Dev

.github/workflows/ci.yml

@@ -8,15 +8,23 @@ jobs:
     strategy:
       matrix:
         os: [t4_gpu, ubuntu-latest, windows-latest]
+      fail-fast: false
+    env:
+      # T4 can't run bf16 in vllm; size for the 16GB card. (No-op on the
+      # CPU runners, which skip the VLM-backed tests.)
+      VLLM_DTYPE: float16
+      VLLM_GPU_TYPE: t4
+      SURYA_INFERENCE_STARTUP_TIMEOUT: "1200"
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
         with:
-          python-version: 3.11
-      - name: Install python dependencies
-        run: |
-          pip install poetry
-          poetry install
+          version: latest
+          enable-cache: true
+      - name: Set up Python 3.11
+        run: uv python install 3.11
+      - name: Install dependencies
+        run: uv sync --frozen --group dev
       - name: Run tests
-        run: poetry run pytest
+        run: uv run pytest

.github/workflows/cla.yml

@@ -26,7 +26,7 @@ jobs:
           PERSONAL_ACCESS_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
         with:
           path-to-signatures: 'signatures/version1/cla.json'
-          path-to-document: 'https://github.com/VikParuchuri/surya/blob/master/CLA.md'
+          path-to-document: 'https://github.com/datalab-to/surya/blob/master/CLA.md'
           # branch should not be protected
           branch: 'master'
           allowlist: VikParuchuri

.github/workflows/publish.yml

@@ -7,21 +7,17 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
         with:
-          python-version: 3.11
-      - name: Install python dependencies
-        run: |
-          pip install poetry
-          poetry install
+          version: latest
+          enable-cache: true
+      - name: Set up Python 3.11
+        run: uv python install 3.11
       - name: Build package
-        run: |
-          poetry build
+        run: uv build
       - name: Publish package
         env:
-          PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
-        run: |
-          poetry config pypi-token.pypi "$PYPI_TOKEN"
-          poetry publish
+          UV_PUBLISH_TOKEN: ${{ secrets.PYPI_TOKEN }}
+        run: uv publish

.github/workflows/scripts.yml

@@ -5,33 +5,36 @@ on: [push]
 jobs:
   build:
     runs-on: t4_gpu
+    env:
+      # T4 (Turing, compute 7.5) can't run bf16 in vllm; size vllm for the 16GB
+      # card and give the cold start (image pull + model download) headroom.
+      VLLM_DTYPE: float16
+      VLLM_GPU_TYPE: t4
+      SURYA_INFERENCE_STARTUP_TIMEOUT: "1200"
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
         with:
-          python-version: 3.11
-      - name: Install python dependencies
-        run: |
-          pip install poetry
-          poetry install
+          version: latest
+          enable-cache: true
+      - name: Set up Python 3.11
+        run: uv python install 3.11
+      - name: Install dependencies
+        run: uv sync --frozen --group dev
       - name: Download benchmark data
         run: |
           wget -O benchmark_data.zip "https://drive.google.com/uc?export=download&id=1NHrdYatR1rtqs2gPVfdvO0BAvocH8CJi"
           unzip -o benchmark_data.zip
       - name: Test detection
-        run: poetry run surya_detect benchmark_data/pdfs/switch_trans.pdf --page_range 0
+        run: uv run surya_detect benchmark_data/pdfs/switch_trans.pdf --page_range 0
+      # Spawn the vllm server once and reuse it across the OCR/layout/table
+      # steps (--keep_server) instead of paying a cold start three times.
       - name: Test OCR
-        env:
-          RECOGNITION_MAX_TOKENS: 25
-        run: poetry run surya_ocr benchmark_data/pdfs/switch_trans.pdf --page_range 0
+        run: uv run surya_ocr benchmark_data/pdfs/switch_trans.pdf --page_range 0 --keep_server
       - name: Test layout
-        run: poetry run surya_layout benchmark_data/pdfs/switch_trans.pdf --page_range 0
+        run: uv run surya_layout benchmark_data/pdfs/switch_trans.pdf --page_range 0 --keep_server
       - name: Test table
-        run: poetry run surya_table benchmark_data/pdfs/switch_trans.pdf --page_range 0
-      - name: Test texify
-        env:
-          TEXIFY_MAX_TOKENS: 25
-        run: poetry run surya_latex_ocr benchmark_data/pdfs/switch_trans.pdf --page_range 0
+        run: uv run surya_table benchmark_data/pdfs/switch_trans.pdf --page_range 0 --keep_server
       - name: Test detection folder
-        run: poetry run surya_detect benchmark_data/pdfs --page_range 0
+        run: uv run surya_detect benchmark_data/pdfs --page_range 0

CITATION.cff

@@ -6,6 +6,6 @@ authors:
     given-names: Vikas
   - name: Datalab Team
 date-released: 2025-05-13
-url: https://github.com/VikParuchuri/surya
-version: 0.14.0
-repository-code: https://github.com/VikParuchuri/surya
+url: https://github.com/datalab-to/surya
+version: 1.0.0
+repository-code: https://github.com/datalab-to/surya