app.py

app.py

@@ -1,5 +1,6 @@
 import os
-from langchain_huggingface import HuggingFaceEndpoint
+from transformers import pipeline
+# from langchain_huggingface import HuggingFaceEndpoint
 import streamlit as st
 from langchain_core.prompts import PromptTemplate
 from langchain_core.output_parsers import StrOutputParser
@@ -18,12 +19,10 @@ def get_llm_hf_inference(model_id=model_id, max_new_tokens=128, temperature=0.1)
     Returns:
     - llm (HuggingFaceEndpoint): The language model for HuggingFace inference.
     """
-    llm = HuggingFaceEndpoint(
-        repo_id=model_id,
-        max_new_tokens=max_new_tokens,
-        temperature=temperature,
-        token = os.getenv("HF_TOKEN")
-    )
+    llm = pipeline('text-generation',
+                    model=model_id,
+                      tokenizer=model_id,
+                        use_auth_token=os.getenv("HF_TOKEN"))
     return llm
 
 # Configure the Streamlit app