datalab-python-sdk 0.1.0__tar.gz

datalab_python_sdk-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,19 @@
+name: Unit tests
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.13
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.13
+      - name: Install python dependencies
+        run: |
+          pip install uv
+          uv sync
+      - name: Run tests
+        run: uv run pytest tests/

datalab_python_sdk-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,39 @@
+name: Publish python package
+on:
+  push:
+    tags:
+      - "v*.*.*"
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+      - name: Install python dependencies
+        run: |
+          pip install uv
+          uv sync --group dev
+      - name: Build package
+        run: |
+          uv build
+      - name: Extract version from pyproject.toml
+        id: version
+        run: |
+          VERSION=$(python -c "import tomllib; print(tomllib.load(open('pyproject.toml', 'rb'))['project']['version'])")
+          echo "version=v$VERSION" >> $GITHUB_OUTPUT
+
+      - name: Validate tag matches version
+        run: |
+          if [ "${{ github.ref_name }}" != "${{ steps.version.outputs.version }}" ]; then
+            echo "Tag ${{ github.ref_name }} doesn't match pyproject.toml version ${{ steps.version.outputs.version }}"
+            exit 1
+          fi
+      - name: Publish package
+        env:
+          PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          cd python
+          uv publish --token "$PYPI_TOKEN"

datalab_python_sdk-0.1.0/.gitignore

@@ -0,0 +1,219 @@
+arxiv_papers/
+.env
+examples/+*
+examples_all/
+python/examples
+e2e.sh
+TODO.md
+.vscode/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

datalab_python_sdk-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.12.3
+  hooks:
+    # Run the linter.
+    - id: ruff-check
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format

datalab_python_sdk-0.1.0/.python-version

@@ -0,0 +1 @@
+3.13

datalab_python_sdk-0.1.0/LICENSE

@@ -0,0 +1,18 @@
+Copyright 2025 Endless Labs Inc
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the “Software”), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

datalab_python_sdk-0.1.0/PKG-INFO

@@ -0,0 +1,17 @@
+Metadata-Version: 2.4
+Name: datalab-python-sdk
+Version: 0.1.0
+Summary: Auto-generated SDK for Datalab API
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: aiohttp>=3.12.14
+Requires-Dist: click>=8.2.1
+Requires-Dist: pydantic-settings<3.0.0,>=2.10.1
+Requires-Dist: pydantic<3.0.0,>=2.11.7
+Requires-Dist: pytest-asyncio>=1.0.0
+Provides-Extra: test
+Requires-Dist: aiofiles>=23.2.0; extra == 'test'
+Requires-Dist: pytest-asyncio>=0.21.0; extra == 'test'
+Requires-Dist: pytest-cov>=4.1.0; extra == 'test'
+Requires-Dist: pytest-mock>=3.11.0; extra == 'test'
+Requires-Dist: pytest>=7.4.0; extra == 'test'

datalab_python_sdk-0.1.0/README.md

@@ -0,0 +1,174 @@
+# Datalab SDK
+
+A Python SDK for the [Datalab API](https://www.datalab.to) - a document intelligence platform powered by [marker](https://github.com/VikParuchuri/marker) and [surya](https://github.com/VikParuchuri/surya).
+
+## Installation
+
+```bash
+pip install datalab-sdk
+```
+
+## Quick Start
+
+### Authentication
+
+Get your API key from [https://www.datalab.to/app/keys](https://www.datalab.to/app/keys):
+
+```bash
+export DATALAB_API_KEY="your_api_key_here"
+```
+
+### Basic Usage
+
+```python
+from datalab_sdk import DatalabClient
+
+client = DatalabClient() # use env var from above, or pass api_key="your_api_key_here"
+
+# Convert PDF to markdown
+result = client.convert("document.pdf")
+print(result.markdown)
+
+# OCR a document
+ocr_result = client.ocr("document.pdf")
+print(ocr_result.get_text())  # Get all text as string
+```
+
+### Async Usage
+
+```python
+import asyncio
+from datalab_sdk import AsyncDatalabClient
+
+async def main():
+    async with AsyncDatalabClient(api_key="YOUR_API_KEY") as client:
+        # Convert PDF to markdown
+        result = await client.convert("document.pdf")
+        print(result.markdown)
+        
+        # OCR a document
+        ocr_result = await client.ocr("document.pdf")
+        print(f"OCR found {len(ocr_result.pages)} pages")
+
+asyncio.run(main())
+```
+
+## API Methods
+
+### Document Conversion
+
+Convert PDFs, Office documents, and images to markdown, HTML, or JSON.
+
+```python
+# Basic conversion
+result = client.convert("document.pdf")
+
+# With options
+from datalab_sdk import ProcessingOptions
+options = ProcessingOptions(
+    force_ocr=True,
+    output_format="html",
+    use_llm=True,
+    max_pages=10
+)
+result = client.convert("document.pdf", options=options)
+
+# Convert and save automatically
+result = client.convert("document.pdf", save_output="output/result")
+```
+
+### OCR
+
+Extract text with bounding boxes from documents.
+
+```python
+# Basic OCR
+result = client.ocr("document.pdf")
+print(result.get_text())
+
+# OCR with options
+result = client.ocr("document.pdf", max_pages=5)
+
+# OCR and save automatically
+result = client.ocr("document.pdf", save_output="output/ocr_result")
+```
+
+## CLI Usage
+
+The SDK includes a command-line interface:
+
+```bash
+# Convert document to markdown
+datalab convert document.pdf
+
+# OCR with JSON output
+datalab ocr document.pdf --output-format json
+```
+
+## Error Handling
+
+```python
+from datalab_sdk import DatalabAPIError, DatalabTimeoutError
+
+try:
+    result = client.convert("document.pdf")
+except DatalabAPIError as e:
+    print(f"API Error: {e}")
+except DatalabTimeoutError as e:
+    print(f"Timeout: {e}")
+```
+
+## Supported File Types
+
+- **PDF**: `pdf`
+- **Images**: `png`, `jpeg`, `webp`, `gif`, `tiff`
+- **Office Documents**: `docx`, `xlsx`, `pptx`, `doc`, `xls`, `ppt`
+- **Other**: `html`, `epub`, `odt`, `ods`, `odp`
+
+## Rate Limits
+
+- 200 requests per 60 seconds
+- Maximum 200 concurrent requests
+- 200MB file size limit
+
+* email hi@datalab.to for higher limits.
+
+## Examples
+
+### Extract JSON Data
+
+```python
+from datalab_sdk import DatalabClient, ProcessingOptions
+
+client = DatalabClient(api_key="YOUR_API_KEY")
+options = ProcessingOptions(output_format="json")
+result = client.convert("research_paper.pdf", options=options)
+
+# Parse JSON to find equations
+import json
+data = json.loads(result.json)
+equations = [block for block in data if block.get('btype') == 'Formula']
+print(f"Found {len(equations)} equations")
+```
+
+### Batch Process Documents
+
+```python
+import asyncio
+from pathlib import Path
+from datalab_sdk import AsyncDatalabClient
+
+async def process_documents():
+    files = list(Path("documents/").glob("*.pdf"))
+    
+    async with AsyncDatalabClient(api_key="YOUR_API_KEY") as client:
+        for file in files[:5]:
+            result = await client.convert(str(file), save_output=f"output/{file.stem}")
+            print(f"{file.name}: {result.page_count} pages")
+
+asyncio.run(process_documents())
+```
+
+## License
+
+MIT License