Update app.py

app.py

@@ -20,6 +20,9 @@ from langchain_huggingface.llms import HuggingFacePipeline
 from langchain_cerebras import ChatCerebras
 from queue import Queue
 from threading import Thread
+from langchain.chains import LLMChain
+from langchain_core.prompts import PromptTemplate
+from langchain_huggingface import HuggingFaceEndpoint
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -98,10 +101,21 @@ retriever = db.as_retriever(
     search_kwargs={"k": 5}
 )
 
-llm = ChatCerebras(
-    model="llama-3.3-70b",
-    api_key=C_apikey,
-    streaming=True
+# llm = ChatCerebras(
+#     model="llama-3.3-70b",
+#     api_key=C_apikey,
+#     streaming=True
+# )
+
+repo_id = "Qwen/QwQ-32B-Preview"
+
+llm = HuggingFaceEndpoint(
+    repo_id=repo_id,
+    max_length=8192,
+    temperature=0.2,
+    huggingfacehub_api_token=HF_TOKEN,
+    streaming=True,
+    
 )
 
 template = """