Add PDF chatbot application

.gitignore

@@ -0,0 +1,5 @@
+.venv/
+.env
+__pycache__/
+*.pyc
+.vscode/

app.py

@@ -1,69 +1,220 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-import streamlit as st
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import os
+import streamlit as st  # type: ignore
+
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+
+from langchain_classic.text_splitter import RecursiveCharacterTextSplitter
+from langchain_cohere import CohereEmbeddings, ChatCohere
+from langchain_community.vectorstores import FAISS
+from langchain_classic.chains import ConversationalRetrievalChain
+from langchain_classic.memory import ConversationBufferMemory
+
+load_dotenv()
+
+st.set_page_config(
+    page_title="Chat with Documents",
+    page_icon="📚"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+
+def get_pdf_text(pdf_docs):
+    text = ""
+
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+
+        for page in pdf_reader.pages:
+            text += page.extract_text() or ""
+
+    return text
+
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(
+        separators=["\n\n", "\n", " ", ""],
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+
+    return text_splitter.split_text(text)
+
+
+def get_embeddings():
+    return CohereEmbeddings(
+        model='embed-english-v3.0',
+        user_agent="langchain"
+    )
+
+
+def get_conversational_chain(vectorstore):
+    llm = ChatCohere(
+        model="command-r-08-2024",
+        temperature=0
+    )
+
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        return_messages=True,
+        output_key="answer"
+    )
+
+    conversational_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory,
+        return_source_documents=True
+    )
+
+    return conversational_chain
+
+
+def handle_userinput(user_question):
+    response = st.session_state.conversational_chain.invoke(
+        {"question": user_question}
+    )
+
+    answer = response["answer"]
+
+    st.session_state.chat_history = (
+        st.session_state.conversational_chain.memory
+        .load_memory_variables({})["chat_history"]
+    )
+
+    for i, message in enumerate(st.session_state.chat_history):
+        if message.type == "human":
+            with st.chat_message("user"):
+                st.write(message.content)
+        else:
+            with st.chat_message("assistant"):
+                st.write(message.content)
+
+
+def main():
+    st.markdown(
+        """
+        <style>
+        .main {
+            background: linear-gradient(135deg, #f8fbff 0%, #eef5ff 100%);
+        }
+        .block-container {
+            padding-top: 2rem;
+            padding-bottom: 2rem;
+        }
+        .hero {
+            background: linear-gradient(135deg, #0f172a 0%, #1d4ed8 100%);
+            padding: 2rem 2rem;
+            border-radius: 22px;
+            box-shadow: 0 12px 30px rgba(29, 78, 216, 0.18);
+            margin-bottom: 1.5rem;
+            margin-top: 1.5rem;
+        }
+        .hero h1 {
+            color: white !important;
+            font-size: 2.5rem !important;
+            font-weight: 800 !important;
+            margin: 0 !important;
+        }
+        .hero p {
+            color: #dbeafe !important;
+            font-size: 1.05rem !important;
+            margin-top: 0.5rem !important;
+            margin-bottom: 0 !important;
+        }
+        </style>
+        """,
+        unsafe_allow_html=True,
+    )
+
+    st.markdown(
+        """
+        <div class="hero">
+            <h1> AI Chatbot for Your Documents</h1>
+            <p>Upload a PDF and ask questions in natural language.</p>
+        </div>
+        """,
+        unsafe_allow_html=True,
+    )
+
+    if "conversational_chain" not in st.session_state:
+        st.session_state.conversational_chain = None
+
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = []
+
+    with st.sidebar:
+        st.header("Upload Documents")
+
+        pdf_docs = st.file_uploader(
+            "Upload your PDF files",
+            type=["pdf"],
+            accept_multiple_files=True
+        )
+
+        if st.button("Process Documents"):
+            if not pdf_docs:
+                st.warning("Please upload at least one PDF.")
+            elif not os.getenv("COHERE_API_KEY"):
+                st.error("Cohere API key is missing.")
+            else:
+                try:
+                    with st.spinner("Processing documents..."):
+                        raw_text = get_pdf_text(pdf_docs)
+
+                        if not raw_text.strip():
+                            st.error("No extractable text found in the PDFs.")
+                            return
+
+                        chunks = get_text_chunks(raw_text)
+
+                        embeddings = get_embeddings()
+
+                        vectorstore = FAISS.from_texts(
+                            texts=chunks,
+                            embedding=embeddings
+                        )
+
+                        st.session_state.conversational_chain = (
+                            get_conversational_chain(vectorstore)
+                        )
+
+                        st.session_state.chat_history = []
+
+                    st.success("Documents processed successfully!")
+
+                except Exception as e:
+                    st.error(f"Error processing documents: {e}")
+
+    user_question = st.chat_input("Ask a question about your PDFs")
+
+    if user_question:
+        if st.session_state.conversational_chain is None:
+            st.warning("Please upload and process your documents first.")
+        else:
+            with st.chat_message("user"):
+                st.write(user_question)
+
+            with st.chat_message("assistant"):
+                with st.spinner("Thinking..."):
+                    try:
+                        response = (
+                            st.session_state.conversational_chain.invoke(
+                                {"question": user_question}
+                            )
+                        )
+                        st.write(response["answer"])
+
+                        st.session_state.chat_history = (
+                            st.session_state.conversational_chain
+                            .memory.load_memory_variables(
+                                {}
+                            )["chat_history"]
+                        )
+
+                    except Exception as e:
+                        st.error(f"Error generating answer: {e}")
 
 
 if __name__ == "__main__":
-    demo.launch()
+    main()

requirements.txt

@@ -0,0 +1,10 @@
+streamlit
+gradio
+python-dotenv
+PyPDF2
+langchain
+langchain-community
+langchain-cohere
+langchain-classic
+langchain-text-splitters
+faiss-cpu