Update app.py

app.py

@@ -1,6 +1,7 @@
 from langchain_community.vectorstores import Qdrant
-from langchain_groq import ChatGroq
 from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.llms import HuggingFacePipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import os
 from dotenv import load_dotenv
 from langchain.prompts import ChatPromptTemplate
@@ -13,8 +14,6 @@ import gradio as gr
 # Load environment variables
 load_dotenv()
 
-os.environ["GROQ_API_KEY"] = os.getenv("GROQ_API")
-
 # HuggingFace Embeddings
 embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-large-en-v1.5")
 
@@ -56,14 +55,14 @@ retriever = db.as_retriever(
     search_kwargs={"k": 5}
 )
 
-# LLM setup
-llm = ChatGroq(
-    model="llama-3.3-70b-versatile",
-    temperature=0.1,
-    max_tokens=None,
-    timeout=None,
-    max_retries=2,
-)
+# Load Hugging Face Model
+model_name = "meta-llama/Llama-2-7b-chat-hf"  # Replace with your desired model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)
+hf_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+# LangChain LLM using Hugging Face Pipeline
+llm = HuggingFacePipeline(pipeline=hf_pipeline)
 
 # Create prompt template
 template = """