File size: 6,856 Bytes
3d5dd87
 
 
f389421
00551a6
f389421
281bb73
f389421
3d5dd87
00551a6
 
 
 
 
281bb73
3d5dd87
 
 
 
 
 
 
 
 
 
 
281bb73
f389421
3d5dd87
281bb73
f389421
 
3d5dd87
 
 
 
281bb73
3d5dd87
 
281bb73
3d5dd87
 
281bb73
f389421
 
 
 
00551a6
281bb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00551a6
 
 
 
 
 
 
 
 
 
 
 
3d5dd87
281bb73
 
 
 
3d5dd87
 
281bb73
3d5dd87
 
281bb73
3d5dd87
 
 
 
281bb73
f389421
3d5dd87
 
 
 
 
281bb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00551a6
 
281bb73
 
3d5dd87
281bb73
3d5dd87
 
281bb73
3d5dd87
281bb73
3d5dd87
 
 
 
281bb73
 
3d5dd87
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
import streamlit as st
from huggingface_hub import HfApi
import pandas as pd
import asyncio
import os

# Initialize the Hugging Face API
api = HfApi()

# Directory to save the generated HTML files
HTML_DIR = "generated_html_pages"
if not os.path.exists(HTML_DIR):
    os.makedirs(HTML_DIR)

# Default list of Hugging Face usernames - where all the magic begins! πŸͺ„
default_users = {
    "users": [
        "awacke1", "rogerxavier", "jonatasgrosman", "kenshinn", "Csplk", "DavidVivancos",
        "cdminix", "Jaward", "TuringsSolutions", "Severian", "Wauplin",
        "phosseini", "Malikeh1375", "gokaygokay", "MoritzLaurer", "mrm8488",
        "TheBloke", "lhoestq", "xw-eric", "Paul", "Muennighoff",
        "ccdv", "haonan-li", "chansung", "lukaemon", "hails",
        "pharmapsychotic", "KingNish", "merve", "ameerazam08", "ashleykleynhans"
    ]
}

# Asynchronous function to fetch user content - because why wait when you can multitask? πŸš€
async def fetch_user_content(username):
    try:
        # Fetch models and datasets - the stars of our show! 🌟
        models = await asyncio.to_thread(api.list_models, author=username)
        datasets = await asyncio.to_thread(api.list_datasets, author=username)
        
        return {
            "username": username,
            "models": models,
            "datasets": datasets
        }
    except Exception as e:
        # Oops! Something went wrong - blame it on the gremlins! 😈
        return {"username": username, "error": str(e)}

# Fetch all users concurrently - more hands (or threads) make light work! πŸ’ͺ
async def fetch_all_users(usernames):
    tasks = [fetch_user_content(username) for username in usernames]
    return await asyncio.gather(*tasks)

# Generate HTML content for a user and save it to a file - because who doesn't love a good download link? πŸ’Ύ
def generate_html_page(username, models, datasets):
    html_content = f"""
    <html>
    <head>
        <title>{username}'s Hugging Face Content</title>
    </head>
    <body>
        <h1>{username}'s Hugging Face Profile</h1>
        <p><a href="https://huggingface.co/{username}">πŸ”— Profile Link</a></p>
        <h2>🧠 Models</h2>
        <ul>
    """
    for model in models:
        model_name = model.modelId.split("/")[-1]
        html_content += f'<li><a href="https://huggingface.co/{model.modelId}">{model_name}</a></li>'
    
    html_content += """
        </ul>
        <h2>πŸ“š Datasets</h2>
        <ul>
    """
    for dataset in datasets:
        dataset_name = dataset.id.split("/")[-1]
        html_content += f'<li><a href="https://huggingface.co/datasets/{dataset.id}">{dataset_name}</a></li>'
    
    html_content += """
        </ul>
    </body>
    </html>
    """

    # Save the HTML content to a file
    html_file_path = os.path.join(HTML_DIR, f"{username}.html")
    with open(html_file_path, "w") as html_file:
        html_file.write(html_content)

    return html_file_path

# Cache the HTML generation process using Streamlit's caching decorator - because no one likes to repeat themselves! πŸ”
@st.cache_data(show_spinner=False)
def get_cached_html_page(username, models, datasets):
    return generate_html_page(username, models, datasets)

# Streamlit app setup - the nerve center of our operation! πŸŽ›οΈ
st.title("Hugging Face User Content Display - Let's Automate Some Fun! πŸŽ‰")

# Convert the default users list to a string - because nobody likes typing out long lists! πŸ“
default_users_str = "\n".join(default_users["users"])

# Text area with default list of usernames - feel free to add your friends! πŸ‘₯
usernames = st.text_area("Enter Hugging Face usernames (one per line):", value=default_users_str, height=300)

# Show User Content button - the big red button! (But actually it's blue) πŸ–±οΈ
if st.button("Show User Content"):
    if usernames:
        username_list = [username.strip() for username in usernames.split('\n') if username.strip()]

        # Run the asyncio loop to fetch all users - time to unleash the hounds! πŸ•
        results = asyncio.run(fetch_all_users(username_list))

        st.markdown("### User Content Overview")
        for result in results:
            username = result["username"]
            if "error" not in result:
                with st.container():
                    # Profile link - because everyone deserves their 15 seconds of fame! 🎀
                    st.markdown(f"**{username}** [πŸ”— Profile](https://huggingface.co/{username})")

                    # Create columns for models and datasets - divide and conquer! πŸ›οΈ
                    col1, col2 = st.columns(2)

                    # Models section with emoji - 🧠 because AI models are brainy! 🧠
                    with col1:
                        st.markdown("**Models:** 🧠")
                        if result['models']:
                            for model in result['models']:
                                model_name = model.modelId.split("/")[-1]
                                st.markdown(f"- [{model_name}](https://huggingface.co/{model.modelId})")
                        else:
                            st.markdown("No models found. Did you check under the rug? πŸ•΅οΈβ€β™‚οΈ")

                    # Datasets section with emoji - πŸ“š because data is the foundation of AI! πŸ“š
                    with col2:
                        st.markdown("**Datasets:** πŸ“š")
                        if result['datasets']:
                            for dataset in result['datasets']:
                                dataset_name = dataset.id.split("/")[-1]
                                st.markdown(f"- [{dataset_name}](https://huggingface.co/datasets/{dataset.id})")
                        else:
                            st.markdown("No datasets found. Maybe they’re still baking in the oven? πŸͺ")

                    # Generate HTML page and provide download link - because who wouldn't want a custom webpage? 🌐
                    html_file_path = get_cached_html_page(username, result['models'], result['datasets'])
                    st.markdown(f"[πŸ“„ Download {username}'s HTML Page]({html_file_path})")
                    
                    st.markdown("---")
            else:
                st.warning(f"{username}: {result['error']} - Looks like the AI needs a coffee break β˜•")

    else:
        st.warning("Please enter at least one username. Don't be shy! πŸ˜…")

# Sidebar instructions - just in case you get lost! πŸ—ΊοΈ
st.sidebar.markdown("""
## How to use:
1. The text area is pre-filled with a list of Hugging Face usernames. You can edit this list or add more usernames.
2. Click 'Show User Content'.
3. View the user's models and datasets along with a link to their Hugging Face profile.
4. Download an HTML page for each user to use the absolute links offline!
""")