Create app.py

app.py

@@ -0,0 +1,108 @@
+import streamlit as st
+from langchain.prompts import PromptTemplate
+from langchain.chains.question_answering import load_qa_chain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain_community.vectorstores.faiss import FAISS
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
+from dotenv import load_dotenv
+import PyPDF2
+import os
+import io
+
+# st.title("Chat Your PDFs")  # Updated title
+st.set_page_config(layout="centered")
+st.markdown("<h1 style='font-size:24px;'>RAG with LangChain & GenAI: Any PDF</h1>", unsafe_allow_html=True)
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Retrieve API key from environment variable
+google_api_key = os.getenv("GOOGLE_API_KEY")
+
+# Check if the API key is available
+if google_api_key is None:
+    st.warning("API key not found. Please set the google_api_key environment variable.")
+    st.stop()
+
+# File Upload with user-defined name
+uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
+
+prompt_template = """
+Answer the question as detailed as possible from the provided context,
+make sure to provide all the details, if the answer is not in
+provided context just say, "answer is not available in the context",
+don't provide the wrong answer\n\n
+Context:\n {context}?\n
+Question: \n{question}\n
+Answer:
+"""
+
+# Additional prompts to enhance the template
+prompt_template = prompt_template + """
+--------------------------------------------------
+Prompt Suggestions:
+1. Summarize the main idea of the context.
+2. Provide a detailed explanation of the key concepts mentioned in the context.
+3. Identify any supporting evidence or examples that can be used to answer the question.
+4. Analyze any trends or patterns mentioned in the context that are relevant to the question.
+5. Compare and contrast different aspects or viewpoints presented in the context.
+6. Discuss any implications or consequences of the information provided in the context.
+7. Evaluate the reliability or credibility of the information presented in the context.
+8. Offer recommendations or suggestions based on the information provided.
+9. Predict potential future developments or outcomes based on the context.
+10. Provide additional context or background information relevant to the question.
+11. Explain any technical terms or jargon used in the context.
+12. Interpret any charts, graphs, or visual aids included in the context.
+13. Discuss any limitations or caveats that should be considered when answering the question.
+14. Address any potential biases or assumptions present in the context.
+15. Offer alternative perspectives or interpretations of the information provided.
+16. Discuss any ethical considerations or implications raised by the context.
+17. Analyze any cause-and-effect relationships mentioned in the context.
+18. Identify any unanswered questions or areas for further investigation.
+19. Clarify any ambiguities or inconsistencies in the context.
+20. Provide examples or case studies that illustrate the concepts discussed in the context.
+"""
+
+# Return the enhanced prompt template
+prompt_template = prompt_template + """
+--------------------------------------------------
+Context:\n{context}\n
+Question:\n{question}\n
+Answer:
+"""
+
+if uploaded_file is not None:
+    st.text("PDF File Uploaded Successfully!")
+
+    # PDF Processing (using PyPDF2 directly)
+    pdf_data = uploaded_file.read()
+    pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_data))
+    pdf_pages = pdf_reader.pages
+
+    context = "\n\n".join(page.extract_text() for page in pdf_pages)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=200)
+    texts = text_splitter.split_text(context)
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    # vector_index = Chroma.from_texts(texts, embeddings).as_retriever()
+    vector_index = FAISS.from_texts(texts, embeddings).as_retriever()
+
+    user_question = st.text_input("Enter your Question below:", "")
+
+
+
+    if st.button("Get Answer"):
+        if user_question:
+            with st.spinner("Processing..."):
+                # Get Relevant Documents
+                docs = vector_index.get_relevant_documents(user_question)
+                prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question'])
+                model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, api_key=google_api_key)
+                chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+                response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+                st.subheader("Answer:")
+                st.write(response['output_text'])
+
+        else:
+            st.warning("Please enter a question.")
+