docpick 0.1.0__tar.gz

docpick-0.1.0/.gitignore

@@ -0,0 +1,47 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+*.egg-info/
+dist/
+build/
+*.egg
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Models / large files
+*.onnx
+*.pt
+*.pth
+*.bin
+*.safetensors
+
+# Logs
+*.log
+
+# Environment
+.env
+.env.local
+CLAUDE.md
+PLAN.txt

docpick-0.1.0/LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by the Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding any notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 QuartzUnit
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

docpick-0.1.0/PKG-INFO

@@ -0,0 +1,282 @@
+Metadata-Version: 2.4
+Name: docpick
+Version: 0.1.0
+Summary: Document in, Structured JSON out. Schema-driven document extraction with local OCR + LLM.
+Project-URL: Homepage, https://github.com/QuartzUnit/docpick
+Project-URL: Repository, https://github.com/QuartzUnit/docpick
+Project-URL: Issues, https://github.com/QuartzUnit/docpick/issues
+Author: QuartzUnit
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: document-extraction,idp,invoice,llm,ocr,schema,structured-data
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Image Recognition
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.11
+Requires-Dist: click>=8.0
+Requires-Dist: httpx>=0.27
+Requires-Dist: pillow>=10.0
+Requires-Dist: pydantic-settings>=2.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pypdfium2>=4.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0
+Provides-Extra: all
+Requires-Dist: easyocr>=1.7; extra == 'all'
+Requires-Dist: paddleocr>=2.9; extra == 'all'
+Requires-Dist: paddlepaddle>=3.0; extra == 'all'
+Requires-Dist: torch>=2.0; extra == 'all'
+Requires-Dist: transformers>=4.40; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.24; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.8; extra == 'dev'
+Provides-Extra: easyocr
+Requires-Dist: easyocr>=1.7; extra == 'easyocr'
+Provides-Extra: got
+Requires-Dist: torch>=2.0; extra == 'got'
+Requires-Dist: transformers>=4.40; extra == 'got'
+Provides-Extra: paddle
+Requires-Dist: paddleocr>=2.9; extra == 'paddle'
+Requires-Dist: paddlepaddle>=3.0; extra == 'paddle'
+Description-Content-Type: text/markdown
+
+# Docpick
+
+> Document in, Structured JSON out. Locally. With your schema.
+
+**docpick** is a lightweight, schema-driven document extraction pipeline that combines local OCR engines with local LLMs to extract structured JSON from any document — invoices, receipts, bills of lading, tax forms, and more.
+
+- **Zero cloud dependency** — runs entirely on your machine (CPU or GPU)
+- **Custom schemas** — define your own Pydantic models or use 8 built-in document schemas
+- **Validation built-in** — checkdigit verification, cross-field rules, cross-document consistency
+- **Apache 2.0** — no GPL/AGPL dependencies
+
+## Install
+
+```bash
+pip install docpick            # core (LLM extraction only)
+pip install docpick[paddle]    # + PaddleOCR (recommended)
+pip install docpick[easyocr]   # + EasyOCR (Korean-optimized)
+pip install docpick[got]       # + GOT-OCR2.0 (GPU, vision-language)
+pip install docpick[all]       # all OCR backends
+```
+
+**Requirements:** Python 3.11+ / LLM endpoint (vLLM, Ollama, or OpenAI-compatible)
+
+## Quick Start
+
+### Python API
+
+```python
+from docpick import DocpickPipeline
+from docpick.schemas import InvoiceSchema
+
+pipeline = DocpickPipeline()
+result = pipeline.extract("invoice.pdf", schema=InvoiceSchema)
+
+print(result.data)           # Structured dict matching schema
+print(result.validation)     # Validation errors/warnings
+print(result.confidence)     # Per-field confidence scores
+```
+
+### CLI
+
+```bash
+# Extract structured data
+docpick extract invoice.pdf --schema invoice --output result.json
+
+# OCR only (no LLM)
+docpick ocr document.png --lang ko,en
+
+# Validate extracted JSON
+docpick validate result.json --schema invoice
+
+# Batch process a directory
+docpick batch ./documents/ --schema invoice --output ./results/ --concurrency 4
+
+# List available schemas
+docpick schemas list
+
+# Show schema details
+docpick schemas show invoice
+```
+
+## Built-in Schemas
+
+| Schema | Document Type | Key Validations |
+|--------|--------------|-----------------|
+| `invoice` | Commercial invoices | Line item sums, tax ID checkdigit, date order |
+| `receipt` | Retail/restaurant receipts | Total = subtotal + tax + tip |
+| `bill_of_lading` | Ocean/air B/L | Container weight sums, ISO 6346, HS code format |
+| `purchase_order` | Purchase orders | PO total = line items, delivery date order |
+| `kr_tax_invoice` | Korean e-tax invoice (세금계산서) | Business number checkdigit (x2), supply/tax/total sums |
+| `bank_statement` | Bank statements | IBAN mod97, period date order |
+| `id_document` | Passport/ID (ICAO 9303) | MRZ, ISO 3166 country codes, date ranges |
