Spaces:
Sleeping
Sleeping
File size: 3,843 Bytes
47fd10e fd77339 47fd10e c586aa5 47fd10e fd77339 47fd10e b2a97bc 47fd10e c586aa5 47fd10e fd77339 feca159 fd77339 47fd10e c586aa5 47fd10e feca159 c586aa5 fd77339 feca159 fd77339 c586aa5 47fd10e feca159 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
import os
import requests
import streamlit as st
import PyMuPDF
# Get the Hugging Face API Token from environment variables
HF_API_TOKEN = os.getenv("HF_API_KEY")
if not HF_API_TOKEN:
raise ValueError("Hugging Face API Token is not set in the environment variables.")
# Hugging Face API URL and header for Gemma 27B-it model
GEMMA_27B_API_URL = "https://api-inference.huggingface.co/models/google/gemma-2-27b-it"
HEADERS = {"Authorization": f"Bearer {HF_API_TOKEN}"}
def query_model(api_url, payload):
response = requests.post(api_url, headers=HEADERS, json=payload)
return response.json()
def extract_pdf_text(uploaded_file):
pdf_text = ""
pdf_doc = PyMuPDF.open(uploaded_file)
for page_num in range(len(pdf_doc)):
pdf_text += pdf_doc.getPageText(page_num)
return pdf_text
def add_message_to_conversation(user_message, bot_message, model_name):
if "conversation" not in st.session_state:
st.session_state.conversation = []
st.session_state.conversation.append((user_message, bot_message, model_name))
# Streamlit app
st.set_page_config(page_title="Gemma 27B-it Chatbot Interface", layout="wide")
st.title("Gemma 27B-it Chatbot Interface")
st.write("Gemma 27B-it Chatbot Interface")
# Initialize session state for conversation and uploaded file
if "conversation" not in st.session_state:
st.session_state.conversation = []
if "uploaded_file" not in st.session_state:
st.session_state.uploaded_file = None
# File uploader for PDF
uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
# Handle PDF upload and text extraction
if uploaded_file:
pdf_text = extract_pdf_text(uploaded_file)
st.write("### PDF Text Extracted:")
st.write(pdf_text)
# User input for question
question = st.text_input("Question", placeholder="Enter your question here...")
# Handle user input and Gemma 27B-it model response
if st.button("Send") and question:
try:
with st.spinner("Waiting for the model to respond..."):
# Construct the chat history
chat_history = " ".join([msg[1] for msg in st.session_state.conversation[-5:]]) + f"User: {question}\n"
response = query_model(GEMMA_27B_API_URL, {"inputs": chat_history})
if isinstance(response, list):
answer = response[0].get("generated_text", "No response")
elif isinstance(response, dict):
answer = response.get("generated_text", "No response")
else:
answer = "No response"
# Add PDF text to the chat history
if st.session_state.uploaded_file:
chat_history += f"Document Text: {pdf_text}\n"
add_message_to_conversation(question, answer, "Gemma-2-27B-it")
except ValueError as e:
st.error(str(e))
# Custom CSS for chat bubbles
st.markdown(
"""
<style>
.chat-bubble {
padding: 10px 14px;
border-radius: 14px;
margin-bottom: 10px;
display: inline-block;
max-width: 80%;
color: black;
}
.chat-bubble.user {
background-color: #dcf8c6;
align-self: flex-end;
}
.chat-bubble.bot {
background-color: #fff;
align-self: flex-start;
}
.chat-container {
display: flex;
flex-direction: column;
gap: 10px;
margin-top: 20px;
}
</style>
""",
unsafe_allow_html=True
)
# Display the conversation
st.write('<div class="chat-container">', unsafe_allow_html=True)
for user_message, bot_message, model_name in st.session_state.conversation:
st.write(f'<div class="chat-bubble user">You: {user_message}</div>', unsafe_allow_html=True)
st.write(f'<div class="chat-bubble bot">{model_name}: {bot_message}</div>', unsafe_allow_html=True)
st.write('</div>', unsafe_allow_html=True) |