docslight 0.1.2__tar.gz → 0.1.3__tar.gz

{docslight-0.1.2 → docslight-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docslight
-Version: 0.1.2
+Version: 0.1.3
 Summary: Lightweight ComPDF document parsing and extraction SDK
 Author-email: ComPDF AI <support@compdf.com>
 License-Expression: MIT
@@ -87,14 +87,13 @@ Extract specific fields:
 docslight extract invoice.pdf --fields invoice_number,total_amount
 ```
 
-Launch the local Web UI workbench:
+Launch the local API server:
 
 ```bash
-pip install "docslight[web]"
 docslight web
-# Open http://127.0.0.1:8000
+# Health: http://127.0.0.1:8000/api/health
 
-# Or run the same Web UI directly as a module
+# Or run the same API server directly as a module
 python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 ```
 
@@ -104,7 +103,7 @@ python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 - **Parse → Markdown** — Convert PDF, DOCX, PPTX, XLSX, and images (PNG, JPG, TIFF, BMP, WebP) to clean Markdown
 - **Extract → JSON** — Pull structured data by field list, JSON Schema, or structured template (key-value + table extraction)
 - **CLI first** — Full-featured command-line interface, script-friendly
-- **Web UI** — Local Flask workbench with drag-and-drop, live preview with bbox highlights, and a Fields Builder UI
+- **API server** — Local Flask backend exposing parse, extract, preview, health, and system-info endpoints
 - **Batch processing** — `parse_batch()` / `extract_batch()` for multiple files
 - **Local LLM extraction** — Ollama or any OpenAI-compatible provider for offline extraction
 - **Document types** — Classify and route documents by type for cloud extraction
@@ -117,7 +116,7 @@ python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 | Core SDK & CLI | `pip install docslight` |
 | + Local parsing (OCR, Office) | `pip install "docslight[local]"` |
 | + Local LLM extraction | `pip install "docslight[local,local-llm]"` |
-| + Web UI workbench | `pip install "docslight[web]"` |
+| + API server | `pip install "docslight[web]"` |
 
 > Local CPU parsing is experimental. Validate accuracy and latency on your own documents before production use.
 
@@ -209,7 +208,7 @@ client = DocSlight(
 
 ```python
 results = client.parse_batch(["doc1.pdf", "doc2.pdf", "doc3.pdf"])
-for r in results:[release.ps1](scripts/release.ps1)
+for r in results:
     print(r.to_markdown()[:200])
 ```
 
@@ -229,25 +228,24 @@ docslight extract "D:\pdf\invoice\1.pdf" --mode local --fields invoice_number --
 # Extract with schema
 docslight extract invoice.pdf --schema schema.json
 
-# Web UI
+# API server
 docslight web --host 127.0.0.1 --port 8000
 ```
 
-## Web UI Workbench
+## API Server
 
-DocSlight Workbench is a local Flask app for visual document processing.
+DocSlight includes a local Flask API server for document processing. Frontend assets are not bundled in this package.
 
 ```bash
-pip install "docslight[web]"
 docslight web
 python -m docslight.web_app
 ```
 
-- **Parse & Extract tabs** — Switch between parsing and extraction workflows
-- **Drag-and-drop upload** — PDF, images, DOCX, PPTX, XLSX
-- **Live preview** — PDF page rendering with bbox highlight overlays
-- **Fields Builder** — Structured UI for building key-value and table extraction templates
-- **Download results** — One-click download of Markdown or JSON output
+- `GET /api/health`
+- `GET /api/system-info`
+- `POST /api/parse`
+- `POST /api/extract`
+- `POST /api/preview`
 
 ## Environment Variables
 

{docslight-0.1.2 → docslight-0.1.3}/README.md

@@ -39,16 +39,15 @@ Extract specific fields:
 docslight extract invoice.pdf --fields invoice_number,total_amount
 ```
 
-Launch the local Web UI workbench:
-
-```bash
-pip install "docslight[web]"
-docslight web
-# Open http://127.0.0.1:8000
-
-# Or run the same Web UI directly as a module
-python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
-```
+Launch the local API server:
+
+```bash
+docslight web
+# Health: http://127.0.0.1:8000/api/health
+
+# Or run the same API server directly as a module
+python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
+```
 
