Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
update
Browse files- .gitignore +1 -0
- README.md +5 -6
- app.py +449 -99
- constants/prompts.toml +17 -0
- date_iterator.sh +27 -0
- gen/gemini.py +142 -0
- gen/utils.py +37 -0
- outputs.json +0 -0
- paper/download.py +102 -0
- paper/parser.py +57 -0
- requirements.txt +9 -0
- utils.py +28 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
__pycache__
|
README.md
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 4.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
11 |
-
short_description: Explore papers with auto generated Q&As!
|
12 |
---
|
13 |
|
14 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
---
|
2 |
+
title: Test Paperqa
|
3 |
+
emoji: π₯
|
4 |
+
colorFrom: indigo
|
5 |
+
colorTo: pink
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 4.20.0
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
|
|
11 |
---
|
12 |
|
13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
CHANGED
@@ -1,12 +1,34 @@
|
|
1 |
-
import
|
|
|
2 |
import copy
|
3 |
import datasets
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
5 |
STYLE = """
|
6 |
|
7 |
-
|
8 |
-
|
9 |
-
|
|
|
|
|
10 |
}
|
11 |
|
12 |
.small-font{
|
@@ -16,7 +38,7 @@ STYLE = """
|
|
16 |
.small-font:hover {
|
17 |
font-size: 20px !important;
|
18 |
transition: font-size 0.3s ease-out;
|
19 |
-
transition-delay:
|
20 |
}
|
21 |
|
22 |
.group {
|
@@ -50,22 +72,207 @@ STYLE = """
|
|
50 |
border-radius: 0px;
|
51 |
}
|
52 |
|
53 |
-
|
|
|
|
|
|
|
|
|
54 |
display: none;
|
55 |
}
|
56 |
|
57 |
-
|
58 |
display: none;
|
59 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
"""
|
61 |
|
|
|
|
|
|
|
62 |
dataset_repo_id = "chansung/auto-paper-qa2"
|
|
|
|
|
63 |
ds = datasets.load_dataset(dataset_repo_id)
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
title2qna = {}
|
66 |
date2qna = {}
|
67 |
longest_qans = 0
|
68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
def count_nans(row):
|
70 |
count = 0
|
71 |
|
@@ -119,33 +326,33 @@ def set_paper(date, paper_title):
|
|
119 |
return (
|
120 |
gr.Markdown(f"# {selected_paper['title']}"), gr.Markdown(selected_paper["summary"]),
|
121 |
|
122 |
-
gr.Markdown(f"
|
123 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_answers:eli5']}"),
|
124 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_answers:expert']}"),
|
125 |
-
gr.Markdown(f"
|
126 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_depth_q:answers:eli5']}"),
|
127 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_depth_q:answers:expert']}"),
|
128 |
-
gr.Markdown(f"
|
129 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_breath_q:answers:eli5']}"),
|
130 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_breath_q:answers:expert']}"),
|
131 |
|
132 |
-
gr.Markdown(f"
|
133 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_answers:eli5']}"),
|
134 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_answers:expert']}"),
|
135 |
-
gr.Markdown(f"
|
136 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_depth_q:answers:eli5']}"),
|
137 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_depth_q:answers:expert']}"),
|
138 |
-
gr.Markdown(f"
|
139 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_breath_q:answers:eli5']}"),
|
140 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_breath_q:answers:expert']}"),
|
141 |
|
142 |
-
gr.Markdown(f"
|
143 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_answers:eli5']}"),
|
144 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_answers:expert']}"),
|
145 |
-
gr.Markdown(f"
|
146 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_depth_q:answers:eli5']}"),
|
147 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_depth_q:answers:expert']}"),
|
148 |
-
gr.Markdown(f"
|
149 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_breath_q:answers:eli5']}"),
|
150 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_breath_q:answers:expert']}"),
|
151 |
)
|
@@ -196,7 +403,7 @@ function search(searchIn, maxResults = 3) {{
|
|
196 |
let titles = {list(titles)};
|
197 |
|
198 |
for (const title of titles) {{ // Assuming 'titles' is an array defined elsewhere
|
199 |
-
if (results.length >
|
200 |
break;
|
201 |
}} else {{
|
202 |
if (title.toLowerCase().includes(searchIn.toLowerCase())) {{ // JavaScript's equivalent to Python's 'in'
|
@@ -206,7 +413,7 @@ function search(searchIn, maxResults = 3) {{
|
|
206 |
}}
|
207 |
|
208 |
// Handle UI elements (Explanation below)
|
209 |
-
const resultElements = [1,
|
210 |
return results[index - 1] || '';
|
211 |
}});
|
212 |
|
@@ -228,13 +435,74 @@ function search(searchIn, maxResults = 3) {{
|
|
228 |
document.getElementById('search_r3').style.display = 'block';
|
229 |
}}
|
230 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
231 |
return resultElements;
|
232 |
}} else {{
|
233 |
document.getElementById('search_r1').style.display = 'none';
|
234 |
document.getElementById('search_r2').style.display = 'none';
|
235 |
document.getElementById('search_r3').style.display = 'none';
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
236 |
|
237 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
238 |
}}
|
239 |
}}
|
240 |
"""
|
@@ -251,7 +519,7 @@ def set_papers(date, title):
|
|
251 |
gr.Textbox("")
|
252 |
)
|
253 |
|
254 |
-
with gr.Blocks(css=STYLE) as demo:
|
255 |
gr.Markdown("# Let's explore papers with auto generated Q&As")
|
256 |
|
257 |
with gr.Column(elem_classes=["group"]):
|
@@ -272,108 +540,164 @@ with gr.Blocks(css=STYLE) as demo:
|
|
272 |
)
|
273 |
|
274 |
with gr.Column(elem_classes=["no-gap"]):
|
275 |
-
search_in = gr.Textbox("", placeholder="Enter keywords to search...",
|
276 |
search_r1 = gr.Button(visible=False, elem_id="search_r1", elem_classes=["no-radius"])
|
277 |
search_r2 = gr.Button(visible=False, elem_id="search_r2", elem_classes=["no-radius"])
|
278 |
search_r3 = gr.Button(visible=False, elem_id="search_r3", elem_classes=["no-radius"])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
279 |
|
280 |
-
title = gr.Markdown(f"# {selected_paper['title']}")
|
281 |
-
summary = gr.Markdown(f"{selected_paper['summary']}", elem_classes=["small-font"])
|
282 |
-
|
283 |
-
with gr.Row():
|
284 |
-
with gr.Column(scale=7):
|
285 |
-
gr.Markdown("## Auto generated Questions & Answers")
|
286 |
-
|
287 |
-
exp_type = gr.Radio(choices=["ELI5", "Technical"], value="ELI5", elem_id="exp-type", scale=3)
|
288 |
-
|
289 |
-
# 1
|
290 |
-
with gr.Column(elem_classes=["group"], visible=True) as q_0:
|
291 |
-
basic_q_0 = gr.Markdown(f"## π {selected_paper['0_question']}")
|
292 |
-
basic_q_eli5_0 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_answers:eli5']}", elem_classes=["small-font"])
