jee_main.py

import fitz  # PyMuPDF

pdf_path="D:\Professional\AI_ML\Embeddings\jee_mains.pdf"
def extract_text_from_pdf(pdf_path):

    doc = fitz.open(pdf_path)
    text = ""
    for page in doc:
        text += page.get_text()
    doc.close()
    return text

pdf_text = extract_text_from_pdf("jee_mains.pdf")
print(pdf_text[:5000])  # preview



#

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("all-MiniLM-L6-v2")  # Small and fast

# Optional: split large text into chunks
def split_into_chunks(text, chunk_size=500):
    words = text.split()
    for i in range(0, len(words), chunk_size):
        yield " ".join(words[i:i+chunk_size])

chunks = list(split_into_chunks(pdf_text, chunk_size=500))

# Generate embeddings
embeddings = model.encode(chunks)

print("The embedding for the text is:\n")
print(embeddings)