Upload 2 files

app.py

@@ -0,0 +1,43 @@
+import os
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+
+# Set your OpenAI API key here
+os.environ["OPENAI_API_KEY"] = "sk-proj-Mb6oBgg51EUsImee2TMdT3BlbkFJjyQuPaCGgFNzYwt1c52m"
+
+st.title("PDF Question Answering")
+
+uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
+
+if uploaded_file is not None:
+    pdf_reader = PdfReader(uploaded_file)
+    
+    raw_text = ''
+    for i, page in enumerate(pdf_reader.pages):
+        text = page.extract_text()
+        if text:
+            raw_text += text
+    
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=600,
+        chunk_overlap=200,
+        length_function=len
+    )
+
+    texts = text_splitter.split_text(raw_text)
+    embeddings = OpenAIEmbeddings()
+    document_search = FAISS.from_texts(texts, embeddings)
+    
+    query = st.text_input("Enter your question:")
+
+    if st.button("Get Answer"):
+        docs = document_search.similarity_search(query)
+        chain = load_qa_chain(OpenAI(), chain_type="stuff")
+        answer = chain.run(input_documents=docs, question=query)
+        st.write("Answer:", answer)

requirements.txt

@@ -0,0 +1,7 @@
+openai
+langchain
+streamlit
+PyPDF2
+faiss-cpu
+tiktoken
+langchain-community