Update backend/query_llm.py

backend/query_llm.py

@@ -8,7 +8,7 @@ from typing import Any, Dict, Generator, List
 
 from huggingface_hub import InferenceClient
 from transformers import AutoTokenizer
-
+from gradio_client import Client
 #tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
 tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
 #tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
@@ -24,7 +24,7 @@ HF_TOKEN = getenv("HUGGING_FACE_HUB_TOKEN")
 #        token=HF_TOKEN
 #        )
 
-
+client = Client("Qwen/Qwen1.5-110B-Chat-demo")
 hf_client = InferenceClient(
         "mistralai/Mixtral-8x7B-Instruct-v0.1",
         token=HF_TOKEN
@@ -105,6 +105,17 @@ def generate_hf(prompt: str, history: str, temperature: float = 0.5, max_new_tok
             gr.Warning("Unfortunately Mistral is unable to process")
             return "I do not know what happened, but I couldn't understand you."
 
+def generate_qwen(formatted_prompt: str, history: str):
+    response = client.predict(
+                    query=formatted_prompt,
+                    history=history,
+                    system="You are a helpful assistant.", 
+                    api_name="/model_chat"
+                )
+    print(response)
+    return response
+    
+    
 
 def generate_openai(prompt: str, history: str, temperature: float = 0.9, max_new_tokens: int = 256,
              top_p: float = 0.95, repetition_penalty: float = 1.0) -> Generator[str, None, str]: