Setup transformers.js during Docker build

Dockerfile

@@ -5,12 +5,19 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     PORT=8501
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    git git-lfs ffmpeg libsm6 libxext6 cmake libgl1 build-essential \
+    git git-lfs ffmpeg libsm6 libxext6 cmake libgl1 build-essential curl \
     && rm -rf /var/lib/apt/lists/* \
     && git lfs install
 
 WORKDIR /app
 
+ARG TRANSFORMERS_JS_VERSION=3.7.6
+RUN curl -L "https://github.com/huggingface/transformers.js/archive/refs/tags/${TRANSFORMERS_JS_VERSION}.tar.gz" -o transformers.tar.gz \
+    && tar -xzf transformers.tar.gz \
+    && mv "transformers.js-${TRANSFORMERS_JS_VERSION}" transformers.js \
+    && pip install --no-cache-dir -r "transformers.js/scripts/requirements.txt" \
+    && rm -rf transformers.tar.gz
+
 COPY requirements.txt ./
 RUN pip install --no-cache-dir -U pip \
     && pip install --no-cache-dir -r requirements.txt

app.py

@@ -2,13 +2,10 @@ import logging
 import os
 import subprocess
 import sys
-import tempfile
-import tarfile
 import shutil
-from dataclasses import dataclass
 from pathlib import Path
 from typing import List, Optional, Tuple
-from urllib.request import urlopen, urlretrieve
+from dataclasses import dataclass
 
 import streamlit as st
 from huggingface_hub import HfApi, whoami
@@ -24,11 +21,7 @@ class Config:
     hf_token: str
     hf_username: str
     is_using_user_token: bool
-    transformers_version: str = "3.7.6"
     hf_base_url: str = "https://huggingface.co"
-    transformers_base_url: str = (
-        "https://github.com/huggingface/transformers.js/archive/refs"
-    )
     repo_path: Path = Path("./transformers.js")
 
     @classmethod
@@ -65,57 +58,11 @@ class ModelConverter:
         self.config = config
         self.api = HfApi(token=config.hf_token)
 
-    def _get_ref_type(self) -> str:
-        """Determine the reference type for the transformers repository."""
-        url = f"{self.config.transformers_base_url}/tags/{self.config.transformers_version}.tar.gz"
-        try:
-            return "tags" if urlopen(url).getcode() == 200 else "heads"
-        except Exception as e:
-            logger.warning(f"Failed to check tags, defaulting to heads: {e}")
-            return "heads"
-
     def setup_repository(self) -> None:
-        """Download and setup transformers repository if needed."""
-        if self.config.repo_path.exists():
-            return
-
-        ref_type = self._get_ref_type()
-        archive_url = f"{self.config.transformers_base_url}/{ref_type}/{self.config.transformers_version}.tar.gz"
-        archive_path = Path(f"./transformers_{self.config.transformers_version}.tar.gz")
-
-        try:
-            urlretrieve(archive_url, archive_path)
-            self._extract_archive(archive_path)
-            self._install_scripts_requirements()
-            logger.info("Repository downloaded and extracted successfully")
-        except Exception as e:
-            raise RuntimeError(f"Failed to setup repository: {e}")
-        finally:
-            archive_path.unlink(missing_ok=True)
-
-    def _extract_archive(self, archive_path: Path) -> None:
-        """Extract the downloaded archive."""
-        with tempfile.TemporaryDirectory() as tmp_dir:
-            with tarfile.open(archive_path, "r:gz") as tar:
-                tar.extractall(tmp_dir)
-
-            extracted_folder = next(Path(tmp_dir).iterdir())
-            extracted_folder.rename(self.config.repo_path)
-
-    def _install_scripts_requirements(self) -> None:
-        req_path = self.config.repo_path / "scripts" / "requirements.txt"
-        if req_path.exists():
-            subprocess.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--no-cache-dir",
-                    "-r",
-                    str(req_path),
-                ],
-                check=True,
+        """Ensure the bundled transformers.js repository is present."""
+        if not self.config.repo_path.exists():
+            raise RuntimeError(
+                f"Expected transformers.js repository at {self.config.repo_path} but it was not found."
             )
 
     def _run_conversion_subprocess(

requirements.txt

@@ -4,10 +4,3 @@ onnxscript==0.5.4
 onnxconverter_common==1.16.0
 onnx_graphsurgeon==0.5.8
 torch==2.5.1
-transformers==4.49.0
-onnxruntime==1.20.1
-optimum@git+https://github.com/huggingface/optimum.git@b04feaea78cda58d79b8da67dca3fd0c4ab33435
-onnx==1.17.0
-tqdm==4.67.1
-onnxslim==0.1.48
-numpy==2.2.6