Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Kia_EV6.pdf filter=lfs diff=lfs merge=lfs -text

Kia_EV6.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363f7482ab9c73eae7a92ba6a45162e787ab9a57679656f150d3293108f20ffb
+size 8591101

PDF_Reader.py

@@ -0,0 +1,31 @@
+import PyPDF2
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceBgeEmbeddings
+from langchain.vectorstores import FAISS
+
+def read_pdf(uploaded_file):
+    pdf_reader = PyPDF2.PdfReader(uploaded_file)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+def Chunks(docs):
+    text_splitter = RecursiveCharacterTextSplitter(
+    # Set a really small chunk size, just to show.
+    chunk_size = 1000,
+    chunk_overlap  = 100,
+)
+    doc = text_splitter.split_text(docs)
+    return doc
+
+
+def PDF_4_QA(file):
+    content = read_pdf(file)
+    pdf_chunks = Chunks(docs=content)
+
+    embeddings = HuggingFaceBgeEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
+                                          model_kwargs={'device': 'cpu'})
+    vectorstore_openai = FAISS.from_texts(pdf_chunks, embeddings)
+
+    return vectorstore_openai

QA_Bot.py

@@ -0,0 +1,37 @@
+import streamlit as st
+from QnA import Q_A
+import re,time
+
+
+def QA_Bot(vectorstore):
+    st.title("Q&A Bot")
+    # Initialize chat history
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+    # Display chat messages from history on app rerun
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+    # React to user input
+    if prompt := st.chat_input("What is up?"):
+        # Display user message in chat message container
+        st.chat_message("user").markdown(prompt)
+        # Add user message to chat history
+        st.session_state.messages.append({"role": "user", "content": prompt})
+
+        ai_response = Q_A(vectorstore,prompt)
+        response = f"Echo: {ai_response}"
+        # Display assistant response in chat message container
+        with st.chat_message("assistant"):
+            message_placeholder = st.empty()
+            full_response = ""
+            for chunk in re.split(r'(\s+)', response):
+                full_response += chunk + " "
+                time.sleep(0.01)
+
+                # Add a blinking cursor to simulate typing
+                message_placeholder.markdown(full_response + "▌")
+        # Add assistant response to chat history
+        st.session_state.messages.append({"role": "assistant", "content": full_response})

QnA.py

@@ -0,0 +1,10 @@
+from langchain.chains import RetrievalQA
+from Api_Key import google_plam
+from langchain.llms import GooglePalm
+
+def Q_A(vectorstore,question):
+    google_llm = GooglePalm(google_api_key=google_plam, temperature=0.5)
+    qa = RetrievalQA.from_chain_type(llm=google_llm, chain_type="stuff", retriever=vectorstore.as_retriever())
+    answer = qa.run(question)
+
+    return answer

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+from QA_Bot import QA_Bot
+from PDF_Reader import PDF_4_QA
+from PIL import Image
+
+# Streamlit app
+def main():
+    # Page icon
+    icon = Image.open('td-logo.png')
+
+    # Page config
+    st.set_page_config(page_title="Q&A ChatBot",
+                       page_icon=icon,
+                       layout="wide"
+                       )
+
+    company_logo_path = 'td-logo.png'
+    st.sidebar.image(company_logo_path, width=50)
+    st.sidebar.title("Upload PDF")
+    st.sidebar.write("Download Demo PDF file from Below....")
+    with open("Kia_EV6.pdf", "rb") as file:
+        btn = st.sidebar.download_button(
+            label="Download PDF",
+            data=file,
+            file_name="Kia_EV6.pdf"
+        )
+
+    uploaded_file = st.sidebar.file_uploader("Choose a PDF file", type="pdf")
+    if uploaded_file is not None:
+        st.sidebar.success("File uploaded successfully.")
+        vector_store = PDF_4_QA(uploaded_file)
+        QA_Bot(vector_store)
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,9 @@
+langchain==0.0.339
+streamlit==1.29.0
+google-ai-generativelanguage==0.4.0
+google-generativeai==0.3.2
+google-cloud-aiplatform==1.38.1
+faiss-cpu==1.7.4
+tiktoken==0.5.2
+PyPDF2==3.0.1
+sentence-transformers==2.2.2