File size: 6,363 Bytes
787b7f8
85a6b6e
2a632c8
 
 
 
 
 
 
 
 
 
3edd9d1
6d17d44
787b7f8
85a6b6e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
787b7f8
2a632c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3edd9d1
2a632c8
 
 
3edd9d1
2a632c8
 
 
 
3edd9d1
2a632c8
 
 
 
 
 
3edd9d1
2a632c8
 
3edd9d1
2a632c8
 
 
 
 
 
3edd9d1
2a632c8
 
 
787b7f8
6d17d44
 
3edd9d1
85a6b6e
787b7f8
85a6b6e
 
787b7f8
85a6b6e
787b7f8
85a6b6e
 
 
 
 
 
6d17d44
85a6b6e
6d17d44
787b7f8
85a6b6e
2a632c8
85a6b6e
2a632c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85a6b6e
2a9458c
2a632c8
2a9458c
3edd9d1
 
2a9458c
 
2a632c8
2a9458c
3edd9d1
2a9458c
 
 
 
6d17d44
 
 
 
 
 
 
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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
import streamlit as st
import base64
from reportlab.lib.pagesizes import A4
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.lib import colors
import pikepdf
import fpdf
import fitz  # pymupdf
import cv2
from PIL import Image
import imutils.video
import io
import os

# 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"
]

# Demo functions for PDF libraries
def demo_pikepdf():
    pdf = pikepdf.Pdf.new()
    pdf.pages.append(pikepdf.Page(pikepdf.Dictionary()))
    buffer = io.BytesIO()
    pdf.save(buffer)
    buffer.seek(0)
    return buffer.getvalue()

def demo_fpdf():
    pdf = fpdf.FPDF()
    pdf.add_page()
    pdf.set_font("Arial", size=12)
    pdf.cell(200, 10, txt="FPDF Demo", ln=True)
    buffer = io.BytesIO()
    pdf.output(buffer)
    buffer.seek(0)
    return buffer.getvalue()

def demo_pymupdf():
    doc = fitz.open()
    page = doc.new_page()
    page.insert_text((100, 100), "PyMuPDF Demo")
    buffer = io.BytesIO()
    doc.save(buffer)
    buffer.seek(0)
    return buffer.getvalue()

# Demo function for image capture (using OpenCV as representative)
def demo_image_capture():
    try:
        cap = cv2.VideoCapture(0)
        ret, frame = cap.read()
        if ret:
            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            img = Image.fromarray(rgb_frame)
            buffer = io.BytesIO()
            img.save(buffer, format="JPEG")
            buffer.seek(0)
            cap.release()
            return buffer.getvalue()
        cap.release()
    except:
        return None
    return None

# Main PDF creation using ReportLab
def create_main_pdf(outline_items):
    buffer = io.BytesIO()
    doc = SimpleDocTemplate(buffer, pagesize=(A4[1], A4[0]))  # Landscape
    styles = getSampleStyleSheet()
    story = []
    
    # Title style
    title_style = styles['Heading1']
    title_style.textColor = colors.darkblue
    
    # Normal style
    normal_style = styles['Normal']
    normal_style.fontSize = 10
    normal_style.leading = 14
    
    # Page 1: Items 1-6
    story.append(Paragraph("Cutting-Edge ML Areas (1-6)", title_style))
    story.append(Spacer(1, 12))
    for item in outline_items[:6]:
        story.append(Paragraph(item, normal_style))
        story.append(Spacer(1, 6))
    
    # Page break
    story.append(Spacer(1, 500))  # Force new page
    
    # Page 2: Items 7-12
    story.append(Paragraph("Cutting-Edge ML Areas (7-12)", title_style))
    story.append(Spacer(1, 12))
    for item in outline_items[6:]:
        story.append(Paragraph(item, normal_style))
        story.append(Spacer(1, 6))
    
    doc.build(story)
    buffer.seek(0)
    return buffer.getvalue()

def get_binary_file_downloader_html(bin_data, file_label='File'):
    bin_str = base64.b64encode(bin_data).decode()
    href = f'<a href="data:application/octet-stream;base64,{bin_str}" download="{file_label}">Download {file_label}</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", encoding='utf-8') as f:
        f.write(outline_text)
    st.markdown(get_binary_file_downloader_html(outline_text.encode('utf-8'), "ml_outline.md"), unsafe_allow_html=True)

with col2:
    st.header("πŸ“‘ PDF Preview & Demos")
    
    # Library Demos
    st.subheader("Library Demos")
    if st.button("Run PDF Demos"):
        with st.spinner("Running demos..."):
            # pikepdf demo
            pike_pdf = demo_pikepdf()
            st.download_button("Download pikepdf Demo", pike_pdf, "pikepdf_demo.pdf")
            
            # fpdf demo
            fpdf_pdf = demo_fpdf()
            st.download_button("Download fpdf Demo", fpdf_pdf, "fpdf_demo.pdf")
            
            # pymupdf demo
            pymupdf_pdf = demo_pymupdf()
            st.download_button("Download pymupdf Demo", pymupdf_pdf, "pymupdf_demo.pdf")
            
            # Image capture demo
            img_data = demo_image_capture()
            if img_data:
                st.image(img_data, caption="OpenCV Image Capture Demo")
            else:
                st.warning("Image capture demo failed - camera not detected")

    # Main PDF Generation
    if st.button("Generate Main PDF"):
        with st.spinner("Generating PDF..."):
            try:
                pdf_bytes = create_main_pdf(ml_outline)
                
                with open("ml_outline.pdf", "wb") as f:
                    f.write(pdf_bytes)
                
                st.download_button(
                    label="Download Main PDF",
                    data=pdf_bytes,
                    file_name="ml_outline.pdf",
                    mime="application/pdf"
                )
                
                base64_pdf = base64.b64encode(pdf_bytes).decode('utf-8')
                pdf_display = f'''
                    <embed 
                        src="data:application/pdf;base64,{base64_pdf}" 
                        width="100%" 
                        height="400px" 
                        type="application/pdf">
                '''
                st.markdown(pdf_display, unsafe_allow_html=True)
            except Exception as e:
                st.error(f"Error generating PDF: {str(e)}")

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