|
293 |
-
basic_q_expert_0 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_answers:expert']}", visible=False, elem_classes=["small-font"])
|
294 |
-
|
295 |
-
with gr.Accordion("Additional question #1", open=False, elem_classes=["accordion"]) as aq_0_0:
|
296 |
-
depth_q_0 = gr.Markdown(f"## ππ {selected_paper['0_additional_depth_q:follow up question']}")
|
297 |
-
depth_q_eli5_0 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_depth_q:answers:eli5']}", elem_classes=["small-font"])
|
298 |
-
depth_q_expert_0 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_depth_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
299 |
-
|
300 |
-
with gr.Accordion("Additional question #2", open=False, elem_classes=["accordion"]) as aq_0_1:
|
301 |
-
breath_q_0 = gr.Markdown(f"## ππ {selected_paper['0_additional_breath_q:follow up question']}")
|
302 |
-
breath_q_eli5_0 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
|
303 |
-
breath_q_expert_0 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
304 |
-
|
305 |
-
# 2
|
306 |
-
with gr.Column(elem_classes=["group"], visible=True) as q_1:
|
307 |
-
basic_q_1 = gr.Markdown(f"## π {selected_paper['1_question']}")
|
308 |
-
basic_q_eli5_1 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_answers:eli5']}", elem_classes=["small-font"])
|
309 |
-
basic_q_expert_1 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_answers:expert']}", visible=False, elem_classes=["small-font"])
|
310 |
-
|
311 |
-
with gr.Accordion("Additional question #1", open=False, elem_classes=["accordion"]) as aq_1_0:
|
312 |
-
depth_q_1 = gr.Markdown(f"## ππ {selected_paper['1_additional_depth_q:follow up question']}")
|
313 |
-
depth_q_eli5_1 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_depth_q:answers:eli5']}", elem_classes=["small-font"])
|
314 |
-
depth_q_expert_1 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_depth_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
315 |
-
|
316 |
-
with gr.Accordion("Additional question #2", open=False, elem_classes=["accordion"]) as aq_1_1:
|
317 |
-
breath_q_1 = gr.Markdown(f"## ππ {selected_paper['1_additional_breath_q:follow up question']}")
|
318 |
-
breath_q_eli5_1 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
|
319 |
-
breath_q_expert_1 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
320 |
-
|
321 |
-
# 3
|
322 |
-
with gr.Column(elem_classes=["group"], visible=True) as q_2:
|
323 |
-
basic_q_2 = gr.Markdown(f"## π {selected_paper['2_question']}")
|
324 |
-
basic_q_eli5_2 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_answers:eli5']}", elem_classes=["small-font"])
|
325 |
-
basic_q_expert_2 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_answers:expert']}", visible=False, elem_classes=["small-font"])
|
326 |
-
|
327 |
-
with gr.Accordion("Additional question #1", open=False, elem_classes=["accordion"]) as aq_2_0:
|
328 |
-
depth_q_2 = gr.Markdown(f"## ππ {selected_paper['2_additional_depth_q:follow up question']}")
|
329 |
-
depth_q_eli5_2 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_depth_q:answers:eli5']}", elem_classes=["small-font"])
|
330 |
-
depth_q_expert_2 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_depth_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
331 |
-
|
332 |
-
with gr.Accordion("Additional question #2", open=False, elem_classes=["accordion"]) as aq_2_1:
|
333 |
-
breath_q_2 = gr.Markdown(f"## ππ {selected_paper['2_additional_breath_q:follow up question']}")
|
334 |
-
breath_q_eli5_2 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
|
335 |
-
breath_q_expert_2 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
336 |
|
337 |
gr.Markdown("The target papers are collected from [Hugging Face π€ Daily Papers](https://huggingface.co/papers) on a daily basis. "
|
338 |
"The entire data is generated by [Google's Gemini 1.0](https://deepmind.google/technologies/gemini/) Pro. "
|
339 |
"If you are curious how it is done, visit the [Auto Paper Q&A Generation project repository](https://github.com/deep-diver/auto-paper-analysis) "
|
340 |
"Also, the generated dataset is hosted on Hugging Face π€ Dataset repository as well([Link](https://huggingface.co/datasets/chansung/auto-paper-qa2)). ")
|
341 |
|
342 |
-
search_r1.click(
|
343 |
-
set_date,
|
344 |
-
search_r1,
|
345 |
-
date_dd
|
346 |
-
).then(
|
347 |
set_papers,
|
348 |
inputs=[date_dd, search_r1],
|
349 |
outputs=[papers_dd, search_in]
|
350 |
)
|
351 |
|
352 |
-
search_r2.click(
|
353 |
-
set_date,
|
354 |
-
search_r2,
|
355 |
-
date_dd
|
356 |
-
).then(
|
357 |
set_papers,
|
358 |
inputs=[date_dd, search_r2],
|
359 |
outputs=[papers_dd, search_in]
|
360 |
)
|
361 |
|
362 |
-
search_r3.click(
|
363 |
-
set_date,
|
364 |
-
search_r3,
|
365 |
-
date_dd
|
366 |
-
).then(
|
367 |
set_papers,
|
368 |
inputs=[date_dd, search_r3],
|
369 |
outputs=[papers_dd, search_in]
|
370 |
)
|
371 |
|
372 |
-
date_dd.
|
373 |
-
|
374 |
-
date_dd,
|
375 |
-
papers_dd
|
376 |
-
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
377 |
set_paper,
|
378 |
[date_dd, papers_dd],
|
379 |
[
|
@@ -413,7 +737,10 @@ with gr.Blocks(css=STYLE) as demo:
|
|
413 |
|
414 |
search_in.change(
|
415 |
inputs=[search_in],
|
416 |
-
outputs=[
|
|
|
|
|
|
|
417 |
js=UPDATE_SEARCH_RESULTS,
|
418 |
fn=None
|
419 |
)
|
@@ -428,4 +755,27 @@ with gr.Blocks(css=STYLE) as demo:
|
|
428 |
]
|
429 |
)
|
430 |
|
431 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import re
|
3 |
import copy
|
4 |
import datasets
|
5 |
+
import pandas as pd
|
6 |
+
import gradio as gr
|
7 |
+
|
8 |
+
from datetime import datetime, timedelta
|
9 |
+
from datasets import Dataset
|
10 |
+
from huggingface_hub import HfApi
|
11 |
+
from huggingface_hub import create_repo
|
12 |
+
from huggingface_hub.utils import HfHubHTTPError
|
13 |
+
|
14 |
+
from paper.download import (
|
15 |
+
download_pdf_from_arxiv,
|
16 |
+
get_papers_from_hf_daily_papers,
|
17 |
+
get_papers_from_arxiv_ids
|
18 |
+
)
|
19 |
+
from paper.parser import extract_text_and_figures
|
20 |
+
from gen.gemini import get_basic_qa, get_deep_qa
|
21 |
+
import utils
|
22 |
+
|
23 |
+
from apscheduler.schedulers.background import BackgroundScheduler
|
24 |
|
25 |
STYLE = """
|
26 |
|
27 |
+
@media only screen and (max-width: 700px) {
|
28 |
+
.main {
|
29 |
+
width: 80% !important;
|
30 |
+
margin: 0 auto; /* Center the container */
|
31 |
+
}
|
32 |
}
|
33 |
|
34 |
.small-font{
|
|
|
38 |
.small-font:hover {
|
39 |
font-size: 20px !important;
|
40 |
transition: font-size 0.3s ease-out;
|
41 |
+
transition-delay: 1.5s;
|
42 |
}
|
43 |
|
44 |
.group {
|
|
|
72 |
border-radius: 0px;
|
73 |
}
|
74 |
|
75 |
+
.textbox-no-label > label > span {
|
76 |
+
display: none;
