Update app.py

app.py

@@ -1,6 +1,5 @@
 import streamlit as st
 from langchain_community.llms import HuggingFaceEndpoint
-from langchain.embeddings import HuggingFaceEmbeddings
 from langchain_core.runnables import RunnablePassthrough
 from langchain_core.output_parsers import StrOutputParser
 from langchain.prompts import ChatPromptTemplate
@@ -13,8 +12,13 @@ from langchain.prompts import PromptTemplate
 from langchain_community.document_loaders import PyPDFLoader
 from langchain_chroma import Chroma
 from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+# Load model directly
+from transformers import AutoModelForCausalLM
 
 
+access_token = os.getenv("HUGGINGFACE_API_KEY")
+
 
 
 #st.set_page_config(page_title="Document Genie", layout="wide")
@@ -63,7 +67,7 @@ def text_splitter(text):
 
 #GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
 #COHERE_API_KEY = os.getenv("COHERE_API_KEY")
-HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
+#HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
 
 def get_conversational_chain():
     prompt_template = """
@@ -82,10 +86,10 @@ def get_conversational_chain():
     #repo_id ='google/gemma-1.1-2b-it'
     #repo_id='meta-llama/Meta-Llama-3-70B'
     repo_id = 'microsoft/Phi-3-mini-4k-instruct'
-    llm = HuggingFaceEndpoint(repo_id=repo_id, max_length=512, temperature=0.3, token=HUGGINGFACE_API_KEY)
+    #llm = HuggingFaceEndpoint(repo_id=repo_id, max_length=512, temperature=0.3, token=HUGGINGFACE_API_KEY)
     #tokenizer = AutoTokenizer.from_pretrained("google/gemma-1.1-2b-it")
     #llm = AutoModelForCausalLM.from_pretrained("google/gemma-1.1-2b-it")
-
+    llm = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True, token=access_token)
     #llm = pipeline("text-generation", model="google/gemma-1.1-2b-it")
 
     pt = ChatPromptTemplate.from_template(prompt_template)