Assignment3 / app.py
Gagan202004's picture
Update app.py
973a786 verified
Raw History Blame Contribute Delete
884 Bytes
import gradio as gr
from huggingface_hub import InferenceClient
from typing import List, Tuple
import fitz # PyMuPDF
from sentence_transformers import SentenceTransformer, util
import numpy as np
import faiss
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
"""
class MyApp:
def __init__(self) -> None:
self.documents = []
self.embeddings = None
self.index = None
self.load_pdf("Mypdf")
self.build_vector_db()
def load_pdf(self, file:///C:/Users/gagan/OneDrive/Desktop/Mypdf.pdf: str) -> None:
doc = fitz.open(file:///C:/Users/gagan/OneDrive/Desktop/Mypdf.pdf)
self.documents = []
for page_num in range(len(doc)):
page = doc[page_num]
text = page.get_text()
self.documents.append({"page": page_num + 1, "content": text})
print("PDF processed successfully!")