|
77 |
+
}
|
78 |
+
|
79 |
+
.exp-type > span {
|
80 |
display: none;
|
81 |
}
|
82 |
|
83 |
+
.conv-type > span {
|
84 |
display: none;
|
85 |
}
|
86 |
+
|
87 |
+
.conv-type .wrap:nth-child(3) {
|
88 |
+
width: 167px;
|
89 |
+
margin: auto;
|
90 |
+
}
|
91 |
+
|
92 |
+
button {
|
93 |
+
font-size: 10pt !important;
|
94 |
+
}
|
95 |
+
|
96 |
+
h3 {
|
97 |
+
font-size: 13pt !important;
|
98 |
+
}
|
99 |
"""
|
100 |
|
101 |
+
gemini_api_key = os.getenv("GEMINI_API_KEY")
|
102 |
+
hf_token = os.getenv("HF_TOKEN")
|
103 |
+
|
104 |
dataset_repo_id = "chansung/auto-paper-qa2"
|
105 |
+
request_arxiv_repo_id="chansung/requested-arxiv-ids-3"
|
106 |
+
|
107 |
ds = datasets.load_dataset(dataset_repo_id)
|
108 |
+
request_ds = datasets.load_dataset(request_arxiv_repo_id)
|
109 |
+
requested_arxiv_ids = []
|
110 |
+
for request_d in request_ds['train']:
|
111 |
+
arxiv_ids = request_d['Requested arXiv IDs']
|
112 |
+
requested_arxiv_ids = requested_arxiv_ids + arxiv_ids
|
113 |
+
requested_arxiv_ids_df = pd.DataFrame({'Requested arXiv IDs': requested_arxiv_ids})
|
114 |
|
115 |
title2qna = {}
|
116 |
date2qna = {}
|
117 |
longest_qans = 0
|
118 |
|
119 |
+
def filter_function(example, ids):
|
120 |
+
ids_e = example['Requested arXiv IDs']
|
121 |
+
for iid in ids:
|
122 |
+
if iid in ids_e:
|
123 |
+
ids_e.remove(iid)
|
124 |
+
example['Requested arXiv IDs'] = ids_e
|
125 |
+
|
126 |
+
print(example)
|
127 |
+
return example
|
128 |
+
|
129 |
+
def process_arxiv_ids(gemini_api, hf_repo_id, req_hf_repo_id, hf_token, how_many=10):
|
130 |
+
arxiv_ids = []
|
131 |
+
|
132 |
+
ds1 = datasets.load_dataset(req_hf_repo_id)
|
133 |
+
for d in ds1['train']:
|
134 |
+
req_arxiv_ids = d['Requested arXiv IDs']
|
135 |
+
if len(req_arxiv_ids) > 0 and req_arxiv_ids[0] != "top":
|
136 |
+
arxiv_ids = arxiv_ids + req_arxiv_ids
|
137 |
+
|
138 |
+
arxiv_ids = arxiv_ids[:how_many]
|
139 |
+
|
140 |
+
if arxiv_ids is not None and len(arxiv_ids) > 0:
|
141 |
+
print(f"1. Get metadata for the papers [{arxiv_ids}]")
|
142 |
+
papers = get_papers_from_arxiv_ids(arxiv_ids)
|
143 |
+
print("...DONE")
|
144 |
+
|
145 |
+
print("2. Generating QAs for the paper")
|
146 |
+
for paper in papers:
|
147 |
+
try:
|
148 |
+
title = paper['title']
|
149 |
+
target_date = paper['target_date']
|
150 |
+
abstract = paper['paper']['summary']
|
151 |
+
arxiv_id = paper['paper']['id']
|
152 |
+
authors = paper['paper']['authors']
|
153 |
+
|
154 |
+
print(f"...PROCESSING ON[{arxiv_id}, {title}]")
|
155 |
+
print(f"......Downloading the paper PDF")
|
156 |
+
filename = download_pdf_from_arxiv(arxiv_id)
|
157 |
+
print(f"......DONE")
|
158 |
+
|
159 |
+
print(f"......Extracting text and figures")
|
160 |
+
texts, figures = extract_text_and_figures(filename)
|
161 |
+
text =' '.join(texts)
|
162 |
+
print(f"......DONE")
|
163 |
+
|
164 |
+
print(f"......Generating the seed(basic) QAs")
|
165 |
+
qnas = get_basic_qa(text, gemini_api_key=gemini_api, trucate=30000)
|
166 |
+
qnas['title'] = title
|
167 |
+
qnas['abstract'] = abstract
|
168 |
+
qnas['authors'] = ','.join(authors)
|
169 |
+
qnas['arxiv_id'] = arxiv_id
|
170 |
+
qnas['target_date'] = target_date
|
171 |
+
qnas['full_text'] = text
|
172 |
+
print(f"......DONE")
|
173 |
+
|
174 |
+
print(f"......Generating the follow-up QAs")
|
175 |
+
qnas = get_deep_qa(text, qnas, gemini_api_key=gemini_api, trucate=30000)
|
176 |
+
del qnas["qna"]
|
177 |
+
print(f"......DONE")
|
178 |
+
|
179 |
+
print(f"......Exporting to HF Dataset repo at [{hf_repo_id}]")
|
180 |
+
utils.push_to_hf_hub(qnas, hf_repo_id, hf_token)
|
181 |
+
print(f"......DONE")
|
182 |
+
|
183 |
+
print(f"......Updating request arXiv HF Dataset repo at [{req_hf_repo_id}]")
|
184 |
+
ds1 = ds1['train'].map(
|
185 |
+
lambda example: filter_function(example, [arxiv_id])
|
186 |
+
).filter(
|
187 |
+
lambda example: len(example['Requested arXiv IDs']) > 0
|
188 |
+
)
|
189 |
+
ds1.push_to_hub(req_hf_repo_id, token=hf_token)
|
190 |
+
|
191 |
+
print(f"......DONE")
|
192 |
+
except Exception as e:
|
193 |
+
print(f".......failed due to exception {e}")
|
194 |
+
continue
|
195 |
+
|
196 |
+
HfApi(token=hf_token).restart_space(
|
197 |
+
repo_id="chansung/paper_qa", token=hf_token
|
198 |
+
)
|
199 |
+
|
200 |
+
def push_to_hf_hub(
|
201 |
+
df, repo_id, token, append=True
|
202 |
+
):
|
203 |
+
exist = False
|
204 |
+
ds = Dataset.from_pandas(df)
|
205 |
+
|
206 |
+
try:
|
207 |
+
create_repo(request_arxiv_repo_id, repo_type="dataset", token=hf_token)
|
208 |
+
except HfHubHTTPError as e:
|
209 |
+
exist = True
|
210 |
+
|
211 |
+
if exist and append:
|
212 |
+
existing_ds = datasets.load_dataset(repo_id)
|
213 |
+
ds = datasets.concatenate_datasets([existing_ds['train'], ds])
|
214 |
+
|
215 |
+
ds.push_to_hub(repo_id, token=token)
|
216 |
+
|
217 |
+
def _filter_duplicate_arxiv_ids(arxiv_ids_to_be_added):
|
218 |
+
ds1 = datasets.load_dataset("chansung/requested-arxiv-ids-3")
|
219 |
+
ds2 = datasets.load_dataset("chansung/auto-paper-qa2")
|
220 |
+
|
221 |
+
unique_arxiv_ids = set()
|
222 |
+
|
223 |
+
for d in ds1['train']:
|
224 |
+
arxiv_ids = d['Requested arXiv IDs']
|
225 |
+
unique_arxiv_ids = set(list(unique_arxiv_ids) + arxiv_ids)
|
226 |
+
|
227 |
+
for d in ds2['train']:
|
228 |
+
arxiv_id = d['arxiv_id']
|
229 |
+
unique_arxiv_ids.add(arxiv_id)
|
230 |
+
|
231 |
+
return list(set(arxiv_ids_to_be_added) - unique_arxiv_ids)
|
232 |
+
|
233 |
+
def _is_arxiv_id_valid(arxiv_id):
|
234 |
+
pattern = r"^\d{4}\.\d{5}$"
|
235 |
+
return bool(re.match(pattern, arxiv_id))
|
236 |
+
|
237 |
+
def _get_valid_arxiv_ids(arxiv_ids_str):
|
238 |
+
valid_arxiv_ids = []
|
239 |
+
invalid_arxiv_ids = []
|
240 |
+
|
241 |
+
for arxiv_id in arxiv_ids_str.split(","):
|
242 |
+
arxiv_id = arxiv_id.strip()
|
243 |
+
if _is_arxiv_id_valid(arxiv_id):
|
244 |
+
valid_arxiv_ids.append(arxiv_id)
|
245 |
+
else:
|
246 |
+
invalid_arxiv_ids.append(arxiv_id)
|
247 |
+
|
248 |
+
return valid_arxiv_ids, invalid_arxiv_ids
|
249 |
+
|
250 |
+
def add_arxiv_ids_to_queue(queue, arxiv_ids_str):
|
251 |
+
print(0)
|
252 |
+
valid_arxiv_ids, invalid_arxiv_ids = _get_valid_arxiv_ids(arxiv_ids_str)
|
253 |
+
print("01")
|
254 |
+
|
255 |
+
if len(invalid_arxiv_ids) > 0:
|
256 |
+
gr.Warning(f"found invalid arXiv ids as in {invalid_arxiv_ids}")
|
257 |
+
|
258 |
+
if len(valid_arxiv_ids) > 0:
|
259 |
+
valid_arxiv_ids = _filter_duplicate_arxiv_ids(valid_arxiv_ids)
|
260 |
+
|
261 |
+
if len(valid_arxiv_ids) > 0:
|
262 |
+
valid_arxiv_ids = [[arxiv_id] for arxiv_id in valid_arxiv_ids]
|
263 |
+
gr.Warning(f"Processing on [{valid_arxiv_ids}]. Other requested arXiv IDs not found on this list should be already processed or being processed...")
