Update

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: check-executables-have-shebangs
       - id: check-json
@@ -18,13 +18,15 @@ repos:
     hooks:
       - id: docformatter
         args: ["--in-place"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.4
     hooks:
-      - id: isort
-        args: ["--profile", "black"]
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+        args: ["--line-length", "119"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.9.0
+    rev: v1.14.0
     hooks:
       - id: mypy
         args: ["--ignore-missing-imports"]
@@ -35,14 +37,8 @@ repos:
             "types-PyYAML",
             "types-pytz",
           ]
-  - repo: https://github.com/psf/black
-    rev: 24.4.0
-    hooks:
-      - id: black
-        language_version: python3.10
-        args: ["--line-length", "119"]
   - repo: https://github.com/kynan/nbstripout
-    rev: 0.7.1
+    rev: 0.8.1
     hooks:
       - id: nbstripout
         args:
@@ -51,7 +47,7 @@ repos:
             "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
           ]
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.5
+    rev: 1.9.1
     hooks:
       - id: nbqa-black
       - id: nbqa-pyupgrade

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "ms-python.python",
+        "charliermarsh.ruff",
+        "streetsidesoftware.code-spell-checker",
+        "tamasfe.even-better-toml"
+    ]
+}

.vscode/settings.json

@@ -2,29 +2,20 @@
     "editor.formatOnSave": true,
     "files.insertFinalNewline": false,
     "[python]": {
-        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.defaultFormatter": "charliermarsh.ruff",
         "editor.formatOnType": true,
         "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
             "source.organizeImports": "explicit"
         }
     },
     "[jupyter]": {
         "files.insertFinalNewline": false
     },
-    "black-formatter.args": [
-        "--line-length=119"
-    ],
-    "isort.args": ["--profile", "black"],
-    "flake8.args": [
-        "--max-line-length=119"
-    ],
-    "ruff.lint.args": [
-        "--line-length=119"
-    ],
     "notebook.output.scrolling": true,
     "notebook.formatOnCellExecution": true,
     "notebook.formatOnSave.enabled": true,
-        "notebook.codeActionsOnSave": {
-            "source.organizeImports": "explicit"
-        }
+    "notebook.codeActionsOnSave": {
+        "source.organizeImports": "explicit"
+    }
 }

README.md

@@ -4,7 +4,7 @@ emoji: 📊
 colorFrom: green
 colorTo: purple
 sdk: gradio
-sdk_version: 4.36.1
+sdk_version: 5.9.1
 app_file: app.py
 pinned: true
 header: mini

app.py

@@ -48,8 +48,7 @@ DEFAULT_COLUMNS = [
 def update_num_papers(df: pd.DataFrame) -> str:
     if "claimed" in df.columns:
         return f"{len(df)} / {len(paper_list.df_raw)} ({len(df[df['claimed'].str.contains('✅')])} claimed)"
-    else:
-        return f"{len(df)} / {len(paper_list.df_raw)}"
+    return f"{len(df)} / {len(paper_list.df_raw)}"
 
 
 def update_df(
@@ -73,7 +72,7 @@ def update_df(
     )
 
 
-with gr.Blocks(css="style.css") as demo:
+with gr.Blocks(css_paths="style.css") as demo:
     gr.Markdown(DESCRIPTION)
     with gr.Accordion(label="Tutorial", open=True):
         gr.Markdown(TUTORIAL)
@@ -121,7 +120,7 @@ with gr.Blocks(css="style.css") as demo:
         type="pandas",
         row_count=(0, "dynamic"),
         interactive=False,
-        height=1000,
+        max_height=1000,
         elem_id="table",
         wrap=True,
     )

papers.py

@@ -19,7 +19,7 @@ ABSTRACT_RETRIEVER.search("LLM")
 
 
 class PaperList:
-    COLUMN_INFO = [
+    COLUMN_INFO = (
         ["Title", "str"],
         ["Authors", "str"],
         ["Type", "str"],
@@ -33,16 +33,16 @@ class PaperList:
         ["Models", "markdown"],
         ["Datasets", "markdown"],
         ["claimed", "markdown"],
-    ]
+    )
 
-    def __init__(self):
+    def __init__(self) -> None:
         self.df_raw = self.get_df()
         self.df_prettified = self.prettify(self.df_raw)
 
     @staticmethod
     def get_df() -> pd.DataFrame:
-        df = pd.merge(
-            left=datasets.load_dataset("ICLR2024/ICLR2024-papers", split="train").to_pandas(),
+        df = datasets.load_dataset("ICLR2024/ICLR2024-papers", split="train").to_pandas()
+        df = df.merge(
             right=datasets.load_dataset("ICLR2024/ICLR2024-paper-stats", split="train").to_pandas(),
             on="id",
             how="left",
@@ -102,14 +102,14 @@ class PaperList:
         return pd.DataFrame(rows, columns=PaperList.get_column_names())
 
