Update app.py

app.py

@@ -1,10 +1,12 @@
 from langchain.prompts import PromptTemplate
 from langchain_core.output_parsers import JsonOutputParser, StrOutputParser
 from langchain_community.chat_models import ChatOllama
+from langchain_community.llms import HuggingFacePipeline
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 from langchain_core.tools import Tool
 from langchain_google_community import GoogleSearchAPIWrapper
 from firecrawl import FirecrawlApp
+from transformers import pipeline
 
 import gradio as gr
 import os
@@ -21,14 +23,17 @@ os.environ["GOOGLE_CSE_ID"] = os.getenv('GOOGLE_CSE_ID')
 os.environ["GOOGLE_API_KEY"] = os.getenv('GOOGLE_API_KEY')
 
 # Llama Endpoint
-llm = HuggingFaceEndpoint(
-    # endpoint_url = os.getenv('HF_ENDPOINT'),
-    repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct",
-    task="text-generation",
-    max_new_tokens=4000,
-    do_sample=False,
-    repetition_penalty=1.03
-    )
+# llm = HuggingFaceEndpoint(
+#     # endpoint_url = os.getenv('HF_ENDPOINT'),
+#     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")
+llm = HuggingFacePipeline(pipeline=pipe)
 
 llama3 = ChatHuggingFace(llm=llm, temperature = 1)
 llama3_json = ChatHuggingFace(llm=llm, format = 'json', temperature = 0)