|
264 |
+
valid_arxiv_ids = pd.DataFrame({'Requested arXiv IDs': valid_arxiv_ids})
|
265 |
+
queue = pd.concat([queue, valid_arxiv_ids])
|
266 |
+
queue.reset_index(drop=True)
|
267 |
+
|
268 |
+
push_to_hf_hub(valid_arxiv_ids, request_arxiv_repo_id, hf_token)
|
269 |
+
else:
|
270 |
+
gr.Warning(f"All requested arXiv IDs are already processed or being processed...")
|
271 |
+
else:
|
272 |
+
gr.Warning(f"No valid arXiv IDs found...")
|
273 |
+
|
274 |
+
return queue
|
275 |
+
|
276 |
def count_nans(row):
|
277 |
count = 0
|
278 |
|
|
|
326 |
return (
|
327 |
gr.Markdown(f"# {selected_paper['title']}"), gr.Markdown(selected_paper["summary"]),
|
328 |
|
329 |
+
gr.Markdown(f"### π {selected_paper['0_question']}"),
|
330 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_answers:eli5']}"),
|
331 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_answers:expert']}"),
|
332 |
+
gr.Markdown(f"### ππ {selected_paper['0_additional_depth_q:follow up question']}"),
|
333 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_depth_q:answers:eli5']}"),
|
334 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_depth_q:answers:expert']}"),
|
335 |
+
gr.Markdown(f"### ππ {selected_paper['0_additional_breath_q:follow up question']}"),
|
336 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_breath_q:answers:eli5']}"),
|
337 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_breath_q:answers:expert']}"),
|
338 |
|
339 |
+
gr.Markdown(f"### π {selected_paper['1_question']}"),
|
340 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_answers:eli5']}"),
|
341 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_answers:expert']}"),
|
342 |
+
gr.Markdown(f"### ππ {selected_paper['1_additional_depth_q:follow up question']}"),
|
343 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_depth_q:answers:eli5']}"),
|
344 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_depth_q:answers:expert']}"),
|
345 |
+
gr.Markdown(f"### ππ {selected_paper['1_additional_breath_q:follow up question']}"),
|
346 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_breath_q:answers:eli5']}"),
|
347 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_breath_q:answers:expert']}"),
|
348 |
|
349 |
+
gr.Markdown(f"### π {selected_paper['2_question']}"),
|
350 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_answers:eli5']}"),
|
351 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_answers:expert']}"),
|
352 |
+
gr.Markdown(f"### ππ {selected_paper['2_additional_depth_q:follow up question']}"),
|
353 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_depth_q:answers:eli5']}"),
|
354 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_depth_q:answers:expert']}"),
|
355 |
+
gr.Markdown(f"### ππ {selected_paper['2_additional_breath_q:follow up question']}"),
|
356 |
gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_breath_q:answers:eli5']}"),
|
357 |
gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_breath_q:answers:expert']}"),
|
358 |
)
|
|
|
403 |
let titles = {list(titles)};
|
404 |
|
405 |
for (const title of titles) {{ // Assuming 'titles' is an array defined elsewhere
|
406 |
+
if (results.length > 10) {{
|
407 |
break;
|
408 |
}} else {{
|
409 |
if (title.toLowerCase().includes(searchIn.toLowerCase())) {{ // JavaScript's equivalent to Python's 'in'
|
|
|
413 |
}}
|
414 |
|
415 |
// Handle UI elements (Explanation below)
|
416 |
+
const resultElements = [1,2,3,4,5,6,7,8,9,10].map(index => {{
|
417 |
return results[index - 1] || '';
|
418 |
}});
|
419 |
|
|
|
435 |
document.getElementById('search_r3').style.display = 'block';
|
436 |
}}
|
437 |
|
438 |
+
if (resultElements[3] == '') {{
|
439 |
+
document.getElementById('search_r4').style.display = 'none';
|
440 |
+
}} else {{
|
441 |
+
document.getElementById('search_r4').style.display = 'block';
|
442 |
+
}}
|
443 |
+
|
444 |
+
if (resultElements[4] == '') {{
|
445 |
+
document.getElementById('search_r5').style.display = 'none';
|
446 |
+
}} else {{
|
447 |
+
document.getElementById('search_r5').style.display = 'block';
|
448 |
+
}}
|
449 |
+
|
450 |
+
if (resultElements[5] == '') {{
|
451 |
+
document.getElementById('search_r6').style.display = 'none';
|
452 |
+
}} else {{
|
453 |
+
document.getElementById('search_r6').style.display = 'block';
|
454 |
+
}}
|
455 |
+
|
456 |
+
if (resultElements[6] == '') {{
|
457 |
+
document.getElementById('search_r7').style.display = 'none';
|
458 |
+
}} else {{
|
459 |
+
document.getElementById('search_r7').style.display = 'block';
|
460 |
+
}}
|
461 |
+
|
462 |
+
if (resultElements[7] == '') {{
|
463 |
+
document.getElementById('search_r8').style.display = 'none';
|
464 |
+
}} else {{
|
465 |
+
document.getElementById('search_r8').style.display = 'block';
|
466 |
+
}}
|
467 |
+
|
468 |
+
if (resultElements[8] == '') {{
|
469 |
+
document.getElementById('search_r9').style.display = 'none';
|
470 |
+
}} else {{
|
471 |
+
document.getElementById('search_r9').style.display = 'block';
|
472 |
+
}}
|
473 |
+
|
474 |
+
if (resultElements[9] == '') {{
|
475 |
+
document.getElementById('search_r10').style.display = 'none';
|
476 |
+
}} else {{
|
477 |
+
document.getElementById('search_r10').style.display = 'block';
|
478 |
+
}}
|
479 |
+
|
480 |
return resultElements;
|
481 |
}} else {{
|
482 |
document.getElementById('search_r1').style.display = 'none';
|
483 |
document.getElementById('search_r2').style.display = 'none';
|
484 |
document.getElementById('search_r3').style.display = 'none';
|
485 |
+
document.getElementById('search_r4').style.display = 'none';
|
486 |
+
document.getElementById('search_r5').style.display = 'none';
|
487 |
+
document.getElementById('search_r6').style.display = 'none';
|
488 |
+
document.getElementById('search_r7').style.display = 'none';
|
489 |
+
document.getElementById('search_r8').style.display = 'none';
|
490 |
+
document.getElementById('search_r9').style.display = 'none';
|
491 |
+
document.getElementById('search_r10').style.display = 'none';
|
492 |
+
|
493 |
+
return ['', '', '', '', '', '', '', '', '', '']
|
494 |
+
}}
|
495 |
+
}}
|
496 |
+
"""
|
497 |
|
498 |
+
UPDATE_IF_TYPE = f"""
|
499 |
+
function chage_if_type(if_type) {{
|
500 |
+
if (if_type == 'Q&As') {{
|
501 |
+
document.getElementById('chat_block').style.display = 'none';
|
502 |
+
document.getElementById('qna_block').style.display = 'block';
|
503 |
+
}} else {{
|
504 |
+
document.getElementById('chat_block').style.display = 'block';
|
505 |
+
document.getElementById('qna_block').style.display = 'none';
|
506 |
}}
|
507 |
}}
|
508 |
"""
|
|
|
519 |
gr.Textbox("")
|
520 |
)
|
521 |
|
522 |
+
with gr.Blocks(css=STYLE, theme=gr.themes.Soft()) as demo:
|
523 |
gr.Markdown("# Let's explore papers with auto generated Q&As")
|
524 |
|
525 |
with gr.Column(elem_classes=["group"]):
|
|
|
540 |
)
|
541 |
|
542 |
with gr.Column(elem_classes=["no-gap"]):
|
543 |
+
search_in = gr.Textbox("", placeholder="Enter keywords to search...", elem_classes=["textbox-no-label"])
|
544 |
search_r1 = gr.Button(visible=False, elem_id="search_r1", elem_classes=["no-radius"])
|
545 |
search_r2 = gr.Button(visible=False, elem_id="search_r2", elem_classes=["no-radius"])
|
546 |
search_r3 = gr.Button(visible=False, elem_id="search_r3", elem_classes=["no-radius"])
|
547 |
+
search_r4 = gr.Button(visible=False, elem_id="search_r4", elem_classes=["no-radius"])
|
548 |
+
search_r5 = gr.Button(visible=False, elem_id="search_r5", elem_classes=["no-radius"])
|
549 |
+
search_r6 = gr.Button(visible=False, elem_id="search_r6", elem_classes=["no-radius"])
|
550 |
+
search_r7 = gr.Button(visible=False, elem_id="search_r7", elem_classes=["no-radius"])
|
551 |
+
search_r8 = gr.Button(visible=False, elem_id="search_r8", elem_classes=["no-radius"])
|
552 |
+
search_r9 = gr.Button(visible=False, elem_id="search_r9", elem_classes=["no-radius"])
|
553 |
+
search_r10 = gr.Button(visible=False, elem_id="search_r10", elem_classes=["no-radius"])
|
554 |
+
|
555 |
+
conv_type = gr.Radio(choices=["Q&As", "Chat"], value="Q&As", interactive=True, visible=False, elem_classes=["conv-type"])
|
556 |
+
|
557 |
+
with gr.Column(scale=7):
|
558 |
+
title = gr.Markdown(f"# {selected_paper['title']}")
|
559 |
+
summary = gr.Markdown(f"{selected_paper['summary']}", elem_classes=["small-font"])
|
560 |
+
|
561 |
+
with gr.Column(elem_id="chat_block", visible=False):
|
562 |
+
gr.Chatbot([("hello", "world"), ("how", "are you?")])