 ## Features
 
@@ -56,7 +55,7 @@ python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 - **Parse → Markdown** — Convert PDF, DOCX, PPTX, XLSX, and images (PNG, JPG, TIFF, BMP, WebP) to clean Markdown
 - **Extract → JSON** — Pull structured data by field list, JSON Schema, or structured template (key-value + table extraction)
 - **CLI first** — Full-featured command-line interface, script-friendly
-- **Web UI** — Local Flask workbench with drag-and-drop, live preview with bbox highlights, and a Fields Builder UI
+- **API server** — Local Flask backend exposing parse, extract, preview, health, and system-info endpoints
 - **Batch processing** — `parse_batch()` / `extract_batch()` for multiple files
 - **Local LLM extraction** — Ollama or any OpenAI-compatible provider for offline extraction
 - **Document types** — Classify and route documents by type for cloud extraction
@@ -69,7 +68,7 @@ python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 | Core SDK & CLI | `pip install docslight` |
 | + Local parsing (OCR, Office) | `pip install "docslight[local]"` |
 | + Local LLM extraction | `pip install "docslight[local,local-llm]"` |
-| + Web UI workbench | `pip install "docslight[web]"` |
+| + API server | `pip install "docslight[web]"` |
 
 > Local CPU parsing is experimental. Validate accuracy and latency on your own documents before production use.
 
@@ -160,9 +159,9 @@ client = DocSlight(
 ### Batch Processing
 
 ```python
-results = client.parse_batch(["doc1.pdf", "doc2.pdf", "doc3.pdf"])
-for r in results:[release.ps1](scripts/release.ps1)
-    print(r.to_markdown()[:200])
+results = client.parse_batch(["doc1.pdf", "doc2.pdf", "doc3.pdf"])
+for r in results:
+    print(r.to_markdown()[:200])
 ```
 
 ## CLI Usage
@@ -181,25 +180,24 @@ docslight extract "D:\pdf\invoice\1.pdf" --mode local --fields invoice_number --
 # Extract with schema
 docslight extract invoice.pdf --schema schema.json
 
-# Web UI
-docslight web --host 127.0.0.1 --port 8000
-```
-
-## Web UI Workbench
-
-DocSlight Workbench is a local Flask app for visual document processing.
-
-```bash
-pip install "docslight[web]"
-docslight web
-python -m docslight.web_app
-```
-
-- **Parse & Extract tabs** — Switch between parsing and extraction workflows
-- **Drag-and-drop upload** — PDF, images, DOCX, PPTX, XLSX
-- **Live preview** — PDF page rendering with bbox highlight overlays
-- **Fields Builder** — Structured UI for building key-value and table extraction templates
-- **Download results** — One-click download of Markdown or JSON output
+# API server
+docslight web --host 127.0.0.1 --port 8000
+```
+
+## API Server
+
+DocSlight includes a local Flask API server for document processing. Frontend assets are not bundled in this package.
+
+```bash
+docslight web
+python -m docslight.web_app
+```
+
+- `GET /api/health`
+- `GET /api/system-info`
+- `POST /api/parse`
+- `POST /api/extract`
+- `POST /api/preview`
 
 ## Environment Variables
 

{docslight-0.1.2 → docslight-0.1.3}/docslight/cli.py

@@ -108,7 +108,7 @@ def _to_pretty_json(data: Any) -> str:
     return json.dumps(data, ensure_ascii=False, indent=2)
 
 
-def run_web_app(host: str, port: int, debug: bool) -> None:
+def run_web_app(host: str, port: int, debug: bool) -> None:
     """Run the optional Flask web application."""
     if importlib.util.find_spec("docslight.web_app") is None:
         raise CLIUsageError(WEB_EXTRA_ERROR)
@@ -119,8 +119,8 @@ def run_web_app(host: str, port: int, debug: bool) -> None:
         if exc.name in {"flask", "werkzeug"}:
             raise CLIUsageError(WEB_EXTRA_ERROR) from exc
         raise
-    _run_web_app = web_app.run_web_app
-    _run_web_app(host, port, debug)
+    _run_web_app = web_app.run_web_app
+    _run_web_app(host, port, debug)
 
 
 def _print_cli_error(error: Exception) -> int:
@@ -165,10 +165,10 @@ def build_parser() -> argparse.ArgumentParser:
     extract_parser.set_defaults(func=_run_extract)
 
     web_parser = subparsers.add_parser("web", help="Run the web application")
-    web_parser.add_argument("--host", default="127.0.0.1")
-    web_parser.add_argument("--port", type=int, default=8000)
-    web_parser.add_argument("--debug", action="store_true")
-    web_parser.set_defaults(func=_run_web)
+    web_parser.add_argument("--host", default="127.0.0.1")
+    web_parser.add_argument("--port", type=int, default=8000)
+    web_parser.add_argument("--debug", action="store_true")
+    web_parser.set_defaults(func=_run_web)
 
     return parser
 
@@ -227,9 +227,9 @@ def _run_extract(args: argparse.Namespace) -> int:
     return 0
 
