Update model

app.py

@@ -12,7 +12,7 @@ index = pc.Index("medicine")
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
 
 embedding_model = SentenceTransformer(
     "nomic-ai/nomic-embed-text-v1", trust_remote_code=True
@@ -55,7 +55,7 @@ def respond(
     messages.append({"role": "user", "content": retrieved_data})
 
     response = ""
-
+    print("Completion request")
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,