|
563 |
+
|
564 |
+
with gr.Column(elem_id="qna_block", visible=True):
|
565 |
+
with gr.Row():
|
566 |
+
with gr.Column(scale=7):
|
567 |
+
gr.Markdown("## Auto generated Questions & Answers")
|
568 |
+
|
569 |
+
exp_type = gr.Radio(choices=["ELI5", "Technical"], value="ELI5", elem_classes=["exp-type"], scale=3)
|
570 |
+
|
571 |
+
# 1
|
572 |
+
with gr.Column(elem_classes=["group"], visible=True) as q_0:
|
573 |
+
basic_q_0 = gr.Markdown(f"### π {selected_paper['0_question']}")
|
574 |
+
basic_q_eli5_0 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_answers:eli5']}", elem_classes=["small-font"])
|
575 |
+
basic_q_expert_0 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_answers:expert']}", visible=False, elem_classes=["small-font"])
|
576 |
+
|
577 |
+
with gr.Accordion("Additional question #1", open=False, elem_classes=["accordion"]) as aq_0_0:
|
578 |
+
depth_q_0 = gr.Markdown(f"### ππ {selected_paper['0_additional_depth_q:follow up question']}")
|
579 |
+
depth_q_eli5_0 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_depth_q:answers:eli5']}", elem_classes=["small-font"])
|
580 |
+
depth_q_expert_0 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_depth_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
581 |
+
|
582 |
+
with gr.Accordion("Additional question #2", open=False, elem_classes=["accordion"]) as aq_0_1:
|
583 |
+
breath_q_0 = gr.Markdown(f"### ππ {selected_paper['0_additional_breath_q:follow up question']}")
|
584 |
+
breath_q_eli5_0 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['0_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
|
585 |
+
breath_q_expert_0 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['0_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
586 |
+
|
587 |
+
# 2
|
588 |
+
with gr.Column(elem_classes=["group"], visible=True) as q_1:
|
589 |
+
basic_q_1 = gr.Markdown(f"### π {selected_paper['1_question']}")
|
590 |
+
basic_q_eli5_1 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_answers:eli5']}", elem_classes=["small-font"])
|
591 |
+
basic_q_expert_1 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_answers:expert']}", visible=False, elem_classes=["small-font"])
|
592 |
+
|
593 |
+
with gr.Accordion("Additional question #1", open=False, elem_classes=["accordion"]) as aq_1_0:
|
594 |
+
depth_q_1 = gr.Markdown(f"### ππ {selected_paper['1_additional_depth_q:follow up question']}")
|
595 |
+
depth_q_eli5_1 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_depth_q:answers:eli5']}", elem_classes=["small-font"])
|
596 |
+
depth_q_expert_1 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_depth_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
597 |
+
|
598 |
+
with gr.Accordion("Additional question #2", open=False, elem_classes=["accordion"]) as aq_1_1:
|
599 |
+
breath_q_1 = gr.Markdown(f"### ππ {selected_paper['1_additional_breath_q:follow up question']}")
|
600 |
+
breath_q_eli5_1 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['1_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
|
601 |
+
breath_q_expert_1 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['1_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
602 |
+
|
603 |
+
# 3
|
604 |
+
with gr.Column(elem_classes=["group"], visible=True) as q_2:
|
605 |
+
basic_q_2 = gr.Markdown(f"### π {selected_paper['2_question']}")
|
606 |
+
basic_q_eli5_2 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_answers:eli5']}", elem_classes=["small-font"])
|
607 |
+
basic_q_expert_2 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_answers:expert']}", visible=False, elem_classes=["small-font"])
|
608 |
+
|
609 |
+
with gr.Accordion("Additional question #1", open=False, elem_classes=["accordion"]) as aq_2_0:
|
610 |
+
depth_q_2 = gr.Markdown(f"### ππ {selected_paper['2_additional_depth_q:follow up question']}")
|
611 |
+
depth_q_eli5_2 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_depth_q:answers:eli5']}", elem_classes=["small-font"])
|
612 |
+
depth_q_expert_2 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_depth_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
613 |
+
|
614 |
+
with gr.Accordion("Additional question #2", open=False, elem_classes=["accordion"]) as aq_2_1:
|
615 |
+
breath_q_2 = gr.Markdown(f"### ππ {selected_paper['2_additional_breath_q:follow up question']}")
|
616 |
+
breath_q_eli5_2 = gr.Markdown(f"βͺ **(ELI5)** {selected_paper['2_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
|
617 |
+
breath_q_expert_2 = gr.Markdown(f"βͺ **(Technical)** {selected_paper['2_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
|
618 |
+
|
619 |
+
gr.Markdown("## Request any arXiv ids")
|
620 |
+
arxiv_queue = gr.Dataframe(
|
621 |
+
headers=["Requested arXiv IDs"], col_count=(1, "fixed"),
|
622 |
+
value=requested_arxiv_ids_df,
|
623 |
+
datatype=["str"],
|
624 |
+
interactive=False
|
625 |
+
)
|
626 |
+
|
627 |
+
arxiv_id_enter = gr.Textbox(placeholder="Enter comma separated arXiv IDs...", elem_classes=["textbox-no-label"])
|
628 |
+
arxiv_id_enter.submit(
|
629 |
+
add_arxiv_ids_to_queue,
|
630 |
+
[arxiv_queue, arxiv_id_enter],
|
631 |
+
arxiv_queue
|
632 |
+
)
|
633 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
634 |
|
635 |
gr.Markdown("The target papers are collected from [Hugging Face π€ Daily Papers](https://huggingface.co/papers) on a daily basis. "
|
636 |
"The entire data is generated by [Google's Gemini 1.0](https://deepmind.google/technologies/gemini/) Pro. "
|
637 |
"If you are curious how it is done, visit the [Auto Paper Q&A Generation project repository](https://github.com/deep-diver/auto-paper-analysis) "
