Files Updated

.gitignore

@@ -1,2 +1,4 @@
 venv/
-data/*
+data/*
+app2.py
+app3.py

app.py

@@ -1,4 +1,3 @@
-import copy
 import streamlit as st
 from llama_index import VectorStoreIndex
 from llama_index import ServiceContext
@@ -9,12 +8,13 @@ from PyPDF2 import PdfReader
 
 # Streamlit title and description
 st.title("PDF querying using Llama-Index by Rahul Bhoyar")
-st.write("Base Model : **HuggingFaceH4/zephyr-7b-alpha (open-source from HuggineFace)**")
-st.write("Embedding Model : **WhereIsAI/UAE-Large-V1(open-source from HuggineFace)**")
-st.write("This app allows you to upload your own Pdf and query your document.")
+st.write("Base Model: **HuggingFaceH4/zephyr-7b-alpha (open-source from HuggingFace)**")
+st.write("Embedding Model: **WhereIsAI/UAE-Large-V1 (open-source from HuggingFace)**")
+st.write("This app allows you to upload your own PDF and query your document.")
 
 hf_token = st.text_input("Enter your Hugging Face token:")
 
+
 def read_pdf(uploaded_file):
     pdf_reader = PdfReader(uploaded_file)
     text = ""
@@ -22,6 +22,7 @@ def read_pdf(uploaded_file):
         text += pdf_reader.pages[page_num].extract_text()
     return text
 
+
 # Streamlit input for user file upload
 success = False
 query_engine_creation = False
@@ -34,12 +35,11 @@ if uploaded_pdf is not None:
     documents = [documents]
     st.success("Documents loaded successfully!")
     
-    
+    model = st.selectbox('Select the model', ('google/flan-t5-xxl','HuggingFaceH4/zephyr-7b-alpha'), index=0)
+    llm = HuggingFaceInferenceAPI(model_name=model, token=hf_token)
+
     with st.spinner('Creating Vector Embeddings...'):
-        llm = HuggingFaceInferenceAPI(model_name="HuggingFaceH4/zephyr-7b-alpha", token=hf_token)
         embed_model_uae = HuggingFaceEmbedding(model_name="WhereIsAI/UAE-Large-V1")
-
-
         service_context = ServiceContext.from_defaults(
             llm=llm, chunk_size=800, chunk_overlap=20, embed_model=embed_model_uae
         )
@@ -50,19 +50,10 @@ if uploaded_pdf is not None:
         # Display the result of the task
     st.success("Vector embeddings created.")
     success = True
-    # # Streamlit input for user query
-    # user_query = st.text_input("Enter your query:")
-
-    # # Query engine with user input
-    # if user_query:
-    #     with st.spinner('Fetching the response...'):
-    #         response = query_engine.query(user_query)
-            
-    #     st.markdown(f"**Response:** {response}")
 else:
     st.write("Please upload a file first.")
- 
-if query_engine_creation:   
+
+if query_engine_creation:
     QUERY_ENGINE = query_engine
 
     # Streamlit input for user query
@@ -73,8 +64,5 @@ if query_engine_creation:
         if user_query:
             with st.spinner('Fetching the response...'):
                 response = QUERY_ENGINE.query(user_query)
-                
-            st.markdown(f"**Response:** {response}")
 
-
-    
+            st.markdown(f"**Response:** {response}")