+| `certificate_of_origin` | Certificate of Origin | ISO 3166 alpha-2 country codes |
+
+## Custom Schemas
+
+Define your own schema with Pydantic:
+
+```python
+from pydantic import BaseModel
+from docpick import DocpickPipeline
+from docpick.validation.rules import SumEqualsRule, RequiredFieldRule
+
+class MyDocument(BaseModel):
+    """Custom document schema."""
+    company_name: str | None = None
+    total_amount: float | None = None
+    tax_amount: float | None = None
+    net_amount: float | None = None
+    items: list[dict] | None = None
+
+    class ValidationRules:
+        rules = [
+            RequiredFieldRule("company_name"),
+            SumEqualsRule(["net_amount", "tax_amount"], "total_amount"),
+        ]
+
+pipeline = DocpickPipeline()
+result = pipeline.extract("my_document.pdf", schema=MyDocument)
+```
+
+Or use a JSON Schema file:
+
+```bash
+docpick extract document.pdf --schema my_schema.json
+```
+
+## Validation
+
+### Check Digit Algorithms
+
+| Algorithm | Use Case |
+|-----------|----------|
+| `kr_business_number` | Korean business registration number (10 digits) |
+| `luhn` | Credit card numbers |
+| `iso_6346` | Shipping container numbers |
+| `iban_mod97` | International bank account numbers |
+| `awb_mod7` | Air waybill numbers |
+| `mrz` | Machine Readable Zone (passport/ID) |
+
+### Cross-Field Rules
+
+| Rule | Description |
+|------|-------------|
+| `SumEqualsRule` | Sum of fields equals target (with tolerance) |
+| `DateBeforeRule` | Date A must precede Date B |
+| `RequiredFieldRule` | Field must be non-null and non-empty |
+| `FieldEqualsRule` | Two fields must be equal |
+| `RangeRule` | Numeric field within min/max bounds |
+| `RegexRule` | Field matches regex pattern |
+
+### Cross-Document Validation
+
+Validate consistency across related documents (e.g., Invoice + B/L + Packing List):
+
+```python
+from docpick.validation.cross_document import create_trade_document_validator
+
+validator = create_trade_document_validator()
+result = validator.validate({
+    "invoice": invoice_data,
+    "bl": bl_data,
+    "packing_list": packing_list_data,
+    "certificate": certificate_data,
+})
+print(result.is_valid)
+```
+
+## OCR Engines
+
+| Engine | Type | GPU | Languages | Best For |
+|--------|------|-----|-----------|----------|
+| PaddleOCR | Traditional OCR | Optional | 111 | General documents (default) |
+| EasyOCR | Traditional OCR | Optional | 80+ | Korean text |
+| GOT-OCR2.0 | Vision-Language | Required | Multi | Complex layouts |
+| VLM | Vision-Language | Required | Multi | Direct image → JSON |
+
+### 2-Tier Auto Engine
+
+The default `auto` engine uses confidence-based fallback:
+
+1. **Tier 1 (CPU):** PaddleOCR → EasyOCR
+2. **Tier 2 (GPU):** GOT-OCR2.0 → VLM
+
+If Tier 1 average confidence falls below threshold (default 0.7), automatically escalates to Tier 2.
+
+## LLM Providers
+
+| Provider | Endpoint | Default Model |
+|----------|----------|---------------|
+| vLLM | `http://localhost:30000/v1` | Qwen/Qwen3.5-32B-AWQ |
+| Ollama | `http://localhost:11434` | qwen3.5:7b |
+
+Configure via CLI or YAML:
+
+```bash
+docpick config set llm.provider ollama
+docpick config set llm.base_url http://localhost:11434
+docpick config set llm.model qwen3.5:7b
+```
+
+## Error Handling
+
+The pipeline is designed to be resilient:
+
+- **OCR failure** → automatic fallback to next available engine
+- **LLM JSON parse failure** → automatic retry with correction prompt (up to 1 retry)
+- **Partial results** → returns whatever was extracted, with errors logged in `result.errors`
+- **Document load failure** → returns empty result with error message
+
+```python
+result = pipeline.extract("damaged.pdf", schema=InvoiceSchema)
+if result.errors:
+    print("Pipeline warnings:", result.errors)
+if result.data:
+    print("Partial extraction:", result.data)
+```
+
+## Batch Processing
+
+Process entire directories with parallel workers:
+
+```python
+from docpick.batch import BatchProcessor
+from docpick.schemas import InvoiceSchema
+
+processor = BatchProcessor(concurrency=4)
+result = processor.process_directory(
+    "./invoices/",
+    schema=InvoiceSchema,
+    recursive=True,
+)
+
+print(f"Processed {result.succeeded}/{result.total} files")
+for path, extraction in result.results.items():
+    print(f"{path}: {extraction.data.get('total_amount')}")
+```
+
+## Architecture
+
+```
+Document (PDF/Image)
+  → DocumentLoader (pypdfium2)
+  → Tier 1: OCR (PaddleOCR/EasyOCR, CPU)
+    → [confidence < threshold] → Tier 2: VLM (GOT/VLM, GPU)
+  → LLM Extractor (vLLM/Ollama, schema prompt)
+  → Pydantic Validation (checkdigit, cross-field, cross-document)
+  → ExtractionResult (structured JSON + confidence + validation)
+```
+
+## License
+
+Apache 2.0 — all dependencies are Apache 2.0 or MIT licensed.