|
638 |
"Also, the generated dataset is hosted on Hugging Face π€ Dataset repository as well([Link](https://huggingface.co/datasets/chansung/auto-paper-qa2)). ")
|
639 |
|
640 |
+
search_r1.click(set_date, search_r1, date_dd).then(
|
|
|
|
|
|
|
|
|
641 |
set_papers,
|
642 |
inputs=[date_dd, search_r1],
|
643 |
outputs=[papers_dd, search_in]
|
644 |
)
|
645 |
|
646 |
+
search_r2.click(set_date, search_r2, date_dd).then(
|
|
|
|
|
|
|
|
|
647 |
set_papers,
|
648 |
inputs=[date_dd, search_r2],
|
649 |
outputs=[papers_dd, search_in]
|
650 |
)
|
651 |
|
652 |
+
search_r3.click(set_date, search_r3, date_dd).then(
|
|
|
|
|
|
|
|
|
653 |
set_papers,
|
654 |
inputs=[date_dd, search_r3],
|
655 |
outputs=[papers_dd, search_in]
|
656 |
)
|
657 |
|
658 |
+
search_r4.click(set_date, search_r4, date_dd).then(
|
659 |
+
set_papers,
|
660 |
+
inputs=[date_dd, search_r4],
|
661 |
+
outputs=[papers_dd, search_in]
|
662 |
+
)
|
663 |
+
|
664 |
+
search_r5.click(set_date, search_r5, date_dd).then(
|
665 |
+
set_papers,
|
666 |
+
inputs=[date_dd, search_r5],
|
667 |
+
outputs=[papers_dd, search_in]
|
668 |
+
)
|
669 |
+
|
670 |
+
search_r6.click(set_date, search_r6, date_dd).then(
|
671 |
+
set_papers,
|
672 |
+
inputs=[date_dd, search_r6],
|
673 |
+
outputs=[papers_dd, search_in]
|
674 |
+
)
|
675 |
+
|
676 |
+
search_r7.click(set_date, search_r7, date_dd).then(
|
677 |
+
set_papers,
|
678 |
+
inputs=[date_dd, search_r7],
|
679 |
+
outputs=[papers_dd, search_in]
|
680 |
+
)
|
681 |
+
|
682 |
+
search_r8.click(set_date, search_r8, date_dd).then(
|
683 |
+
set_papers,
|
684 |
+
inputs=[date_dd, search_r8],
|
685 |
+
outputs=[papers_dd, search_in]
|
686 |
+
)
|
687 |
+
|
688 |
+
search_r9.click(set_date, search_r9, date_dd).then(
|
689 |
+
set_papers,
|
690 |
+
inputs=[date_dd, search_r9],
|
691 |
+
outputs=[papers_dd, search_in]
|
692 |
+
)
|
693 |
+
|
694 |
+
search_r10.click(set_date, search_r10, date_dd).then(
|
695 |
+
set_papers,
|
696 |
+
inputs=[date_dd, search_r10],
|
697 |
+
outputs=[papers_dd, search_in]
|
698 |
+
)
|
699 |
+
|
700 |
+
date_dd.input(get_papers, date_dd, papers_dd).then(
|
701 |
set_paper,
|
702 |
[date_dd, papers_dd],
|
703 |
[
|
|
|
737 |
|
738 |
search_in.change(
|
739 |
inputs=[search_in],
|
740 |
+
outputs=[
|
741 |
+
search_r1, search_r2, search_r3, search_r4, search_r5,
|
742 |
+
search_r6, search_r7, search_r8, search_r9, search_r10
|
743 |
+
],
|
744 |
js=UPDATE_SEARCH_RESULTS,
|
745 |
fn=None
|
746 |
)
|
|
|
755 |
]
|
756 |
)
|
757 |
|
758 |
+
conv_type.select(
|
759 |
+
inputs=[conv_type],
|
760 |
+
js=UPDATE_IF_TYPE,
|
761 |
+
outputs=None,
|
762 |
+
fn=None
|
763 |
+
)
|
764 |
+
|
765 |
+
start_date = datetime.now() + timedelta(minutes=1)
|
766 |
+
scheduler = BackgroundScheduler()
|
767 |
+
scheduler.add_job(
|
768 |
+
process_arxiv_ids,
|
769 |
+
trigger='interval',
|
770 |
+
seconds=3600,
|
771 |
+
args=[
|
772 |
+
gemini_api_key,
|
773 |
+
dataset_repo_id,
|
774 |
+
request_arxiv_repo_id,
|
775 |
+
hf_token
|
776 |
+
],
|
777 |
+
start_date=start_date
|
778 |
+
)
|
779 |
+
scheduler.start()
|
780 |
+
|
781 |
+
demo.launch(share=True, debug=True)
|
constants/prompts.toml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[basic_qa]
|
2 |
+
prompt = """
|
3 |
+
come up with the 6 questions and answers that could be commonly asked by people about the following paper.
|
4 |
+
There should be two types of answers included, one for expert and the other for ELI5.
|
5 |
+
Your response should be recorded in a JSON format as ```json{"title": text, "summary": text, "qna": [{"question": "answers": {"eli5": text, "expert": text}}, ...]}```
|
6 |
+
"""
|
7 |
+
|
8 |
+
[deep_qa]
|
9 |
+
prompt = """
|
10 |
+
Paper title: $title
|
11 |
+
Previous question: $previous_question
|
12 |
+
The answer on the previous question: $previous_answer
|
13 |
+
|
14 |
+
Based on the previous question and answer above, and based on the paper content below, suggest follow-up question and answers in $tone manner.
|
15 |
+
There should be two types of answers included, one for expert and the other for ELI5.
|
16 |
+
Your response should be recorded in a JSON format as ```json{"follow up question": text, "answers": {"eli5": text, "expert": text}}```
|
17 |
+
"""
|
date_iterator.sh
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/bin/bash
|
2 |
+
|
3 |
+
# Set start and end dates (format YYYY-MM-DD)
|
4 |
+
start_date=$1
|
5 |
+
end_date=$2
|
6 |
+
hf_repo_id=$3
|
7 |
+
|
8 |
+
# Convert dates into seconds since epoch (for easier calculations)
|
9 |
+
start_seconds=$(date -j -f "%Y-%m-%d" "$start_date" "+%s")
|
10 |
+
end_seconds=$(date -j -f "%Y-%m-%d" "$end_date" "+%s")
|
11 |
+
|
12 |
+
# Iterate through dates
|
13 |
+
current_seconds=$start_seconds
|
14 |
+
while [[ $current_seconds -le $end_seconds ]]; do
|
15 |
+
current_date=$(date -j -r $current_seconds "+%Y-%m-%d")
|
16 |
+
|
17 |
+
# Replace with your actual program execution
|
18 |
+
echo "Running program for date: $current_date"
|
19 |
+
python app.py --target-date $current_date \
|
20 |
+
--gemini-api $GEMINI_API_KEY \
|
21 |
+
--hf-token $HF_ACCESS_TOKEN \
|
22 |
+
--hf-repo-id $hf_repo_id \
|
23 |
+
--hf-daily-papers
|
24 |
+
|
25 |
+
current_seconds=$((current_seconds + 86400)) # Add 1 day (86400 seconds)
|
26 |
+
done
|
27 |
+
|
gen/gemini.py
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import ast
|
2 |
+
import copy
|
3 |
+
import toml
|
4 |
+
from string import Template
|
5 |
+
from pathlib import Path
|
6 |
+
from flatdict import FlatDict
|
7 |
+
