Spaces:
Runtime error
Runtime error
File size: 3,948 Bytes
cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 cb35e87 655c971 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 99 100 101 102 103 104 105 106 107 108 109 110 |
import http.client as http_client
import json
import logging
import os
import re
import string
import gradio as gr
import requests
def process_results(results, highlight_terms):
if len(results) == 0:
return """<br><p style='font-family: Arial; color:Silver; text-align: center;'>
No results retrieved.</p><br><hr>"""
results_html = ""
for result in results:
tokens = result["text"].split()
tokens_html = []
for token in tokens:
if token in highlight_terms:
tokens_html.append("<b>{}</b>".format(token))
else:
tokens_html.append(token)
tokens_html = " ".join(tokens_html)
meta_html = (
"""
<p class='underline-on-hover' style='font-size:12px; font-family: Arial; color:#585858; text-align: left;'>
<a href='{}' target='_blank'>{}</a></p>""".format(
result["meta"]["url"], result["meta"]["url"]
)
if "meta" in result and result["meta"] is not None and "url" in result["meta"]
else ""
)
docid_html = str(result["docid"])
results_html += """{}
<p style='font-size:14px; font-family: Arial; color:#7978FF; text-align: left;'>Document ID: {}</p>
<p style='font-size:12px; font-family: Arial; color:MediumAquaMarine'>Language: {}</p>
<p style='font-family: Arial;'>{}</p>
<br>
""".format(
meta_html, docid_html, result["lang"], tokens_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;"> 🌸 🔎 ROOTS search tool 🔍 🌸 </p>
The ROOTS corpus was developed during the [BigScience workshop](https://bigscience.huggingface.co/) for the purpose
of training the Multilingual Large Language Model [BLOOM](https://huggingface.co./bigscience/bloom). This tool allows
you to search through the ROOTS corpus. We serve a BM25 index for each language or group of languages included in
ROOTS. You can read more about the details of the tool design
[here](https://huggingface.co./spaces/bigscience-data/scisearch/blob/main/roots_search_tool_specs.pdf). For more
information and instructions on how to access the full corpus check [this form](https://forms.gle/qyYswbEL5kA23Wu99)."""
if __name__ == "__main__":
demo = gr.Blocks(
css=".underline-on-hover:hover { text-decoration: underline; } .flagging { font-size:12px; color:Silver; }"
)
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)
|