Spaces:
Running
Running
LAION
Browse files
app.py
CHANGED
@@ -2,12 +2,15 @@ import http.client as http_client
|
|
2 |
import json
|
3 |
import logging
|
4 |
import os
|
|
|
5 |
import re
|
6 |
import string
|
7 |
|
8 |
import gradio as gr
|
9 |
import requests
|
10 |
|
|
|
|
|
11 |
|
12 |
def get_docid_html(docid):
|
13 |
data_org, dataset, docid = docid.split("/")
|
@@ -36,6 +39,53 @@ def process_pii(text):
|
|
36 |
return text
|
37 |
|
38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
def process_results(results, highlight_terms):
|
40 |
if len(results) == 0:
|
41 |
return """<br><p style='font-family: Arial; color:Silver; text-align: center;'>
|
@@ -52,24 +102,10 @@ def process_results(results, highlight_terms):
|
|
52 |
tokens_html.append(token)
|
53 |
tokens_html = " ".join(tokens_html)
|
54 |
tokens_html = process_pii(tokens_html)
|
55 |
-
meta_html = (
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
result["meta"]["url"], result["meta"]["url"]
|
60 |
-
)
|
61 |
-
if "meta" in result and result["meta"] is not None and "url" in result["meta"]
|
62 |
-
else ""
|
63 |
-
)
|
64 |
-
docid_html = get_docid_html(result["docid"])
|
65 |
-
results_html += """{}
|
66 |
-
<p style='font-size:14px; font-family: Arial; color:#7978FF; text-align: left;'>Document ID: {}</p>
|
67 |
-
<p style='font-size:12px; font-family: Arial; color:MediumAquaMarine'>Language: {}</p>
|
68 |
-
<p style='font-family: Arial;'>{}</p>
|
69 |
-
<br>
|
70 |
-
""".format(
|
71 |
-
meta_html, docid_html, result["lang"], tokens_html
|
72 |
-
)
|
73 |
return results_html + "<hr>"
|
74 |
|
75 |
|
@@ -92,6 +128,8 @@ def scisearch(query, language, num_results=10):
|
|
92 |
|
93 |
payload = json.loads(output.text)
|
94 |
|
|
|
|
|
95 |
if "err" in payload:
|
96 |
if payload["err"]["type"] == "unsupported_lang":
|
97 |
detected_lang = payload["err"]["meta"]["detected_lang"]
|
@@ -143,6 +181,7 @@ def scisearch(query, language, num_results=10):
|
|
143 |
Check if a relevant discussion already exists in the Community tab. If not, please open a discussion.
|
144 |
</p>
|
145 |
"""
|
|
|
146 |
|
147 |
return results_html
|
148 |
|
|
|
2 |
import json
|
3 |
import logging
|
4 |
import os
|
5 |
+
import pprint
|
6 |
import re
|
7 |
import string
|
8 |
|
9 |
import gradio as gr
|
10 |
import requests
|
11 |
|
12 |
+
pp = pprint.PrettyPrinter(indent=2)
|
13 |
+
|
14 |
|
15 |
def get_docid_html(docid):
|
16 |
data_org, dataset, docid = docid.split("/")
|
|
|
39 |
return text
|
40 |
|
41 |
|
42 |
+
def process_meta_roots(result):
|
43 |
+
meta_html = (
|
44 |
+
"""
|
45 |
+
<p class='underline-on-hover' style='font-size:12px; font-family: Arial; color:#585858; text-align: left;'>
|
46 |
+
<a href='{}' target='_blank'>{}</a></p>""".format(
|
47 |
+
result["meta"]["url"], result["meta"]["url"]
|
48 |
+
)
|
49 |
+
if "meta" in result and result["meta"] is not None and "url" in result["meta"]
|
50 |
+
else ""
|
51 |
+
)
|
52 |
+
|
53 |
+
|
54 |
+
"""
|
55 |
+
'meta': { 'docs': [ { 'TEXT': 'Hello World Example Hello '
|
56 |
+
'World Page Hello World.',
|
57 |
+
'URL': 'http://images.slideplayer.com/8/2335183/slides/slide_6.jpg',
|
58 |
+
'_id': 592573973},
|
59 |
+
{ 'TEXT': 'Hello World Example Hello '
|
60 |
+
'World Page Hello World.',
|
61 |
+
'URL': 'http://images.slideplayer.com/8/2335183/slides/slide_9.jpg',
|
62 |
+
'_id': 1807595732},
|
63 |
+
{ 'TEXT': 'Hello World Example Hello '
|
64 |
+
'World Page Hello World.',
|
65 |
+
'URL': 'http://images.slideplayer.com/8/2335183/slides/slide_10.jpg',
|
66 |
+
'_id': 1864921031},
|
67 |
+
{ 'TEXT': 'Hello World Example Hello '
|
68 |
+
'World Page Hello World!',
|
69 |
+
'URL': 'http://images.slideplayer.com/8/2335183/slides/slide_5.jpg',
|
70 |
+
'_id': 1964462104},
|
71 |
+
{ 'TEXT': 'Hello World Example Hello '
|
72 |
+
'World Page Hello World.',
|
73 |
+
'URL': 'http://images.slideplayer.com/8/2335183/slides/slide_8.jpg',
|
74 |
+
'_id': 2167992166}]},
|
75 |
+
"""
|
76 |
+
def process_meta_laion(result):
|
77 |
+
meta_html = """"""
|
78 |
+
if "meta" not in result:
|
79 |
+
return meta_html
|
80 |
+
for doc in result["meta"]["docs"]:
|
81 |
+
# doc = json.loads(doc)
|
82 |
+
print(type(doc), doc)
|
83 |
+
print(doc["URL"])
|
84 |
+
meta_html += """<p class='underline-on-hover' style='font-size:12px; color:#7978FF; text-align: left;'>
|
85 |
+
<a href='{}' target='_blank'>{}</a></p>""".format(doc["URL"], doc["URL"])
|
86 |
+
|
87 |
+
return meta_html
|
88 |
+
|
89 |
def process_results(results, highlight_terms):
|
90 |
if len(results) == 0:
|
91 |
return """<br><p style='font-family: Arial; color:Silver; text-align: center;'>
|
|
|
102 |
tokens_html.append(token)
|
103 |
tokens_html = " ".join(tokens_html)
|
104 |
tokens_html = process_pii(tokens_html)
|
105 |
+
meta_html = process_meta_laion(result)
|
106 |
+
docid_html = """<p style='font-size:14px; font-family: Arial; color:#7978FF; text-align: left;'>Document ID: {}</p>""".format(result["docid"]) # get_docid_html(result["docid"])
|
107 |
+
language_html = """<p style='font-size:12px; font-family: Arial; color:MediumAquaMarine'>Language: {}</p>""".format(result["lang"])
|
108 |
+
results_html += tokens_html + meta_html + "<br>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
return results_html + "<hr>"
|
110 |
|
111 |
|
|
|
128 |
|
129 |
payload = json.loads(output.text)
|
130 |
|
131 |
+
pp.pprint(payload)
|
132 |
+
|
133 |
if "err" in payload:
|
134 |
if payload["err"]["type"] == "unsupported_lang":
|
135 |
detected_lang = payload["err"]["meta"]["detected_lang"]
|
|
|
181 |
Check if a relevant discussion already exists in the Community tab. If not, please open a discussion.
|
182 |
</p>
|
183 |
"""
|
184 |
+
print(e)
|
185 |
|
186 |
return results_html
|
187 |
|