import google.generativeai as genai
|
8 |
+
|
9 |
+
from gen.utils import parse_first_json_snippet
|
10 |
+
|
11 |
+
def determine_model_name(given_image=None):
|
12 |
+
if given_image is None:
|
13 |
+
return "gemini-pro"
|
14 |
+
else:
|
15 |
+
return "gemini-pro-vision"
|
16 |
+
|
17 |
+
def construct_image_part(given_image):
|
18 |
+
return {
|
19 |
+
"mime_type": "image/jpeg",
|
20 |
+
"data": given_image
|
21 |
+
}
|
22 |
+
|
23 |
+
def call_gemini(prompt="", API_KEY=None, given_text=None, given_image=None, generation_config=None, safety_settings=None):
|
24 |
+
genai.configure(api_key=API_KEY)
|
25 |
+
|
26 |
+
if generation_config is None:
|
27 |
+
generation_config = {
|
28 |
+
"temperature": 0.8,
|
29 |
+
"top_p": 1,
|
30 |
+
"top_k": 32,
|
31 |
+
"max_output_tokens": 4096,
|
32 |
+
}
|
33 |
+
|
34 |
+
if safety_settings is None:
|
35 |
+
safety_settings = [
|
36 |
+
{
|
37 |
+
"category": "HARM_CATEGORY_HARASSMENT",
|
38 |
+
"threshold": "BLOCK_NONE"
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"category": "HARM_CATEGORY_HATE_SPEECH",
|
42 |
+
"threshold": "BLOCK_NONE"
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
|
46 |
+
"threshold": "BLOCK_NONE"
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"category": "HARM_CATEGORY_DANGEROUS_CONTENT",
|
50 |
+
"threshold": "BLOCK_NONE"
|
51 |
+
},
|
52 |
+
]
|
53 |
+
|
54 |
+
model_name = determine_model_name(given_image)
|
55 |
+
model = genai.GenerativeModel(model_name=model_name,
|
56 |
+
generation_config=generation_config,
|
57 |
+
safety_settings=safety_settings)
|
58 |
+
|
59 |
+
USER_PROMPT = prompt
|
60 |
+
if given_text is not None:
|
61 |
+
USER_PROMPT += f"""{prompt}
|
62 |
+
------------------------------------------------
|
63 |
+
{given_text}
|
64 |
+
"""
|
65 |
+
prompt_parts = [USER_PROMPT]
|
66 |
+
if given_image is not None:
|
67 |
+
prompt_parts.append(construct_image_part(given_image))
|
68 |
+
|
69 |
+
response = model.generate_content(prompt_parts)
|
70 |
+
return response.text
|
71 |
+
|
72 |
+
def try_out(prompt, given_text, gemini_api_key, given_image=None, retry_num=5):
|
73 |
+
qna_json = None
|
74 |
+
cur_retry = 0
|
75 |
+
|
76 |
+
while qna_json is None and cur_retry < retry_num:
|
77 |
+
try:
|
78 |
+
qna = call_gemini(
|
79 |
+
prompt=prompt,
|
80 |
+
given_text=given_text,
|
81 |
+
given_image=given_image,
|
82 |
+
API_KEY=gemini_api_key
|
83 |
+
)
|
84 |
+
|
85 |
+
qna_json = parse_first_json_snippet(qna)
|
86 |
+
except Exception as e:
|
87 |
+
cur_retry = cur_retry + 1
|
88 |
+
print(f"......retry {e}")
|
89 |
+
|
90 |
+
return qna_json
|
91 |
+
|
92 |
+
def get_basic_qa(text, gemini_api_key, trucate=7000):
|
93 |
+
prompts = toml.load(Path('.') / 'constants' / 'prompts.toml')
|
94 |
+
basic_qa = try_out(prompts['basic_qa']['prompt'], text[:trucate], gemini_api_key=gemini_api_key)
|
95 |
+
return basic_qa
|
96 |
+
|
97 |
+
|
98 |
+
def get_deep_qa(text, basic_qa, gemini_api_key, trucate=7000):
|
99 |
+
prompts = toml.load(Path('.') / 'constants' / 'prompts.toml')
|
100 |
+
|
101 |
+
title = basic_qa['title']
|
102 |
+
qnas = copy.deepcopy(basic_qa['qna'])
|
103 |
+
|
104 |
+
for idx, qna in enumerate(qnas):
|
105 |
+
q = qna['question']
|
106 |
+
a_expert = qna['answers']['expert']
|
107 |
+
|
108 |
+
depth_search_prompt = Template(prompts['deep_qa']['prompt']).substitute(
|
109 |
+
title=title, previous_question=q, previous_answer=a_expert, tone="in-depth"
|
110 |
+
)
|
111 |
+
breath_search_prompt = Template(prompts['deep_qa']['prompt']).substitute(
|
112 |
+
title=title, previous_question=q, previous_answer=a_expert, tone="broad"
|
113 |
+
)
|
114 |
+
|
115 |
+
depth_search_response = {}
|
116 |
+
breath_search_response = {}
|
117 |
+
|
118 |
+
while 'follow up question' not in depth_search_response or \
|
119 |
+
'answers' not in depth_search_response or \
|
120 |
+
'eli5' not in depth_search_response['answers'] or \
|
121 |
+
'expert' not in depth_search_response['answers']:
|
122 |
+
depth_search_response = try_out(depth_search_prompt, text[:trucate], gemini_api_key=gemini_api_key)
|
123 |
+
|
124 |
+
while 'follow up question' not in breath_search_response or \
|
125 |
+
'answers' not in breath_search_response or \
|
126 |
+
'eli5' not in breath_search_response['answers'] or \
|
127 |
+
'expert' not in breath_search_response['answers']:
|
128 |
+
breath_search_response = try_out(breath_search_prompt, text[:trucate], gemini_api_key=gemini_api_key)
|
129 |
+
|
130 |
+
if depth_search_response is not None:
|
131 |
+
qna['additional_depth_q'] = depth_search_response
|
132 |
+
if breath_search_response is not None:
|
133 |
+
qna['additional_breath_q'] = breath_search_response
|
134 |
+
|
135 |
+
qna = FlatDict(qna)
|
136 |
+
qna_tmp = copy.deepcopy(qna)
|
137 |
+
for k in qna_tmp:
|
138 |
+
value = qna.pop(k)
|
139 |
+
qna[f'{idx}_{k}'] = value
|
140 |
+
basic_qa.update(ast.literal_eval(str(qna)))
|
141 |
+
|
142 |
+
return basic_qa
|
gen/utils.py
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
|
3 |
+
def find_json_snippet(raw_snippet):
|
4 |
+
json_parsed_string = None
|
5 |
+
|
6 |
+
json_start_index = raw_snippet.find('{')
|
7 |
+
json_end_index = raw_snippet.rfind('}')
|
8 |
+
|
9 |
+
if json_start_index >= 0 and json_end_index >= 0:
|
10 |
+
json_snippet = raw_snippet[json_start_index:json_end_index+1]
|
11 |
+
try:
|
12 |
+
json_parsed_string = json.loads(json_snippet, strict=False)
|
13 |
+
except:
|
14 |
+
raise ValueError('......failed to parse string into JSON format')
|
15 |
+
else:
|
16 |
+
raise ValueError('......No JSON code snippet found in string.')