     @staticmethod
-    def get_column_names():
+    def get_column_names() -> list[str]:
         return list(map(operator.itemgetter(0), PaperList.COLUMN_INFO))
 
     def get_column_datatypes(self, column_names: list[str]) -> list[str]:
         mapping = dict(self.COLUMN_INFO)
         return [mapping[name] for name in column_names]
 
-    def search(
+    def search(  # noqa: C901
         self,
         title_search_query: str,
         abstract_search_query: str,

pyproject.toml

@@ -0,0 +1,49 @@
+[project]
+name = "iclr2024-papers"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "datasets>=3.2.0",
+    "gradio>=5.9.1",
+    "hf-transfer>=0.1.8",
+    "ragatouille>=0.0.8.post4",
+    "setuptools>=75.6.0",
+]
+
+[tool.ruff]
+line-length = 119
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [
+    "COM812", # missing-trailing-comma
+    "D203",   # one-blank-line-before-class
+    "D213",   # multi-line-summary-second-line
+    "E501",   # line-too-long
+    "SIM117", # multiple-with-statements
+]
+extend-ignore = [
+    "D100",    # undocumented-public-module
+    "D101",    # undocumented-public-class
+    "D102",    # undocumented-public-method
+    "D103",    # undocumented-public-function
+    "D104",    # undocumented-public-package
+    "D105",    # undocumented-magic-method
+    "D107",    # undocumented-public-init
+    "EM101",   # raw-string-in-exception
+    "FBT001",  # boolean-type-hint-positional-argument
+    "FBT002",  # boolean-default-value-positional-argument
+    "PD901",   # pandas-df-variable-name
+    "PGH003",  # blanket-type-ignore
+    "PLR0913", # too-many-arguments
+    "PLR0915", # too-many-statements
+    "TRY003",  # raise-vanilla-args
+]
+unfixable = [
+    "F401", # unused-import
+]
+
+[tool.ruff.format]
+docstring-code-format = true

