Spaces:
Sleeping
Sleeping
File size: 2,887 Bytes
18056d4 6e2c6a7 18056d4 |
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 |
import gradio as gr
from langchain_community.document_loaders import PyPDFLoader
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_community.llms import HuggingFaceEndpoint
from langchain.chains import RetrievalQA
import os
import shutil
# Hugging Face API key (store in your Space's secrets for security)
HUGGINGFACEHUB_API_TOKEN = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
# Load HF Inference Endpoint (like mistralai/Mistral-7B-Instruct)
llm = HuggingFaceEndpoint(
repo_id="mistralai/Mistral-7B-Instruct-v0.2",
temperature=0.2,
huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN
)
# Embeddings (Hugging Face miniLM for fast processing)
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
# Temporary folder to store PDFs
UPLOAD_DIR = "pdf_uploads"
if not os.path.exists(UPLOAD_DIR):
os.makedirs(UPLOAD_DIR)
def process_pdf(file):
# Save PDF file
file_path = os.path.join(UPLOAD_DIR, file.name)
with open(file_path, "wb") as f:
f.write(file.read())
# Load PDF text using langchain
loader = PyPDFLoader(file_path)
pages = loader.load_and_split()
# Create Chroma vector store (in-memory)
vectordb = Chroma.from_documents(pages, embedding=embeddings)
retriever = vectordb.as_retriever()
# Create RetrievalQA chain
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=retriever,
return_source_documents=True
)
# Return the QA chain to use in the chat
return qa_chain
# Global variable to hold QA chain for the session
qa_chain = None
def upload_pdf(file):
global qa_chain
qa_chain = process_pdf(file)
return "✅ PDF uploaded and processed! Ask me anything about it."
def chatbot(user_message, history):
if qa_chain is None:
return "❌ Please upload a PDF first.", history
response = qa_chain.run(user_message)
history.append((user_message, response))
return "", history
with gr.Blocks(theme=gr.themes.Soft()) as demo:
gr.Markdown("<h1 style='text-align:center;'>📚 PDF Chatbot Assistant</h1>")
with gr.Row():
pdf_upload = gr.File(label="Upload your PDF", file_types=[".pdf"])
upload_btn = gr.Button("Process PDF")
chatbot_ui = gr.Chatbot(height=400)
user_input = gr.Textbox(label="Ask something about the PDF...", placeholder="Type your question here and hit Enter")
upload_btn.click(upload_pdf, inputs=pdf_upload, outputs=chatbot_ui)
user_input.submit(chatbot, [user_input, chatbot_ui], [user_input, chatbot_ui])
gr.Markdown("<footer style='text-align:center; font-size:0.85rem; color:#64748b;'>Created by YourName - Powered by Hugging Face</footer>")
if __name__ == "__main__":
demo.launch()
|