Update 18449

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v4.6.0
     hooks:
       - id: check-executables-have-shebangs
       - id: check-json
@@ -13,21 +13,48 @@ repos:
         args: ["--fix=lf"]
       - id: requirements-txt-fixer
       - id: trailing-whitespace
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.5
     hooks:
-      - id: ruff
-        args: ["--fix"]
-      - id: ruff-format
+      - id: docformatter
+        args: ["--in-place"]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.14.1
+    rev: v1.9.0
     hooks:
       - id: mypy
         args: ["--ignore-missing-imports"]
         additional_dependencies:
           [
             "types-python-slugify",
-            "types-pytz",
-            "types-PyYAML",
             "types-requests",
+            "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
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.8.5
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.python-version

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

.vscode/extensions.json

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

.vscode/settings.json

@@ -2,16 +2,29 @@
     "editor.formatOnSave": true,
     "files.insertFinalNewline": false,
     "[python]": {
-        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.defaultFormatter": "ms-python.black-formatter",
         "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.formatOnSave.enabled": true
+    "notebook.formatOnCellExecution": true,
+    "notebook.formatOnSave.enabled": true,
+        "notebook.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
 }

README.md

@@ -4,9 +4,9 @@ emoji: 📊
 colorFrom: green
 colorTo: purple
 sdk: gradio
-sdk_version: 5.12.0
+sdk_version: 4.27.0
 app_file: app.py
-pinned: true
+pinned: false
 header: mini
 datasets:
   - ICLR2024/ICLR2024-papers

app.py

@@ -8,6 +8,10 @@ from papers import PaperList
 DESCRIPTION = "# ICLR 2024 Papers"
 
 TUTORIAL = """\
+#### Tutorial for creating a PR
+
+To add data to the table below, please use [this Space](https://huggingface.co/spaces/ICLR2024/update-ICLR2024-papers) to create a PR.
+
 #### Tutorial for claiming the ICLR 2024 papers
 
 1. Find your paper in the table below.
@@ -22,10 +26,6 @@ The admin team will validate your request soon. Once confirmed, the Paper page w
 If you need further assistance, see the guide [here](https://huggingface.co/docs/hub/paper-pages#claiming-authorship-to-a-paper).
 
 If your paper is not yet indexed on Hugging Face, you can index it by following this [guide](https://huggingface.co/docs/hub/paper-pages#can-i-have-a-paper-page-even-if-i-have-no-modeldatasetspace) and open a PR with [this Space](https://huggingface.co/spaces/ICLR2024/update-ICLR2024-papers) to add your Paper page to this Space.
-
-#### Tutorial for creating a PR
-
-To add data to the table below, please use [this Space](https://huggingface.co/spaces/ICLR2024/update-ICLR2024-papers) to create a PR.
 """
 
 
@@ -35,10 +35,7 @@ DEFAULT_COLUMNS = [
     "Title",
     "Type",
     "Paper page",
-    "👍",
-    "💬",
     "OpenReview",
-    "Project page",
     "GitHub",
     "Spaces",
     "Models",
@@ -48,7 +45,8 @@ 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)"
-    return f"{len(df)} / {len(paper_list.df_raw)}"
+    else:
+        return f"{len(df)} / {len(paper_list.df_raw)}"
 
 
 def update_df(
@@ -72,7 +70,7 @@ def update_df(
     )
 
 
-with gr.Blocks(css_paths="style.css") as demo:
+with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
     with gr.Accordion(label="Tutorial", open=True):
         gr.Markdown(TUTORIAL)
@@ -120,7 +118,7 @@ with gr.Blocks(css_paths="style.css") as demo:
         type="pandas",
         row_count=(0, "dynamic"),
         interactive=False,
-        max_height=1000,
+        height=1000,
         elem_id="table",
         wrap=True,
     )

papers.py

@@ -19,36 +19,32 @@ ABSTRACT_RETRIEVER.search("LLM")
 
 
 class PaperList:
-    COLUMN_INFO = (
+    COLUMN_INFO = [
         ["Title", "str"],
         ["Authors", "str"],
         ["Type", "str"],
         ["Paper page", "markdown"],
-        ["👍", "number"],
-        ["💬", "number"],
         ["OpenReview", "markdown"],
-        ["Project page", "markdown"],
         ["GitHub", "markdown"],
         ["Spaces", "markdown"],
         ["Models", "markdown"],
         ["Datasets", "markdown"],
         ["claimed", "markdown"],
-    )
+    ]
 
