File size: 4,531 Bytes
787b7f8
85a6b6e
 
787b7f8
 
 
85a6b6e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
787b7f8
85a6b6e
 
 
 
2a9458c
 
 
85a6b6e
 
 
 
 
 
 
 
 
 
 
 
787b7f8
85a6b6e
 
 
 
 
 
 
787b7f8
85a6b6e
 
 
 
 
 
 
 
 
 
787b7f8
85a6b6e
 
 
 
2a9458c
85a6b6e
787b7f8
85a6b6e
 
787b7f8
85a6b6e
787b7f8
85a6b6e
 
 
 
 
 
 
 
 
787b7f8
85a6b6e
 
 
 
 
 
2a9458c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
787b7f8
85a6b6e
 
 
 
 
 
 
 
 
 
 
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
115
116
117
118
119
120
121
import streamlit as st
import base64
from fpdf import FPDF
import pikepdf
import fitz  # pymupdf

# Define the 12-point ML outline with emojis
ml_outline = [
    "🌟 1. Mixture of Experts (MoE)",
    "πŸ”₯ 2. Supervised Fine-Tuning (SFT) using PyTorch",
    "πŸ€– 3. Large Language Models (LLM) using Transformers",
    "πŸ“Š 4. Self-Rewarding Learning using NPS 0-10 and Verbatims",
    "πŸ‘ 5. Reinforcement Learning from Human Feedback (RLHF)",
    "πŸ”— 6. MergeKit: Merging Models to Same Embedding Space",
    "πŸ“ 7. DistillKit: Model Size Reduction with Spectrum Analysis",
    "🧠 8. Agentic RAG Agents using Document Inputs",
    "⏳ 9. Longitudinal Data Summarization from Multiple Docs",
    "πŸ“‘ 10. Knowledge Extraction using Markdown Knowledge Graphs",
    "πŸ—ΊοΈ 11. Knowledge Mapping with Mermaid Diagrams",
    "πŸ’» 12. ML Code Generation with Streamlit/Gradio/HTML5+JS"
]

def create_pdf_with_library(library_name, outline_items):
    if library_name == "fpdf":
        pdf = FPDF(orientation='L', unit='mm', format='A4')
        pdf.add_page()
        # Add Unicode font support
        pdf.add_font('DejaVu', '', 'DejaVuSans.ttf', uni=True)
        pdf.set_font('DejaVu', '', 10)
        
        # Left page (1-6)
        pdf.set_xy(10, 10)
        pdf.multi_cell(140, 5, "Cutting-Edge ML Areas (1-6)\n\n" + "\n".join(outline_items[:6]))
        
        # Right page (7-12)
        pdf.set_xy(150, 10)
        pdf.multi_cell(140, 5, "Cutting-Edge ML Areas (7-12)\n\n" + "\n".join(outline_items[6:]))
        
        filename = "ml_outline_fpdf.pdf"
        pdf.output(filename)
        return filename

    elif library_name == "pikepdf":
        pdf = pikepdf.Pdf.new()
        page = pikepdf.Page(pdf.make_stream(b""))
        pdf.pages.append(page)
        filename = "ml_outline_pikepdf.pdf"
        pdf.save(filename)
        return filename

    elif library_name == "pymupdf":
        doc = fitz.open()
        page = doc.new_page(width=842, height=595)  # A4 landscape
        page.insert_text((20, 20), "Cutting-Edge ML Areas (1-6)\n\n" + "\n".join(outline_items[:6]),
                        fontsize=10)
        page.insert_text((422, 20), "Cutting-Edge ML Areas (7-12)\n\n" + "\n".join(outline_items[6:]),
                        fontsize=10)
        filename = "ml_outline_pymupdf.pdf"
        doc.save(filename)
        return filename

def get_binary_file_downloader_html(bin_file, file_label='File'):
    with open(bin_file, 'rb') as f:
        data = f.read()
    bin_str = base64.b64encode(data).decode()
    href = f'<a href="data:application/octet-stream;base64,{bin_str}" download="{file_label}">Download {file_label aprovada}</a>'
    return href

# Streamlit UI
st.title("πŸš€ Cutting-Edge ML Outline Generator")

col1, col2 = st.columns(2)

with col1:
    st.header("πŸ“ Markdown Outline")
    outline_text = "\n".join(ml_outline)
    st.markdown(outline_text)
    
    md_file = "ml_outline.md"
    with open(md_file, "w") as f:
        f.write(outline_text)
    st.markdown(get_binary_file_downloader_html(md_file, "ml_outline.md"), unsafe_allow_html=True)

with col2:
    st.header("πŸ“‘ PDF Preview")
    pdf_library = st.selectbox("Choose PDF Library", ["fpdf", "pikepdf", "pymupdf"])
    
    if st.button("Generate PDF"):
        with st.spinner("Generating PDF..."):
            try:
                pdf_file = create_pdf_with_library(pdf_library, ml_outline)
                
                with open(pdf_file, "rb") as f:
                    pdf_bytes = f.read()
                
                st.download_button(
                    label="Download PDF",
                    data=pdf_bytes,
                    file_name=pdf_file,
                    mime="application/pdf"
                )
                
                base64_pdf = base64.b64encode(pdf_bytes).decode('utf-8')
                pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="400" type="application/pdf"></iframe>'
                st.markdown(pdf_display, unsafe_allow_html=True)
            except FileNotFoundError:
                st.error("Please download the DejaVuSans.ttf font and place it in the working directory for FPDF Unicode support")
            except Exception as e:
                st.error(f"Error generating PDF: {str(e)}")

st.markdown("""
<style>
    .stButton>button {
        background-color: #4CAF50;
        color: white;
    }
    .stSelectbox {
        max-width: 300px;
    }
</style>
""", unsafe_allow_html=True)