Repository, InferenceClient
 
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 API_URL = "https://api-inference.huggingface.co/models/tiiuae/falcon-180B-chat"
-BOT_NAME = "Medic"
 
 STOP_SEQUENCES = ["\nUser:", "<|endoftext|>", " User:", "###"]
 
@@ -17,7 +16,7 @@ client = InferenceClient(
     headers={"Authorization": f"Bearer {HF_TOKEN}"},
 )
 
-def query(system_prompt, user_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
+def query(bot_name, system_prompt, user_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
     print(temperature, max_new_tokens, top_p, repetition_penalty)
     seed = 42
     generate_kwargs = dict(
@@ -29,10 +28,11 @@ def query(system_prompt, user_prompt, temperature=0.9, max_new_tokens=256, top_p
         do_sample=True,
         seed=seed,
     )
+    print(bot_name)
     print(system_prompt)
     print(user_prompt)
     print('-' * 20)
-    prompt = f"System: {system_prompt}\nUser: {user_prompt}\Medic:"
+    prompt = f"System: {system_prompt}\nUser: {user_prompt}\n{bot_name}: "
     stream = client.text_generation(prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
     for response in stream: