Update app.py

app.py

@@ -1,30 +1,33 @@
 import streamlit as st
-from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
+from llama_index import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
 from llama_index.llms.huggingface import HuggingFaceInferenceAPI
 from dotenv import load_dotenv
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.core import Settings
+from llama_index import set_global_service_context
 import os
 import base64
 
 # Load environment variables
 load_dotenv()
 
-# Configure the Llama index settings for using Hugging Face LLaMA model
-Settings.llm = HuggingFaceInferenceAPI(
-    model_name="facebook/bedrock-llama-7b",  # Use LLaMA 7B model here
-    tokenizer_name="facebook/bedrock-llama-7b",  # Tokenizer for the LLaMA model
-    context_window=30000,  # Set context window size (adjust if necessary)
+# Configure the Llama index settings for using Hugging Face model
+llm = HuggingFaceInferenceAPI(
+    model_name="bigscience/bloom-7b1",  # Use a model available on Hugging Face Inference API
+    tokenizer_name="bigscience/bloom-7b1",
+    context_window=2048,  # Adjust context window based on the model
     api_token=os.getenv("HF_TOKEN"),  # Hugging Face API Token
     max_new_tokens=512,
-    generate_kwargs={"temperature": 0.1},  # Control the generation temperature
+    generate_kwargs={"temperature": 0.1},
 )
 
-# Set up Hugging Face Embedding model to use powerful LLaMA model
-Settings.embed_model = HuggingFaceEmbedding(
-    model_name="facebook/bedrock-llama-7b"  # Powerful model for embeddings
+# Set up Hugging Face Embedding model
+embed_model = HuggingFaceEmbedding(
+    model_name="sentence-transformers/all-MiniLM-L6-v2"  # Use a suitable embedding model
 )
 
+# Set global service context
+service_context = set_global_service_context(llm=llm, embed_model=embed_model)
+
 # Define the directory for persistent storage and data
 PERSIST_DIR = "./db"
 DATA_DIR = "data"
@@ -41,13 +44,13 @@ def displayPDF(file):
 
 def data_ingestion():
     documents = SimpleDirectoryReader(DATA_DIR).load_data()
-    storage_context = StorageContext.from_defaults()
-    index = VectorStoreIndex.from_documents(documents)
-    index.storage_context.persist(persist_dir=PERSIST_DIR)
+    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
+    index = VectorStoreIndex.from_documents(documents, service_context=service_context)
+    index.storage_context.persist()
 
 def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
-    index = load_index_from_storage(storage_context)
+    index = load_index_from_storage(storage_context, service_context=service_context)
     chat_text_qa_msgs = [
         (
             "user",
@@ -94,4 +97,4 @@ if user_prompt:
 
 for message in st.session_state.messages:
     with st.chat_message(message['role']):
-        st.write(message['content'])
+        st.write(message['content'])