Spaces:
Runtime error
Runtime error
File size: 3,511 Bytes
cb35e87 385bf5d fb9e6d1 7f5bdb5 385bf5d cb35e87 7f5bdb5 cb35e87 385bf5d 7f5bdb5 655c971 e146ae1 7f5bdb5 f5e91d1 e146ae1 cb35e87 f5e91d1 cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 cb35e87 f5e91d1 ea75bda f5e91d1 cb35e87 7f5bdb5 cb35e87 655c971 cb35e87 01b1b14 cb35e87 01b1b14 cb35e87 |
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 |
import http.client as http_client
import json
import logging
import os
import re
import string
import gradio as gr
import requests
def mark_tokens_bold(string, tokens):
for token in tokens:
pattern = re.escape(token) #r"\b" + re.escape(token) + r"\b"
string = re.sub(pattern, "<span style='color: #ff75b3;'><b>" + token + "</b></span>", string)
return string
def process_results(results, highlight_terms):
if len(results) == 0:
return """<br><p>No results retrieved.</p><br><hr>"""
results_html = ""
for result in results:
text_html = result["text"]
text_html = mark_tokens_bold(text_html, highlight_terms)
docid_html = str(result["docid"])
licenses = " | ".join(result["repo_license"])
repo_name = result["repo_name"]
repo_path = result["repo_path"]
results_html += """\
<p style='font-size:16px; font-family: Arial; text-align: left; color: white;'>Repository name: <span style='color: #ff75b3;'>{}</span></p>
<p style='font-size:16px; font-family: Arial; text-align: left; color: white;'>Repository path: <span style='color: #ff75b3;'>{}</span></p>
<p style='font-size:16px; font-family: Arial; text-align: left; color: white;'>Repository licenses: <span style='color: #ff75b3;'>{}</span></p>
<pre style='height: 600px; overflow: scroll;'><code>{}</code></pre>
<br>
""".format(repo_name, repo_path, licenses, text_html)
return results_html + "<hr>"
def scisearch(query, language, num_results=10):
query = " ".join(query.split())
if query == "" or query is None:
return ""
post_data = {"query": query, "k": num_results}
output = requests.post(
os.environ.get("address"),
headers={"Content-type": "application/json"},
data=json.dumps(post_data),
timeout=60,
)
payload = json.loads(output.text)
results = payload["results"]
highlight_terms = payload["highlight_terms"]
return process_results(results, highlight_terms)
description = """# <p style="text-align: center; color: white;"> 🔎 IceCoder Dataset Search 🔍 </p>
<span style='color: white;'>When you use <a href="todo" style="color: #ff75b3;">IceCoder</a> to generate code it might produce exact copies of code in the pretraining dataset. In that case the code requires
and with this search tool we aim to provide help to finding out where the code came from.</span>"""
if __name__ == "__main__":
demo = gr.Blocks(
css=".gradio-container {background-color: #20233fff; color:white}"
)
with demo:
with gr.Row():
gr.Markdown(value=description)
with gr.Row():
query = gr.Textbox(lines=1, max_lines=1, placeholder="Type your query here...", label="Query")
with gr.Row():
k = gr.Slider(1, 100, value=10, step=1, label="Max Results")
with gr.Row():
submit_btn = gr.Button("Submit")
with gr.Row():
results = gr.HTML(label="Results")
def submit(query, k, lang="en"):
query = query.strip()
if query is None or query == "":
return "", ""
return {
results: scisearch(query, lang, k),
}
query.submit(fn=submit, inputs=[query, k], outputs=[results])
submit_btn.click(submit, inputs=[query, k], outputs=[results])
demo.launch(enable_queue=True, debug=True)
|