Update app.py

app.py

@@ -10,7 +10,7 @@ import unicodedata
 from typing import TypedDict, Annotated, Any, List, Optional
  
 from huggingface_hub import InferenceClient
-from openai import OpenAI
+ 
 from langchain_core.messages import AnyMessage, HumanMessage, SystemMessage, AIMessage, ToolMessage
 from langchain_core.tools import tool
 from langchain_community.tools import DuckDuckGoSearchRun
@@ -148,11 +148,11 @@ class BasicAgent:
         self.tools_by_name = {t.name: t for t in self.tools_list}
  
         # InferenceClient diretto — usa la Serverless Inference API HF
-        client = OpenAI(
-            api_key=os.getenv("GROQ_API_KEY"),
-            base_url="https://api.groq.com/openai/v1"
+        self.client = InferenceClient(
+            api_key=os.getenv("HF_TOKEN"),
         )
-                # Schema OpenAI dei tool per passarli al client
+         
+        # Schema OpenAI dei tool per passarli al client
         self.tools_schema = [_tool_to_openai_schema(t) for t in self.tools_list]
  
         # Grafo LangGraph per gestire il loop ReAct
@@ -203,9 +203,13 @@ class BasicAgent:
         sys_msg = SystemMessage(content=SYSTEM_PROMPT)
         hf_messages = self._messages_to_hf_format([sys_msg] + state["messages"])
  
-        response = self.client.chat.completions.create(
-            model="llama-3.3-70b-versatile",
+        response = self.client.chat_completion(
+            model="Qwen/Qwen2.5-7B-Instruct",            
             messages=hf_messages,
+            tools=self.tools_schema,
+            tool_choice="auto",
+            max_tokens=512,
+            temperature=0,
         )
  
         choice = response.choices[0].message