-    def __init__(self) -> None:
+    def __init__(self):
         self.df_raw = self.get_df()
         self.df_prettified = self.prettify(self.df_raw)
 
     @staticmethod
     def get_df() -> pd.DataFrame:
-        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(),
+        df = pd.merge(
+            left=datasets.load_dataset("ICLR2024/ICLR2024-papers", split="train").to_pandas(),
+            right=datasets.load_dataset("ICLR2024/ICLR2024-num-claimed-papers", split="train").to_pandas(),
             on="id",
             how="left",
         )
-        keys = ["n_authors", "n_linked_authors", "upvotes", "num_comments"]
-        df[keys] = df[keys].fillna(-1).astype(int)
+        df[["n_authors", "n_linked_authors"]] = df[["n_authors", "n_linked_authors"]].fillna(-1).astype(int)
         df["paper_page"] = df["arxiv_id"].apply(
             lambda arxiv_id: f"https://huggingface.co/papers/{arxiv_id}" if arxiv_id else ""
         )
@@ -66,19 +62,12 @@ class PaperList:
             n_linked_authors = "" if row.n_linked_authors == -1 else row.n_linked_authors
             n_authors = "" if row.n_authors == -1 else row.n_authors
             claimed_paper = "" if n_linked_authors == "" else f"{n_linked_authors}/{n_authors} {author_linked}"
-            upvotes = "" if row.upvotes == -1 else row.upvotes
-            num_comments = "" if row.num_comments == -1 else row.num_comments
 
             new_row = {
                 "Title": row["title"],
                 "Authors": ", ".join(row["authors"]),
                 "Type": row["type"],
                 "Paper page": PaperList.create_link(row["arxiv_id"], row["paper_page"]),
-                "Project page": (
-                    PaperList.create_link("Project page", row["project_page"]) if row["project_page"] else ""
-                ),
-                "👍": upvotes,
-                "💬": num_comments,
                 "OpenReview": PaperList.create_link("OpenReview", row["OpenReview"]),
                 "GitHub": "\n".join([PaperList.create_link("GitHub", url) for url in row["GitHub"]]),
                 "Spaces": "\n".join(
@@ -102,14 +91,14 @@ class PaperList:
         return pd.DataFrame(rows, columns=PaperList.get_column_names())
 
     @staticmethod
-    def get_column_names() -> list[str]:
+    def get_column_names():
         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(  # noqa: C901
+    def search(
         self,
         title_search_query: str,
         abstract_search_query: str,
@@ -130,7 +119,7 @@ class PaperList:
             df = df[df["type"] == presentation_type]
 
         if "Paper page" in filter_names:
-            df = df[df["paper_page"] != ""]
+            df = df[df["paper_page"].notnull()]
         if "GitHub" in filter_names:
             df = df[df["GitHub"].apply(len) > 0]
         if "Space" in filter_names:

pyproject.toml

@@ -1,50 +0,0 @@
-[project]
-name = "iclr2024-papers"
-version = "0.1.0"
-description = ""
-readme = "README.md"
-requires-python = ">=3.10"
-dependencies = [
-    "datasets>=3.2.0",
-    "gradio>=5.12.0",
-    "hf-transfer>=0.1.9",
-    "ragatouille>=0.0.8.post4",
-    "setuptools>=75.6.0",
-    "spaces>=0.32.0",
-]
-
-[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

