Csv
Browse files- app.py +15 -3
- hf_utils.py +53 -0
- requirements.txt +4 -1
app.py
CHANGED
@@ -1,17 +1,29 @@
|
|
1 |
import gradio as gr
|
2 |
import re
|
|
|
|
|
|
|
3 |
|
4 |
def process_repo_input(text):
|
5 |
if not text:
|
6 |
-
return "
|
7 |
# Split by newlines and commas, strip whitespace
|
8 |
repo_ids = [repo.strip() for repo in re.split(r'[\n,]+', text) if repo.strip()]
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
demo = gr.Interface(
|
12 |
fn=process_repo_input,
|
13 |
inputs=gr.Textbox(label="Enter repo IDs (comma or newline separated)", lines=5, placeholder="repo1, repo2\nrepo3"),
|
14 |
-
outputs="
|
15 |
title="Repo ID Input",
|
16 |
description="Enter repo IDs separated by commas or new lines."
|
17 |
)
|
|
|
1 |
import gradio as gr
|
2 |
import re
|
3 |
+
import csv
|
4 |
+
import pandas as pd
|
5 |
+
|
6 |
|
7 |
def process_repo_input(text):
|
8 |
if not text:
|
9 |
+
return pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
|
10 |
# Split by newlines and commas, strip whitespace
|
11 |
repo_ids = [repo.strip() for repo in re.split(r'[\n,]+', text) if repo.strip()]
|
12 |
+
# Write to CSV
|
13 |
+
csv_filename = "repo_ids.csv"
|
14 |
+
with open(csv_filename, mode="w", newline='', encoding="utf-8") as csvfile:
|
15 |
+
writer = csv.writer(csvfile)
|
16 |
+
writer.writerow(["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
|
17 |
+
for repo_id in repo_ids:
|
18 |
+
writer.writerow([repo_id, "", "", "", ""])
|
19 |
+
# Read the CSV into a DataFrame to display
|
20 |
+
df = pd.read_csv(csv_filename)
|
21 |
+
return df
|
22 |
|
23 |
demo = gr.Interface(
|
24 |
fn=process_repo_input,
|
25 |
inputs=gr.Textbox(label="Enter repo IDs (comma or newline separated)", lines=5, placeholder="repo1, repo2\nrepo3"),
|
26 |
+
outputs=gr.Dataframe(headers=["repo id", "strength", "weaknesses", "speciality", "relevance rating"]),
|
27 |
title="Repo ID Input",
|
28 |
description="Enter repo IDs separated by commas or new lines."
|
29 |
)
|
hf_utils.py
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from huggingface_hub import snapshot_download
|
2 |
+
import os
|
3 |
+
import shutil
|
4 |
+
|
5 |
+
def download_space_repo(space_id: str, local_dir: str = "space_repo"):
|
6 |
+
"""
|
7 |
+
Downloads all files from a Hugging Face Space repository.
|
8 |
+
|
9 |
+
Args:
|
10 |
+
space_id (str): The ID of the Hugging Face Space (e.g., "naman1102/Final_Assignment_Template").
|
11 |
+
local_dir (str): Local directory to store the downloaded files.
|
12 |
+
"""
|
13 |
+
print(f"Downloading Space '{space_id}'...")
|
14 |
+
|
15 |
+
# Download the snapshot of the space repo
|
16 |
+
repo_path = snapshot_download(repo_id=space_id, repo_type="space")
|
17 |
+
|
18 |
+
# Remove existing directory if it exists
|
19 |
+
if os.path.exists(local_dir):
|
20 |
+
shutil.rmtree(local_dir)
|
21 |
+
|
22 |
+
# Copy contents to target directory
|
23 |
+
shutil.copytree(repo_path, local_dir)
|
24 |
+
|
25 |
+
print(f"All files from Space '{space_id}' downloaded to: {local_dir}")
|
26 |
+
|
27 |
+
# Example usage
|
28 |
+
# download_space_repo("finegrain/finegrain-image-enhancer")
|
29 |
+
|
30 |
+
from huggingface_hub import list_spaces
|
31 |
+
|
32 |
+
def search_top_spaces(query: str, limit: int = 5):
|
33 |
+
"""
|
34 |
+
Search and return top Hugging Face Space repo IDs based on a keyword.
|
35 |
+
|
36 |
+
Args:
|
37 |
+
query (str): The keyword to search for (e.g., "image", "chatbot").
|
38 |
+
limit (int): Maximum number of results to return.
|
39 |
+
|
40 |
+
Returns:
|
41 |
+
List of repo IDs.
|
42 |
+
"""
|
43 |
+
results = list(list_spaces(search=query, sort="likes", direction=-1)) # Convert generator to list
|
44 |
+
top_spaces = [space.id for space in results[:limit]]
|
45 |
+
|
46 |
+
return top_spaces
|
47 |
+
|
48 |
+
# Example usage
|
49 |
+
# top_image_spaces = search_top_spaces("tic tac toe", limit=10)
|
50 |
+
# print("Top games-related Spaces:")
|
51 |
+
# for space_id in top_image_spaces:
|
52 |
+
# print("-", space_id)
|
53 |
+
|
requirements.txt
CHANGED
@@ -1 +1,4 @@
|
|
1 |
-
gradio
|
|
|
|
|
|
|
|
1 |
+
gradio
|
2 |
+
pandas
|
3 |
+
re
|
4 |
+
csv
|