Refactoring and PDM Integration

.github/workflows/main.yml

@@ -0,0 +1,27 @@
+name: Publish Python Package
+
+on:
+  release:
+    types:
+        - published
+
+jobs:
+  pypi-publish:
+    name: upload release to PyPI
+    runs-on: ubuntu-20.04
+    permissions:
+      contents: read
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.release.tag_name }}
+
+      - name: Setup PDM
+        uses: pdm-project/setup-pdm@v4
+        with:
+          python-version: 3.11
+          version: 2.10.0
+
+      - name: Publish package distributions to PyPI
+        run: pdm publish

.gitignore

@@ -160,3 +160,4 @@ cython_debug/
 #  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/
+tests/data/*

.pre-commit-config.yaml

@@ -0,0 +1,160 @@
+---
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+# - Added pkgs feature flag auto generated code to flake8 exclude list
+# Force all unspecified python hooks to run python 3.10
+default_language_version:
+  python: python3.9
+default_stages:
+  - commit
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      # TODO: Exclude tests/test_data directory
+        exclude: ^tests/test_data/
+        exclude_types:
+          - "markdown"
+      - id: end-of-file-fixer
+      - id: check-yaml
+        args: [--unsafe]
+      - id: check-added-large-files
+        args: ["--maxkb=10240"]
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-ast
+      - id: check-json
+        exclude: ".vscode/launch.json"
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: destroyed-symlinks
+      - id: forbid-new-submodules
+      - id: mixed-line-ending
+      - id: no-commit-to-branch
+  - repo: https://github.com/adrienverge/yamllint
+    rev: v1.35.1
+    hooks:
+      - id: yamllint
+        args: ["-d", "relaxed"]
+        language: system
+  - repo: https://github.com/rhysd/actionlint
+    rev: v1.6.26
+    hooks:
+      - id: actionlint-docker
+        args: [-ignore, 'label ".+" is unknown']
+  - repo: https://github.com/psf/black
+    rev: 24.2.0
+    hooks:
+      - id: black
+        args: [--config=pyproject.toml, -l 120]
+        language: system
+        exclude: |
+          (?x)^(
+              pkgs/unstract-flags/src/unstract/flags/evaluation_.*\.py|
+          )$
+  - repo: https://github.com/pycqa/flake8
+    rev: 7.0.0
+    hooks:
+      - id: flake8
+        args: [--max-line-length=120]
+        exclude: |
+          (?x)^(
+              .*migrations/.*\.py|
+              unstract-core/tests/.*|
+              pkgs/unstract-flags/src/unstract/flags/evaluation_.*\.py|
+          )$
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        files: "\\.(py)$"
+        args:
+          [
+            "--profile",
+            "black",
+            "--filter-files",
+            --settings-path=pyproject.toml,
+          ]
+  - repo: https://github.com/hadialqattan/pycln
+    rev: v2.4.0
+    hooks:
+      - id: pycln
+        args: [--config=pyproject.toml]
+  - repo: https://github.com/pycqa/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+  # - repo: https://github.com/MarcoGorelli/absolufy-imports
+  #   rev: v0.3.1
+  #   hooks:
+  #     - id: absolufy-imports
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.15.0
+    hooks:
+      - id: pyupgrade
+        entry: pyupgrade --py39-plus --keep-runtime-typing
+        types:
+          - python
+  - repo: https://github.com/gitleaks/gitleaks
+    rev: v8.18.2
+    hooks:
+      - id: gitleaks
+  - repo: https://github.com/asottile/yesqa
+    rev: v1.5.0
+    hooks:
+      - id: yesqa
+  # TODO: Uncomment after typing the SDK
+  # - repo: https://github.com/pre-commit/mirrors-mypy
+  #   rev: v1.8.0
+  #   hooks:
+  #     - id: mypy
+  #       language: system
+  #       entry: mypy .
+  #       pass_filenames: false
+  #       # IMPORTANT!
+  #       # Keep args same as tool.mypy section in pyproject.toml
+  #       args:
+  #         [
+  #           --allow-subclassing-any,
+  #           --allow-untyped-decorators,
+  #           --check-untyped-defs,
+  #           --exclude, ".*migrations/.*.py",
+  #           --exclude, "backend/prompt/.*",
+  #           --exclude, "document_display_service/.*",
+  #           --exclude, "pkgs/unstract-connectors/tests/.*",
+  #           --exclude, "pkgs/unstract-core/.*",
+  #           --exclude, "pkgs/unstract-flags/src/unstract/flags/.*",
+  #           --exclude, "sdks/.*",
+  #           --exclude, "unstract-document-service/.*",
+  #           --exclude, "__pypackages__/.*",
+  #           --follow-imports, "silent",
+  #           --ignore-missing-imports,
+  #           --implicit-reexport,
+  #           --pretty,
+  #           --python-version=3.9,
+  #           --show-column-numbers,
+  #           --show-error-codes,
+  #           --strict,
+  #           --warn-redundant-casts,
+  #           --warn-return-any,
+  #           --warn-unreachable,
+  #           --warn-unused-configs,
+  #           --warn-unused-ignores,
+  #         ]
+  - repo: https://github.com/igorshubovych/markdownlint-cli
+    rev: v0.39.0
+    hooks:
+      - id: markdownlint
+        args: [--disable, MD013]
+      - id: markdownlint-fix
+        args: [--disable, MD013]
+  - repo: https://github.com/pdm-project/pdm
+    rev: 2.12.3
+    hooks:
+      - id: pdm-lock-check

README.md

@@ -1,2 +1,63 @@
 # unstract-python-client
 Python client for the Unstract LLM-powered structured data extraction platform
+
+
+## Installation
+
+You can install the Unstract Python Client using pip:
+
+```bash
+pip install unstract-client
+```
+
+## Usage
+
+First, import the `APIDeploymentsClient` from the `client` module:
+
+```python
+from unstract.api_deployments.client import APIDeploymentsClient
+```
+
+Then, create an instance of the `APIDeploymentsClient`:
+
+```python
+client = APIDeploymentsClient(api_url="url", api_key="your_api_key")
+```
+
+Now, you can use the client to interact with the Unstract API deployments API:
+
+```python
+try:
+    adc = APIDeploymentsClient(
+        api_url=os.getenv("UNSTRACT_API_URL"),
+        api_key=os.getenv("UNSTRACT_API_DEPLOYMENT_KEY"),
+        api_timeout=10,
+        logging_level="DEBUG",
+    )
+    # Replace files with pdfs
+    response = adc.structure_file(
+        ["<files>"]
+    )
+    print(response)
+    if response["pending"]:
+        while True:
+            p_response = adc.check_execution_status(
+                response["status_check_api_endpoint"]
+            )
+            print(p_response)
+            if not p_response["pending"]:
+                break
+            print("Sleeping and checking again in 5 seconds..")
+            time.sleep(5)
+except APIDeploymentsClientException as e:
+    print(e)
+```
+
+
+## Questions and Feedback
+
+On Slack, [join great conversations](https://join-slack.unstract.com/) around LLMs, their ecosystem and leveraging them to automate the previously unautomatable!
+
+[Unstract Cloud](https://unstract.com/): Signup and Try!
+
+[Unstract developer documentation](https://docs.unstract.com/): Learn more about Unstract and its API.