Create app.py

app.py

@@ -0,0 +1,99 @@
+# streamlit_app.py
+
+import streamlit as st
+import os
+import openai
+from langchain.vectorstores import Chroma
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain.prompts import PromptTemplate
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_openai import ChatOpenAI
+from langchain.callbacks import get_openai_callback
+
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+def process_pdf(file):
+    loader = PyPDFLoader(file)
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    splits = text_splitter.split_documents(documents)
+    return splits
+
+def create_vectorstore(splits):
+    embeddings = OpenAIEmbeddings()
+    vectorstore = Chroma.from_documents(splits, embeddings)
+    retriever = vectorstore.as_retriever()
+    return retriever
+
+def summarize_document(docs, llm):
+    prompt = """
+    Write a concise summary of the following:
+
+    {context}
+    """
+    chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=None)
+    with get_openai_callback() as cb:  
+      summary = chain.invoke({"context": docs})
+    return summary, cb
+
+def ask_question(query, retriever, llm):
+    prompt_template = PromptTemplate.from_template(
+        """
+        You are an assistant for question-answering tasks.
+        Use the following pieces of retrieved context to answer the question.
+        If you don't know the answer, just say that you don't know.
+        Use three sentences maximum and keep the answer concise.
+
+        {context}
+        Question: {question}
+        Answer:
+        """
+    )
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=retriever,
+        return_source_documents=True
+    )
+    with get_openai_callback() as cb:
+        result = qa_chain.invoke(query)
+        return result, cb
+
+st.title("Research Paper Summarization & Question Answering")
+st.write("Upload a research paper (PDF), summarize its content, or ask specific questions related to the document.")
+
+uploaded_file = st.file_uploader("Upload a PDF Document", type="pdf")
+
+if uploaded_file is not None:
+    with st.spinner("Processing the document..."):
+        docs = process_pdf(uploaded_file)
+        st.success("Document processed successfully!")
+
+    llm = ChatOpenAI(model_name="gpt-4o-mini")
+
+    if st.button("Summarize Document"):
+        with st.spinner("Summarizing the document..."):
+            summary, cb = summarize_document(docs, llm)
+            st.subheader("Summary:")
+            st.write(summary)
+            st.write(f"Tokens Used: {cb.total_tokens}, Total Cost (USD): ${cb.total_cost:.5f}")
+
+    query = st.text_input("Ask a question related to the document:")
+    if st.button("Get Answer"):
+        with st.spinner("Retrieving the answer..."):
+            retriever = create_vectorstore(docs)
+            answer, cb = ask_question(query, retriever, llm)
+            st.subheader("Answer:")
+            st.write(answer)
+            st.write(f"Tokens Used: {cb.total_tokens}, Total Cost (USD): ${cb.total_cost:.5f}")
+
+st.sidebar.title("Instructions")
+st.sidebar.write("""
+1. Upload a research paper in PDF format.
+2. Choose to either summarize the entire document or ask a specific question about its content.
+3. For summarization, click the 'Summarize Document' button.
+4. For Q&A, type your question in the input box and click 'Get Answer'.
+5. Wait a few seconds for the response.
+""")