Update app.py

app.py

@@ -23,16 +23,18 @@ os.environ["GOOGLE_CSE_ID"] = os.getenv('GOOGLE_CSE_ID')
 os.environ["GOOGLE_API_KEY"] = os.getenv('GOOGLE_API_KEY')
 
 # Llama Endpoint
-# llm = HuggingFaceEndpoint(
-#     repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct",
-#     task="text-generation",
-#     max_new_tokens=4000,
-#     do_sample=False,
-#     repetition_penalty=1.03
-#     )
-
-pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-8B-Instruct", token = os.getenv('HF_KEY'))
-llm = HuggingFacePipeline(pipeline=pipe)
+llm = HuggingFaceEndpoint(
+    repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct",
+    task="text-generation",
+    max_new_tokens = 4000,
+    max_length = 4000,
+    do_sample = False,
+    repetition_penalty = 1.03,
+    huggingfacehub_api_token = os.getenv('HF_KEY')
+    )
+
+# pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-8B-Instruct", token = os.getenv('HF_KEY'))
+# llm = HuggingFacePipeline(pipeline=pipe)
 
 llama3 = ChatHuggingFace(llm=llm, temperature = 1)
 llama3_json = ChatHuggingFace(llm=llm, format = 'json', temperature = 0)