Update app.py

app.py

@@ -1,38 +1,34 @@
 import streamlit as st
-from llama_index import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
+from llama_index.core 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 import set_global_service_context
+from llama_index.core import Settings
 import os
 import base64
+import altair as alt
 
 # Load environment variables
 load_dotenv()
 
-# 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
+# Configure the Llama index settings
+Settings.llm = HuggingFaceInferenceAPI(
+    model_name="google/gemma-1.1-7b-it",
+    tokenizer_name="google/gemma-1.1-7b-it",
+    context_window=3000,
+    token=os.getenv("HF_TOKEN"),
     max_new_tokens=512,
     generate_kwargs={"temperature": 0.1},
 )
-
-# Set up Hugging Face Embedding model
-embed_model = HuggingFaceEmbedding(
-    model_name="sentence-transformers/all-MiniLM-L6-v2"  # Use a suitable embedding model
+Settings.embed_model = HuggingFaceEmbedding(
+    model_name="BAAI/bge-small-en-v1.5"
 )
 
-# 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"
 
-# Ensure data directories exist
+# Ensure data directory exists
 os.makedirs(DATA_DIR, exist_ok=True)
 os.makedirs(PERSIST_DIR, exist_ok=True)
 
@@ -44,50 +40,56 @@ def displayPDF(file):
 
 def data_ingestion():
     documents = SimpleDirectoryReader(DATA_DIR).load_data()
-    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
-    index = VectorStoreIndex.from_documents(documents, service_context=service_context)
-    index.storage_context.persist()
+    storage_context = StorageContext.from_defaults()
+    index = VectorStoreIndex.from_documents(documents)
+    index.storage_context.persist(persist_dir=PERSIST_DIR)
 
 def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
-    index = load_index_from_storage(storage_context, service_context=service_context)
+    index = load_index_from_storage(storage_context)
     chat_text_qa_msgs = [
-        (
-            "user",
-            """created by vivek created for Neonflake Enterprises OPC Pvt Ltd
-            Context:
-            {context}
-            Question:
-            {query}
-            """
-        )
+    (
+        "user",
+        """created by vivek created for Neonflake Enterprises OPC Pvt Ltd
+        Context:
+        {context_str}
+        Question:
+        {query_str}
+        """
+    )
     ]
     text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
+    
     query_engine = index.as_query_engine(text_qa_template=text_qa_template)
+    answer = query_engine.query(query)
     
-    try:
-        answer = query_engine.query({"context": "Extracted context from PDF", "query": query})
-        return answer.get('response', "Sorry, no answer found.")
-    except Exception as e:
-        return f"An error occurred: {str(e)}"
+    if hasattr(answer, 'response'):
+        return answer.response
+    elif isinstance(answer, dict) and 'response' in answer:
+        return answer['response']
+    else:
+        return "Sorry, I couldn't find an answer."
+
 
 # Streamlit app initialization
-st.title("Chat with your PDF 📄")
+st.title("Chat with your PDF📄")
 st.markdown("Built by [vivek](https://github.com/saravivek-cyber)")
+st.markdown("chat here")
 
 if 'messages' not in st.session_state:
     st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF and ask me anything about its content.'}]
 
 with st.sidebar:
     st.title("Menu:")
-    uploaded_file = st.file_uploader("Upload your PDF File")
-    if uploaded_file:
-        filepath = os.path.join(DATA_DIR, "saved_pdf.pdf")
-        with open(filepath, "wb") as f:
-            f.write(uploaded_file.getbuffer())
-        st.success("File uploaded successfully. Processing...")
-        data_ingestion()
-        st.success("Data ingestion completed.")
+    uploaded_file = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button")
+    if st.button("Submit & Process"):
+        with st.spinner("Processing..."):
+            filepath = "data/saved_pdf.pdf"
+            with open(filepath, "wb") as f:
+                f.write(uploaded_file.getbuffer())
+            # displayPDF(filepath)  # Display the uploaded PDF
+            data_ingestion()  # Process PDF every time new file is uploaded
+            st.success("Done")
 
 user_prompt = st.chat_input("Ask me anything about the content of the PDF:")
 if user_prompt: