draft

app.py

@@ -0,0 +1,84 @@
+import gradio as gr
+import requests
+
+
+def parse_arxiv_id_from_paper_url(url):
+    return url.split("/")[-1]
+
+
+def get_recommendations_from_semantic_scholar(semantic_scholar_id: str):
+    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"]
+
+
+# arxiv_id = parse_arxiv_id_from_paper_url(paper_page)
+
+# recommendations = get_recommendations_from_semantic_scholar(f"ArXiv:{arxiv_id}")
+# print(recommendations)
+
+
+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
+
+
+# filtered_recommendations = filter_recommendations(recommendations)
+
+
+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."
+)
+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()

requirements.in

@@ -0,0 +1,2 @@
+gradio 
+requests

requirements.txt

@@ -0,0 +1,180 @@
+#
+# This file is autogenerated by pip-compile with Python 3.11
+# by the following command:
+#
+#    pip-compile
+#
+aiofiles==23.2.1
+    # via gradio
+altair==5.1.1
+    # via gradio
+annotated-types==0.5.0
+    # via pydantic
+anyio==3.7.1
+    # via
+    #   fastapi
+    #   httpcore
+    #   starlette
+attrs==23.1.0
+    # via
+    #   jsonschema
+    #   referencing
+certifi==2023.7.22
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.2.0
+    # via requests
+click==8.1.7
+    # via uvicorn
+contourpy==1.1.1
+    # via matplotlib
+cycler==0.11.0
+    # via matplotlib
+fastapi==0.103.1
+    # via gradio
+ffmpy==0.3.1
+    # via gradio
+filelock==3.12.4
+    # via huggingface-hub
+fonttools==4.42.1
+    # via matplotlib
+fsspec==2023.9.2
+    # via
+    #   gradio-client
+    #   huggingface-hub
+gradio==3.45.1
+    # via -r requirements.in
+gradio-client==0.5.2
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==0.18.0
+    # via httpx
+httpx==0.25.0
+    # via
+    #   gradio
+    #   gradio-client
+huggingface-hub==0.17.3
+    # via
+    #   gradio
+    #   gradio-client
+idna==3.4
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+importlib-resources==6.1.0
+    # via gradio
+jinja2==3.1.2
+    # via
+    #   altair
+    #   gradio
+jsonschema==4.19.1
+    # via altair
+jsonschema-specifications==2023.7.1
+    # via jsonschema
+kiwisolver==1.4.5
+    # via matplotlib
+markupsafe==2.1.3
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.8.0
+    # via gradio
+numpy==1.26.0
+    # via
+    #   altair
+    #   contourpy
+    #   gradio
+    #   matplotlib
+    #   pandas
+orjson==3.9.7
+    # via gradio
+packaging==23.1
+    # via
+    #   altair
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   matplotlib
+pandas==2.1.1
+    # via
+    #   altair
+    #   gradio
+pillow==10.0.1
+    # via
+    #   gradio
+    #   matplotlib
+pydantic==2.4.1
+    # via
+    #   fastapi
+    #   gradio
+pydantic-core==2.10.1
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pyparsing==3.1.1
+    # via matplotlib
+python-dateutil==2.8.2
+    # via
+    #   matplotlib
+    #   pandas
+python-multipart==0.0.6
+    # via gradio
+pytz==2023.3.post1
+    # via pandas
+pyyaml==6.0.1
+    # via
+    #   gradio
+    #   huggingface-hub
+referencing==0.30.2
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+requests==2.31.0
+    # via
+    #   -r requirements.in
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+rpds-py==0.10.3
+    # via
+    #   jsonschema
+    #   referencing
+semantic-version==2.10.0
+    # via gradio
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.0
+    # via
+    #   anyio
+    #   httpcore
+    #   httpx
+starlette==0.27.0
+    # via fastapi
+toolz==0.12.0
+    # via altair
+tqdm==4.66.1
+    # via huggingface-hub
+typing-extensions==4.8.0
+    # via
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+tzdata==2023.3
+    # via pandas
+urllib3==2.0.5
+    # via requests
+uvicorn==0.23.2
+    # via gradio
+websockets==11.0.3
+    # via
+    #   gradio
+    #   gradio-client