requirements.txt

@@ -1,6 +1,534 @@
-datasets==2.19.1
-#gradio==4.36.1
-huggingface_hub==0.23.1
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+aiohappyeyeballs==2.4.4
+    # via aiohttp
+aiohttp==3.11.11
+    # via
+    #   datasets
+    #   fsspec
+    #   langchain
+    #   llama-index-core
+aiosignal==1.3.2
+    # via aiohttp
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.7.0
+    # via
+    #   gradio
+    #   httpx
+    #   openai
+    #   starlette
+async-timeout==4.0.3
+    # via
+    #   aiohttp
+    #   langchain
+attrs==24.3.0
+    # via aiohttp
+beautifulsoup4==4.12.3
+    # via llama-index-readers-file
+bitarray==3.0.0
+    # via colbert-ai
+blinker==1.9.0
+    # via flask
+catalogue==2.0.10
+    # via srsly
+certifi==2024.12.14
+    # via
+    #   httpcore
+    #   httpx
+    #   llama-cloud
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   flask
+    #   llama-parse
+    #   nltk
+    #   typer
+    #   uvicorn
+colbert-ai==0.2.19
+    # via ragatouille
+dataclasses-json==0.6.7
+    # via llama-index-core
+datasets==3.2.0
+    # via
+    #   iclr2024-papers (pyproject.toml)
+    #   colbert-ai
+deprecated==1.2.15
+    # via llama-index-core
+dill==0.3.8
+    # via
+    #   datasets
+    #   multiprocess
+dirtyjson==1.0.8
+    # via llama-index-core
+distro==1.9.0
+    # via openai
+exceptiongroup==1.2.2
+    # via anyio
+faiss-cpu==1.9.0.post1
+    # via ragatouille
+fast-pytorch-kmeans==0.2.0.1
+    # via ragatouille
+fastapi==0.115.6
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.16.1
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+filetype==1.2.0
+    # via llama-index-core
+flask==3.1.0
+    # via colbert-ai
+frozenlist==1.5.0
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec==2024.9.0
+    # via
+    #   datasets
+    #   gradio-client
+    #   huggingface-hub
+    #   llama-index-core
+    #   torch
+git-python==1.0.3
+    # via colbert-ai
+gitdb==4.0.11
+    # via gitpython
+gitpython==3.1.43
+    # via git-python
+gradio==5.9.1
+    # via iclr2024-papers (pyproject.toml)
+gradio-client==1.5.2
+    # via gradio
+greenlet==3.1.1
+    # via sqlalchemy
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.8
+    # via iclr2024-papers (pyproject.toml)
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   langsmith
+    #   llama-cloud
+    #   llama-index-core
+    #   openai
+    #   safehttpx
+huggingface-hub==0.27.0
+    # via
+    #   datasets
+    #   gradio
+    #   gradio-client
+    #   sentence-transformers
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+    #   yarl
+itsdangerous==2.2.0
+    # via flask
+jinja2==3.1.5
+    # via
+    #   flask
+    #   gradio
+    #   torch
+jiter==0.8.2
+    # via openai
+joblib==1.4.2
+    # via
+    #   nltk
+    #   scikit-learn
+jsonpatch==1.33
+    # via langchain-core
+jsonpointer==3.0.0
+    # via jsonpatch
+langchain==0.3.13
+    # via ragatouille
+langchain-core==0.3.28
+    # via
+    #   langchain
+    #   langchain-text-splitters
+    #   ragatouille
+langchain-text-splitters==0.3.4
+    # via langchain
+langsmith==0.2.7
+    # via
+    #   langchain
+    #   langchain-core
+llama-cloud==0.1.7
+    # via llama-index-indices-managed-llama-cloud
+llama-index==0.12.9
+    # via ragatouille
+llama-index-agent-openai==0.4.1
+    # via
+    #   llama-index
+    #   llama-index-program-openai
+llama-index-cli==0.4.0
+    # via llama-index
+llama-index-core==0.12.9
+    # via
+    #   llama-index
+    #   llama-index-agent-openai
+    #   llama-index-cli
+    #   llama-index-embeddings-openai
+    #   llama-index-indices-managed-llama-cloud
+    #   llama-index-llms-openai
+    #   llama-index-multi-modal-llms-openai
+    #   llama-index-program-openai
+    #   llama-index-question-gen-openai
+    #   llama-index-readers-file
+    #   llama-index-readers-llama-parse
+    #   llama-parse
+llama-index-embeddings-openai==0.3.1
+    # via
+    #   llama-index
+    #   llama-index-cli
+llama-index-indices-managed-llama-cloud==0.6.3
+    # via llama-index
+llama-index-llms-openai==0.3.12
+    # via
+    #   llama-index
+    #   llama-index-agent-openai
+    #   llama-index-cli
+    #   llama-index-multi-modal-llms-openai
+    #   llama-index-program-openai
+    #   llama-index-question-gen-openai
+llama-index-multi-modal-llms-openai==0.4.1
+    # via llama-index
+llama-index-program-openai==0.3.1
+    # via
+    #   llama-index
+    #   llama-index-question-gen-openai
+llama-index-question-gen-openai==0.3.0
+    # via llama-index
+llama-index-readers-file==0.4.1
+    # via llama-index
+llama-index-readers-llama-parse==0.4.0
+    # via llama-index
+llama-parse==0.5.19
+    # via llama-index-readers-llama-parse
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+    #   werkzeug
+marshmallow==3.23.2
+    # via dataclasses-json
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+multidict==6.1.0
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.16
+    # via datasets
+mypy-extensions==1.0.0
+    # via typing-inspect
+nest-asyncio==1.6.0
+    # via llama-index-core
+networkx==3.4.2
+    # via
+    #   llama-index-core
+    #   torch
+ninja==1.11.1.3
+    # via colbert-ai
+nltk==3.9.1
+    # via
+    #   llama-index
+    #   llama-index-core