|
17 |
+
|
18 |
+
return json_parsed_string
|
19 |
+
|
20 |
+
def parse_first_json_snippet(snippet):
|
21 |
+
json_parsed_string = None
|
22 |
+
|
23 |
+
if isinstance(snippet, list):
|
24 |
+
for snippet_piece in snippet:
|
25 |
+
try:
|
26 |
+
json_parsed_string = find_json_snippet(snippet_piece)
|
27 |
+
return json_parsed_string
|
28 |
+
except:
|
29 |
+
pass
|
30 |
+
else:
|
31 |
+
try:
|
32 |
+
json_parsed_string = find_json_snippet(snippet)
|
33 |
+
except Exception as e:
|
34 |
+
print(e)
|
35 |
+
raise ValueError()
|
36 |
+
|
37 |
+
return json_parsed_string
|
outputs.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
paper/download.py
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import json
|
3 |
+
import requests
|
4 |
+
import datetime
|
5 |
+
from datetime import date
|
6 |
+
from datetime import datetime
|
7 |
+
import xml.etree.ElementTree as ET
|
8 |
+
from requests.exceptions import HTTPError
|
9 |
+
|
10 |
+
def _get_today():
|
11 |
+
return str(date.today())
|
12 |
+
|
13 |
+
def _download_pdf_from_arxiv(filename):
|
14 |
+
url = f'https://arxiv.org/pdf/{filename}'
|
15 |
+
response = requests.get(url)
|
16 |
+
if response.status_code == 200:
|
17 |
+
return response.content
|
18 |
+
else:
|
19 |
+
raise Exception(f"Failed to download pdf for arXiv id {filename}")
|
20 |
+
|
21 |
+
def download_pdf_from_arxiv(arxiv_id):
|
22 |
+
filename = f"{arxiv_id}.pdf"
|
23 |
+
pdf_content = _download_pdf_from_arxiv(filename)
|
24 |
+
|
25 |
+
# Save the pdf content to a file
|
26 |
+
with open(filename, "wb") as f:
|
27 |
+
f.write(pdf_content)
|
28 |
+
|
29 |
+
return filename
|
30 |
+
|
31 |
+
def _get_papers_from_hf_daily_papers(target_date):
|
32 |
+
if target_date is None:
|
33 |
+
target_date = _get_today()
|
34 |
+
print(f"target_date is not set => scrap today's papers [{target_date}]")
|
35 |
+
url = f"https://huggingface.co/api/daily_papers?date={target_date}"
|
36 |
+
|
37 |
+
response = requests.get(url)
|
38 |
+
|
39 |
+
if response.status_code == 200:
|
40 |
+
return target_date, response.text
|
41 |
+
else:
|
42 |
+
raise HTTPError(f"Error fetching data. Status code: {response.status_code}")
|
43 |
+
|
44 |
+
def get_papers_from_hf_daily_papers(target_date):
|
45 |
+
target_date, results = _get_papers_from_hf_daily_papers(target_date)
|
46 |
+
results = json.loads(results)
|
47 |
+
for result in results:
|
48 |
+
result["target_date"] = target_date
|
49 |
+
return target_date, results
|
50 |
+
|
51 |
+
|
52 |
+
def _get_paper_xml_by_arxiv_id(arxiv_id):
|
53 |
+
url = f"http://export.arxiv.org/api/query?search_query=id:{arxiv_id}&start=0&max_results=1"
|
54 |
+
return requests.get(url)
|
55 |
+
|
56 |
+
def _is_arxiv_id_valid(arxiv_id):
|
57 |
+
pattern = r"^\d{4}\.\d{5}$"
|
58 |
+
return bool(re.match(pattern, arxiv_id))
|
59 |
+
|
60 |
+
def _get_paper_metadata_by_arxiv_id(response):
|
61 |
+
root = ET.fromstring(response.content)
|
62 |
+
|
63 |
+
# Example: Extracting title, authors, and abstract
|
64 |
+
title = root.find('{http://www.w3.org/2005/Atom}entry/{http://www.w3.org/2005/Atom}title').text
|
65 |
+
authors = [author.find('{http://www.w3.org/2005/Atom}name').text for author in root.findall('{http://www.w3.org/2005/Atom}entry/{http://www.w3.org/2005/Atom}author')]
|
66 |
+
abstract = root.find('{http://www.w3.org/2005/Atom}entry/{http://www.w3.org/2005/Atom}summary').text
|
67 |
+
target_date = root.find('{http://www.w3.org/2005/Atom}entry/{http://www.w3.org/2005/Atom}published').text
|
68 |
+
|
69 |
+
return title, authors, abstract, target_date
|
70 |
+
|
71 |
+
def get_papers_from_arxiv_ids(arxiv_ids):
|
72 |
+
results = []
|
73 |
+
|
74 |
+
for arxiv_id in arxiv_ids:
|
75 |
+
print(arxiv_id)
|
76 |
+
if _is_arxiv_id_valid(arxiv_id):
|
77 |
+
try:
|
78 |
+
xml_data = _get_paper_xml_by_arxiv_id(arxiv_id)
|
79 |
+
title, authors, abstract, target_date = _get_paper_metadata_by_arxiv_id(xml_data)
|
80 |
+
|
81 |
+
datetime_obj = datetime.strptime(target_date, "%Y-%m-%dT%H:%M:%SZ")
|
82 |
+
formatted_date = datetime_obj.strftime("%Y-%m-%d")
|
83 |
+
|
84 |
+
results.append(
|
85 |
+
{
|
86 |
+
"title": title,
|
87 |
+
"target_date": formatted_date,
|
88 |
+
"paper": {
|
89 |
+
"summary": abstract,
|
90 |
+
"id": arxiv_id,
|
91 |
+
"authors" : authors,
|
92 |
+
}
|
93 |
+
}
|
94 |
+
)
|
95 |
+
except:
|
96 |
+
print("......something wrong happend when downloading metadata")
|
97 |
+
print("......this usually happens when you try out the today's published paper")
|
98 |
+
continue
|
99 |
+
else:
|
100 |
+
print(f"......not a valid arXiv ID[{arxiv_id}]")
|
101 |
+
|
102 |
+
return results
|
paper/parser.py
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import fitz
|
3 |
+
import PyPDF2
|
4 |
+
|
5 |
+
def extract_text_and_figures(pdf_path):
|
6 |
+
"""
|
7 |
+
Extracts text and figures from a PDF file.
|
8 |
+
|
9 |
+
Args:
|
10 |
+
pdf_path (str): The path to the PDF file.
|
11 |
+
|
12 |
+
Returns:
|
13 |
+
tuple: A tuple containing two lists:
|
14 |
+
* A list of extracted text blocks.
|
15 |
+
* A list of extracted figures (as bytes).
|
16 |
+
"""
|
17 |
+
|
18 |
+
texts = []
|
19 |
+
figures = []
|
20 |
+
|
21 |
+
# Open the PDF using PyMuPDF (fitz) for image extraction
|
22 |
+
doc = fitz.open(pdf_path)
|
23 |
+
for page_num, page in enumerate(doc):
|
24 |
+
text = page.get_text("text") # Extract text as plain text
|
25 |
+
texts.append(text)
|
26 |
+
|
27 |
+
# Process images on the page
|
28 |
+
image_list = page.get_images()
|
29 |
+
for image_index, img in enumerate(image_list):
|
30 |
+
xref = img[0] # Image XREF
|
31 |
+
pix = fitz.Pixmap(doc, xref) # Create Pixmap image
|
32 |
+
|
33 |
+
# Save image in desired format (here, PNG)
|
34 |
+
if pix.n < 5: # Grayscale or RGB
|
35 |
+
img_bytes = pix.tobytes("png")
|
36 |
+
else: # CMYK: Convert to RGB first
|
37 |
+
pix = fitz.Pixmap(fitz.csRGB, pix)
|
38 |
+
img_bytes = pix.tobytes("png")
|
39 |
+
|
40 |
+
figures.append(img_bytes)
|
41 |
+
|
42 |
+
# Extract additional text using PyPDF2 (in case fitz didn't get everything)
|
43 |
+
with open(pdf_path, 'rb') as pdf_file:
|
44 |
+
pdf_reader = PyPDF2.PdfReader(pdf_file)
|
45 |
+
for page_num in range(len(pdf_reader.pages)):
|
46 |
+
page = pdf_reader.pages[page_num]
|
47 |
+
text = page.extract_text()
|
48 |
+
texts.append(text)
|
49 |
+
|
50 |
+
try:
|
51 |
+
os.remove(pdf_path)
|
52 |
+
except FileNotFoundError:
|
53 |
+
print(f"File '{pdf_path}' not found.")
|
54 |
+
except PermissionError:
|
55 |
+
print(f"Unable to remove '{pdf_path}'. Check permissions.")
|
56 |
+
|
57 |
+
return texts, figures
|
requirements.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
google-generativeai
|
2 |
+
pypdf2
|
3 |
+
PyMuPDF
|
4 |
+
gradio
|
5 |
+
requests
|
6 |
+
toml
|
7 |
+
datasets
|
8 |
+
flatdict
|
9 |
+
APScheduler
|
utils.py
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
import datasets
|
3 |
+
from datasets import Dataset
|
4 |
+
from huggingface_hub import create_repo
|
5 |
+
from huggingface_hub.utils import HfHubHTTPError
|
6 |
+
|
7 |
+
def push_to_hf_hub(
|
8 |
+
qnas, repo_id, token, append=True
|
9 |
+
):
|
10 |
+
print(1)
|
11 |
+
exist = False
|
12 |
+
df = pd.DataFrame([qnas])
|
13 |
+
ds = Dataset.from_pandas(df)
|
14 |
+
ds = ds.cast_column("target_date", datasets.features.Value("timestamp[s]"))
|
15 |
+
|
16 |
+
print(2)
|
17 |
+
try:
|
18 |
+
create_repo(repo_id, repo_type="dataset", token=token)
|
19 |
+
except HfHubHTTPError as e:
|
20 |
+
exist = True
|
21 |
+
|
22 |
+
if exist and append:
|
23 |
+
print(3)
|
24 |
+
existing_ds = datasets.load_dataset(repo_id)
|
25 |
+
ds = datasets.concatenate_datasets([existing_ds['train'], ds])
|
26 |
+
|
27 |
+
print(4)
|
28 |
+
ds.push_to_hub(repo_id, token=token)
|