Upload 3 files

.env

@@ -0,0 +1 @@
+OPENAI_API_KEY=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

app4.py

@@ -0,0 +1,165 @@
+import streamlit as st
+from llama_index.core import VectorStoreIndex, Document
+from llama_index.llms.openai import OpenAI
+from llama_index.core import Settings
+import os
+import pdfplumber
+from docx import Document as DocxDocument
+from dotenv import load_dotenv
+import json
+
+# Load environment variables from .env file
+load_dotenv()
+
+st.header("Chat with the Streamlit docs 💬 📚")
+
+# Sidebar for OpenAI API Key
+if 'openai_api_key' not in st.session_state:
+    st.session_state.openai_api_key = ""
+
+# Input for OpenAI API Key
+st.session_state.openai_api_key = st.sidebar.text_input("Enter your OpenAI API Key:", 
+                                                         type="password", 
+                                                         value=st.session_state.openai_api_key)
+
+# Initialize session state for messages
+if "messages" not in st.session_state:
+    st.session_state.messages = [
+        {"role": "assistant", "content": "Ask me a question about the documents you uploaded!"}
+    ]
+
+# Function to read PDF files
+def read_pdf(file):
+    with pdfplumber.open(file) as pdf:
+        text = ''
+        for page in pdf.pages:
+            text += page.extract_text() + '\n'
+    return text
+
+# Function to read DOCX files
+def read_docx(file):
+    doc = DocxDocument(file)
+    text = ''
+    for paragraph in doc.paragraphs:
+        text += paragraph.text + '\n'
+    return text
+
+@st.cache_resource(show_spinner=False)
+def load_data(uploaded_files):
+    with st.spinner("Loading and indexing the documents – hang tight! This should take 1-2 minutes."):
+        docs = []
+        for uploaded_file in uploaded_files:
+            if uploaded_file.type == "application/pdf":
+                text = read_pdf(uploaded_file)
+                docs.append(Document(text=text))
+            elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+                text = read_docx(uploaded_file)
+                docs.append(Document(text=text))
+
+        Settings.llm = OpenAI(model="gpt-3.5-turbo", temperature=0.5, 
+                              system_prompt="You are an expert on the Streamlit Python library and your job is to answer technical questions. Assume that all questions are related to the Streamlit Python library. Keep your answers technical and based on facts – do not hallucinate features.")
+        
+        index = VectorStoreIndex.from_documents(docs, settings=Settings.llm)
+        return index
+
+# Function to save the conversation
+def save_conversation():
+    with open("conversations.json", "a") as f:
+        json.dump(st.session_state.messages, f)
+        f.write("\n")
+
+# Function to load previous conversations
+def load_conversations():
+    if os.path.exists("conversations.json"):
+        with open("conversations.json", "r") as f:
+            conversations = [json.loads(line) for line in f]
+        return conversations
+    return []
+
+# Function to delete selected conversations
+def delete_selected_conversations(selected_indices):
+    conversations = load_conversations()
+    remaining_conversations = [conv for i, conv in enumerate(conversations) if i not in selected_indices]
+    with open("conversations.json", "w") as f:
+        for conv in remaining_conversations:
+            json.dump(conv, f)
+            f.write("\n")
+
+# File uploader for multiple PDF and DOCX files
+uploaded_files = st.file_uploader("Upload PDF or DOCX files", type=["pdf", "docx"], accept_multiple_files=True)
+
+if uploaded_files and st.session_state.openai_api_key:
+    index = load_data(uploaded_files)
+    chat_engine = index.as_chat_engine(chat_mode="condense_question", verbose=True)
+
+    # User input for questions
+    if prompt := st.chat_input("Your question"):
+        st.session_state.messages.append({"role": "user", "content": prompt})
+
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.write(message["content"])
+
+    if len(st.session_state.messages) > 0 and st.session_state.messages[-1]["role"] != "assistant":
+        with st.chat_message("assistant"):
+            with st.spinner("Thinking..."):
+                response = chat_engine.chat(prompt)
+                st.write(response.response)
+                message = {"role": "assistant", "content": response.response}
+                st.session_state.messages.append(message)
+
+    if st.button("Save Conversation"):
+        if st.session_state.messages:
+            st.session_state.confirm_save = True
+
+    if st.session_state.get('confirm_save', False):
+        st.warning("Do you want to save the conversation?")
+        col1, col2 = st.columns(2)
+        with col1:
+            if st.button("Yes"):
+                save_conversation()
+                st.success("Conversation saved!")
+                st.session_state.confirm_save = False
+        with col2:
+            if st.button("No"):
+                st.session_state.confirm_save = False
+
+    if st.button("End Conversation"):
+        st.session_state.messages = []
+        st.success("Conversation ended. You can start a new one!")
+
+else:
+    st.sidebar.warning("Please enter your OpenAI API key and upload PDF or DOCX files to proceed.")
+
+# Sidebar to toggle visibility of previous conversations
+if 'show_conversations' not in st.session_state:
+    st.session_state.show_conversations = False
+
+if st.sidebar.button("Toggle Previous Conversations"):
+    st.session_state.show_conversations = not st.session_state.show_conversations
+
+# Show previous conversations if the toggle is enabled
+if st.session_state.show_conversations:
+    st.sidebar.subheader("Previous Conversations")
+    conversations = load_conversations()
+
+    if conversations:
+        selected_indices = []
+        for i, conv in enumerate(conversations):
+            st.sidebar.write(f"Conversation {i + 1}:")
+            for message in conv:
+                st.sidebar.write(f"{message['role']}: {message['content']}")
+            # Checkbox for selecting conversation to delete
+            if st.sidebar.checkbox(f"Select Conversation {i + 1} for Deletion", key=f"delete_checkbox_{i}"):
+                selected_indices.append(i)
+
+        if st.sidebar.button("Delete Selected Conversations"):
+            if selected_indices:
+                delete_selected_conversations(selected_indices)
+                st.success("Selected conversations deleted. Please Refresh to See the Effect!")
+                st.session_state.messages = []  # Optional: reset messages for a fresh start
+
+    else:
+        st.sidebar.write("No previous conversations found.")
+else:
+    st.sidebar.write("Previous conversations are hidden. Click 'Toggle Previous Conversations' to show.")

conversations.json

@@ -0,0 +1 @@
+[{"role": "assistant", "content": "Ask me a question about Streamlit's open-source Python library!"}, {"role": "user", "content": "Pubface: Celebrity face identification based on deep learning\n\nexplain what this paper is about"}, {"role": "assistant", "content": "The paper \"Pubface: Celebrity face identification based on deep learning\" describes a real-time application called PubFace that focuses on recognizing celebrities in public spaces. The application employs a new pose invariant face recognition deep neural network algorithm with a very low error rate. To achieve this, the authors built a novel dataset with over five million labeled faces, fine-tuned the deep convolutional neural network (CNN) VGG-16 architecture on this dataset, and deployed the model on a Raspberry Pi 3 using the OpenCV dnn module. The paper discusses the importance of facial recognition technology, the use of deep learning techniques for face recognition systems, and the challenges associated with collecting large face datasets for training purposes."}]