+numpy==1.26.4
+    # via
+    #   datasets
+    #   faiss-cpu
+    #   fast-pytorch-kmeans
+    #   gradio
+    #   langchain
+    #   llama-index-core
+    #   onnx
+    #   pandas
+    #   scikit-learn
+    #   scipy
+    #   sentence-transformers
+    #   transformers
+    #   voyager
+nvidia-cublas-cu12==12.4.5.8
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.4.127
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.4.127
+    # via torch
+nvidia-cuda-runtime-cu12==12.4.127
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.2.1.3
+    # via torch
+nvidia-curand-cu12==10.3.5.147
+    # via torch
+nvidia-cusolver-cu12==11.6.1.9
+    # via torch
+nvidia-cusparse-cu12==12.3.1.170
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-ml-py==12.560.30
+    # via pynvml
+nvidia-nccl-cu12==2.21.5
+    # via torch
+nvidia-nvjitlink-cu12==12.4.127
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+    #   torch
+nvidia-nvtx-cu12==12.4.127
+    # via torch
+onnx==1.17.0
+    # via ragatouille
+openai==1.58.1
+    # via
+    #   llama-index-agent-openai
+    #   llama-index-embeddings-openai
+    #   llama-index-llms-openai
+orjson==3.10.13
+    # via
+    #   gradio
+    #   langsmith
+packaging==24.2
+    # via
+    #   datasets
+    #   faiss-cpu
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   langchain-core
+    #   marshmallow
+    #   transformers
 pandas==2.2.2
-ragatouille==0.0.8.post2
+    # via
+    #   datasets
+    #   gradio
+    #   llama-index-readers-file
+pillow==11.0.0
+    # via
+    #   gradio
+    #   llama-index-core
+    #   sentence-transformers
+propcache==0.2.1
+    # via
+    #   aiohttp
+    #   yarl
+protobuf==5.29.2
+    # via onnx
+pyarrow==18.1.0
+    # via datasets
+pydantic==2.10.4
+    # via
+    #   fastapi
+    #   gradio
+    #   langchain
+    #   langchain-core
+    #   langsmith
+    #   llama-cloud
+    #   llama-index-core
+    #   llama-parse
+    #   openai
+pydantic-core==2.27.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+pynvml==12.0.0
+    # via fast-pytorch-kmeans
+pypdf==5.1.0
+    # via llama-index-readers-file
+python-dateutil==2.9.0.post0
+    # via pandas
+python-dotenv==1.0.1
+    # via colbert-ai
+python-multipart==0.0.20
+    # via gradio
+pytz==2024.2
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   datasets
+    #   gradio
+    #   huggingface-hub
+    #   langchain
+    #   langchain-core
+    #   llama-index-core
+    #   transformers
+ragatouille==0.0.8.post4
+    # via iclr2024-papers (pyproject.toml)
+regex==2024.11.6
+    # via
+    #   nltk
+    #   tiktoken
+    #   transformers
+requests==2.32.3
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   langchain
+    #   langsmith
+    #   llama-index-core
+    #   requests-toolbelt
+    #   tiktoken
+    #   transformers
+requests-toolbelt==1.0.0
+    # via langsmith
+rich==13.9.4
+    # via typer
+ruff==0.8.4
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.4.5
+    # via transformers
+scikit-learn==1.6.0
+    # via sentence-transformers
+scipy==1.14.1
+    # via
+    #   colbert-ai
+    #   scikit-learn
+    #   sentence-transformers
+semantic-version==2.10.0
+    # via gradio
+sentence-transformers==2.7.0
+    # via ragatouille
+setuptools==75.6.0
+    # via iclr2024-papers (pyproject.toml)
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+smmap==5.0.1
+    # via gitdb
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   openai
+soupsieve==2.6
+    # via beautifulsoup4
+sqlalchemy==2.0.36
+    # via
+    #   langchain
+    #   llama-index-core
+srsly==2.4.8
+    # via ragatouille
+starlette==0.41.3
+    # via
+    #   fastapi
+    #   gradio
+striprtf==0.0.26
+    # via llama-index-readers-file
+sympy==1.13.1
+    # via torch
+tenacity==9.0.0
+    # via
+    #   langchain
+    #   langchain-core
+    #   llama-index-core
+threadpoolctl==3.5.0
+    # via scikit-learn
+tiktoken==0.8.0
+    # via llama-index-core
+tokenizers==0.21.0
+    # via transformers
+tomlkit==0.13.2
+    # via gradio
+torch==2.5.1
+    # via
+    #   fast-pytorch-kmeans
+    #   ragatouille
+    #   sentence-transformers
 tqdm==4.66.4
+    # via
+    #   colbert-ai
+    #   datasets
+    #   huggingface-hub
+    #   llama-index-core
+    #   nltk
+    #   openai
+    #   sentence-transformers
+    #   transformers
+transformers==4.47.1
+    # via
+    #   colbert-ai
+    #   ragatouille
+    #   sentence-transformers
+triton==3.1.0
+    # via torch
+typer==0.15.1
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   langchain-core
+    #   llama-index-core
+    #   multidict
+    #   openai
+    #   pydantic
+    #   pydantic-core
+    #   pypdf
+    #   rich
+    #   sqlalchemy
+    #   torch
+    #   typer
+    #   typing-inspect
+    #   uvicorn
+typing-inspect==0.9.0
+    # via
+    #   dataclasses-json
+    #   llama-index-core
+tzdata==2024.2
+    # via pandas
+ujson==5.10.0
+    # via colbert-ai
+urllib3==2.3.0
+    # via requests
+uvicorn==0.34.0
+    # via gradio
+voyager==2.1.0
+    # via ragatouille
+websockets==14.1
+    # via gradio-client
+werkzeug==3.1.3
+    # via flask
+wrapt==1.17.0
+    # via
+    #   deprecated
+    #   llama-index-core
+xxhash==3.5.0
+    # via datasets
+yarl==1.18.3
+    # via aiohttp