@@ -1,545 +1,6 @@
-# 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==4.8.0
-    # 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==4.0.12
-    # via gitpython
-gitpython==3.1.44
-    # via git-python
-gradio==5.12.0
-    # via
-    #   iclr2024-papers (pyproject.toml)
-    #   spaces
-gradio-client==1.5.4
-    # via gradio
-greenlet==3.1.1
-    # via sqlalchemy
-h11==0.14.0
-    # via
-    #   httpcore
-    #   uvicorn
-hf-transfer==0.1.9
-    # 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
-    #   spaces
-huggingface-hub==0.27.1
-    # 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==0.3.14
-    # via ragatouille
-langchain-core==0.3.29
-    # via
-    #   langchain
-    #   langchain-text-splitters
-    #   ragatouille
-langchain-text-splitters==0.3.5
-    # via langchain
-langsmith==0.2.10
-    # via
-    #   langchain
-    #   langchain-core
-llama-cloud==0.1.8
-    # via llama-index-indices-managed-llama-cloud
-llama-index==0.12.10
-    # 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==0.12.10.post1
-    # 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==0.3.13
-    # 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==0.4.2
-    # 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==0.4.3
-    # 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==3.25.0
-    # 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==1.59.6
-    # via
-    #   llama-index-agent-openai
-    #   llama-index-embeddings-openai
-    #   llama-index-llms-openai
-orjson==3.10.14
-    # via
-    #   gradio
-    #   langsmith
-packaging==24.2
-    # via
-    #   datasets
-    #   faiss-cpu
-    #   gradio
-    #   gradio-client
-    #   huggingface-hub
-    #   langchain-core
-    #   marshmallow
-    #   spaces
-    #   transformers
-pandas==2.2.3
-    # via
-    #   datasets
-    #   gradio
-    #   llama-index-readers-file
-pillow==11.1.0
-    # via
-    #   gradio
-    #   llama-index-core
-    #   sentence-transformers
-propcache==0.2.1
-    # via
-    #   aiohttp
-    #   yarl
-protobuf==5.29.3
-    # via onnx
-psutil==5.9.8
-    # via spaces
-pyarrow==18.1.0
-    # via datasets
-pydantic==2.10.5
-    # via
-    #   fastapi
-    #   gradio
-    #   langchain
-    #   langchain-core
-    #   langsmith
-    #   llama-cloud
-    #   llama-index-core
-    #   llama-parse
-    #   openai
-    #   spaces
-pydantic-core==2.27.2
-    # via pydantic
-pydub==0.25.1
-    # via gradio
-pygments==2.19.1
-    # 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
-    #   spaces
-    #   tiktoken
-    #   transformers
-requests-toolbelt==1.0.0
-    # via langsmith
-rich==13.9.4
-    # via typer
-ruff==0.9.1
-    # via gradio
-safehttpx==0.1.6
-    # via gradio
-safetensors==0.5.2
-    # via transformers
-scikit-learn==1.6.1
-    # via sentence-transformers
-scipy==1.15.1
-    # via
-    #   colbert-ai
-    #   scikit-learn
-    #   sentence-transformers
-semantic-version==2.10.0
-    # via gradio
-sentence-transformers==2.7.0
-    # via ragatouille
-setuptools==75.8.0
-    # via iclr2024-papers (pyproject.toml)
-shellingham==1.5.4
-    # via typer
-six==1.17.0
-    # via python-dateutil
-smmap==5.0.2
-    # via gitdb
-sniffio==1.3.1
-    # via
-    #   anyio
-    #   openai
-soupsieve==2.6
-    # via beautifulsoup4
-spaces==0.32.0
-    # via iclr2024-papers (pyproject.toml)
-sqlalchemy==2.0.37
-    # 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==4.67.1
-    # via
-    #   colbert-ai
-    #   datasets
-    #   huggingface-hub
-    #   llama-index-core
-    #   nltk
-    #   openai
-    #   sentence-transformers
-    #   transformers
-transformers==4.48.0
-    # 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
-    #   spaces
-    #   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==1.17.1
-    # via
-    #   deprecated
-    #   llama-index-core
-xxhash==3.5.0
-    # via datasets
-yarl==1.18.3
-    # via aiohttp
+datasets==2.18.0
+#gradio==4.27.0
+huggingface_hub==0.22.2
+pandas==2.2.1
+ragatouille==0.0.8.post2
+tqdm==4.66.2