File size: 3,042 Bytes
aaf47df 20e59fb aaf47df 20e59fb 3a0a966 aaf47df 20e59fb aaf47df 20e59fb 3a0a966 aaf47df b4ee178 20e59fb b4ee178 aaf47df 02bfdfc aaf47df |
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 |
import gradio as gr
import requests
from cachetools import cached, TTLCache
CACHE_TIME = 60 * 60 * 12 # 12 hours
def parse_arxiv_id_from_paper_url(url):
return url.split("/")[-1]
@cached(cache=TTLCache(maxsize=500, ttl=CACHE_TIME))
def get_recommendations_from_semantic_scholar(semantic_scholar_id: str):
try:
r = requests.post(
"https://api.semanticscholar.org/recommendations/v1/papers/",
json={
"positivePaperIds": [semantic_scholar_id],
},
params={"fields": "externalIds,title,year", "limit": 10},
)
return r.json()["recommendedPapers"]
except KeyError as e:
raise gr.Error(
"Error getting recommendations, if this is a new paper it may not yet have"
" been indexed by Semantic Scholar."
) from e
def filter_recommendations(recommendations, max_paper_count=5):
# include only arxiv papers
arxiv_paper = [
r for r in recommendations if r["externalIds"].get("ArXiv", None) is not None
]
if len(arxiv_paper) > max_paper_count:
arxiv_paper = arxiv_paper[:max_paper_count]
return arxiv_paper
@cached(cache=TTLCache(maxsize=500, ttl=CACHE_TIME))
def get_paper_title_from_arxiv_id(arxiv_id):
try:
return requests.get(f"https://huggingface.co/api/papers/{arxiv_id}").json()[
"title"
]
except Exception as e:
print(f"Error getting paper title for {arxiv_id}: {e}")
raise gr.Error("Error getting paper title for {arxiv_id}: {e}") from e
def format_recommendation_into_markdown(arxiv_id, recommendations):
# title = get_paper_title_from_arxiv_id(arxiv_id)
# url = f"https://huggingface.co/papers/{arxiv_id}"
# comment = f"Recommended papers for [{title}]({url})\n\n"
comment = "The following papers were recommended by the Semantic Scholar API \n\n"
for r in recommendations:
hub_paper_url = f"https://huggingface.co/papers/{r['externalIds']['ArXiv']}"
comment += f"* [{r['title']}]({hub_paper_url}) ({r['year']})\n"
return comment
def return_recommendations(url):
arxiv_id = parse_arxiv_id_from_paper_url(url)
recommendations = get_recommendations_from_semantic_scholar(f"ArXiv:{arxiv_id}")
filtered_recommendations = filter_recommendations(recommendations)
return format_recommendation_into_markdown(arxiv_id, filtered_recommendations)
title = "Semantic Scholar Paper Recommender"
description = (
"Paste a link to a paper on Hugging Face Papers and get recommendations for similar"
" papers from Semantic Scholar.**Note**: Some papers may not have recommendations"
" yet if they are new or have not been indexed by Semantic Scholar."
)
examples = [
"https://huggingface.co/papers/2309.12307",
"https://huggingface.co/papers/2211.10086",
]
interface = gr.Interface(
return_recommendations,
gr.Textbox(lines=1),
gr.Markdown(),
examples=examples,
title=title,
description=description,
)
interface.launch()
|