pdfreader written & feature for reading started

app.py

@@ -1,14 +1,32 @@
 import openai
 import streamlit as st
 import pandas as pd
+import PyPDF2
+
+def pdf_reader(file):
+    """Reads text from a PDF file"""
+    try:
+        # Read the uploaded file using PyPDF2
+        pdf = PyPDF2.PdfReader(file)
+        text = ''
+        for page in range(len(pdf.pages)):
+            text += pdf.pages[page].extract_text()
+
+        return text
+    except Exception as e:
+        # Handle any exceptions that may occur
+        print("Error reading PDF file:", e)
+        return None
+
+
 
 # Setting page title and header
 st.set_page_config(page_icon=":bulb:", page_title="WAAM-GPT")
 st.markdown("<div style='text-align: center;'><h1 style='display: inline-block;'> 💡WAAM-GPT</h1><h5 style='display: inline-block; margin-left: 10px; color: gray;'>homework help</h5></div>", unsafe_allow_html=True)
 
 # Set org ID and API key
-openai.organization = st.secrets["openai_org"]
-openai.api_key = st.secrets["openai_key"]
+openai.organization = "empty"
+openai.api_key = "empty"
 
 system_prompt = "You are a waam, a helpful large language model STEM tutor created during the 2023 5C Hackathon. You help users learn quantitative skills by guiding them through concepts and practice problems step by step instead of immediately giving away the final answer. Never give a student the direct answer. Always use markdown for your responses. Always render equations using LaTeX."
 
@@ -81,6 +99,7 @@
 def generate_response(prompt):
     st.session_state['messages'].append({"role": "user", "content": prompt})
 
+
     completion = openai.ChatCompletion.create(
         model=model,
         messages=st.session_state['messages']
@@ -108,7 +127,15 @@ def generate_response(prompt):
         user_input = st.text_area("", placeholder="What do you want to learn today?", key='input', height=10)
         submit_button = st.form_submit_button(label= '⏩')
 
+    # create a file uploader for PDFs
+        pdf_file = st.file_uploader("Upload a PDF file", type="pdf")
+
+        # if a PDF file is uploaded, extract its text
+        if pdf_file is not None:
+            user_input = pdf_reader(pdf_file)
+
     if submit_button and user_input:
+
         output, total_tokens, prompt_tokens, completion_tokens = generate_response(user_input)
         st.session_state['past'].append(user_input)
         st.session_state['generated'].append(output)

pdfreader.py

@@ -0,0 +1,16 @@
+
+
+def pdf_reader(myPdf):
+    from langchain.document_loaders import PyPDFLoader
+
+    loader = PyPDFLoader(myPDF)
+    pages = loader.load_and_split()
+    pages[0]
+
+    from langchain.vectorstores import FAISS
+    from langchain.embeddings.openai import OpenAIEmbeddings
+
+    faiss_index = FAISS.from_documents(pages, OpenAIEmbeddings())
+    docs = faiss_index.similarity_search("How will the community be engaged?", k=2)
+    for doc in docs:
+        print(str(doc.metadata["page"]) + ":", doc.page_content)