 
-def _run_web(args: argparse.Namespace) -> int:
-    run_web_app(args.host, args.port, args.debug)
-    return 0
+def _run_web(args: argparse.Namespace) -> int:
+    run_web_app(args.host, args.port, args.debug)
+    return 0
 
 
 def main(argv: Sequence[str] | None = None) -> int:

{docslight-0.1.2 → docslight-0.1.3}/docslight/preview.py

@@ -1,4 +1,4 @@
-"""Preview rendering helpers for the local Web UI."""
+"""Preview rendering helpers for the local API server."""
 
 from __future__ import annotations
 

{docslight-0.1.2 → docslight-0.1.3}/docslight/schemas/fields.py

@@ -11,8 +11,8 @@ NormalizedFields = list[str] | StructuredFields | None
 ExtractSchema = dict[str, Any]
 
 
-def normalize_fields(fields: list[str] | str | StructuredFields | None) -> NormalizedFields:
-    """Normalize extraction fields from SDK, CLI, or Web UI inputs."""
+def normalize_fields(fields: list[str] | str | StructuredFields | None) -> NormalizedFields:
+    """Normalize extraction fields from SDK, CLI, or API inputs."""
     if fields is None:
         return None
     if isinstance(fields, str):

{docslight-0.1.2 → docslight-0.1.3}/docslight/web_app.py

@@ -2,19 +2,19 @@
 
 from __future__ import annotations
 
-import argparse
-import base64
-import json
-import logging
-import sys
-import tempfile
+import argparse
+import base64
+import json
+import logging
+import sys
+import tempfile
 from collections.abc import Callable
 from io import BytesIO
 from json import JSONDecodeError
 from pathlib import Path
 from typing import Any, cast
 
-from flask import Flask, Response, jsonify, redirect, render_template, request, send_file, url_for
+from flask import Flask, Response, jsonify, request, send_file
 from werkzeug.datastructures import FileStorage
 from werkzeug.utils import secure_filename
 
@@ -58,21 +58,18 @@ OFFICE_PREVIEW_UNSUPPORTED_MESSAGE = (
 LOG_FORMAT = "%(levelname)s:%(name)s:%(message)s"
 
 
-def create_app(docslight_factory: Callable[..., Any] = DocSlight) -> Flask:
-    """Create the local DocSlight Flask application."""
-    app = Flask(__name__)
-
-    @app.get("/")
-    def index() -> Any:
-        return redirect(url_for("parse_page"))
-
-    @app.get("/parse")
-    def parse_page() -> str:
-        return render_template("parse.html", active_page="parse")
-
-    @app.get("/extract")
-    def extract_page() -> str:
-        return render_template("extract.html", active_page="extract")
+def create_app(docslight_factory: Callable[..., Any] = DocSlight) -> Flask:
+    """Create the local DocSlight Flask application."""
+    app = Flask(__name__)
+
+    @app.get("/")
+    def index() -> Any:
+        return jsonify(
+            {
+                "status": "healthy",
+                "service": "docslight-web",
+            }
+        )
 
     @app.get("/api/health")
     def health() -> Any:
@@ -160,7 +157,11 @@ def create_app(docslight_factory: Callable[..., Any] = DocSlight) -> Flask:
     return app
 
 
-def run_web_app(host: str = "127.0.0.1", port: int = 8000, debug: bool = False) -> None:
+def run_web_app(
+    host: str = "127.0.0.1",
+    port: int = 8000,
+    debug: bool = False,
+) -> None:
     """Run the local DocSlight web application."""
     _configure_web_logging(debug)
     create_app().run(host=host, port=port, debug=debug)
@@ -183,17 +184,17 @@ def build_parser() -> argparse.ArgumentParser:
         prog="python -m docslight.web_app",
         description="Run the DocSlight web application.",
     )
-    parser.add_argument("--host", default="127.0.0.1")
-    parser.add_argument("--port", type=int, default=8000)
-    parser.add_argument("--debug", action="store_true")
-    return parser
+    parser.add_argument("--host", default="127.0.0.1")
+    parser.add_argument("--port", type=int, default=8000)
+    parser.add_argument("--debug", action="store_true")
+    return parser
 
 
 def main(argv: list[str] | None = None) -> int:
-    """Run the standalone DocSlight web application entrypoint."""
-    args = build_parser().parse_args(argv)
-    run_web_app(args.host, args.port, args.debug)
-    return 0
+    """Run the standalone DocSlight web application entrypoint."""
+    args = build_parser().parse_args(argv)
+    run_web_app(args.host, args.port, args.debug)
+    return 0
 
 
 def local_llm_from_form(form: Any) -> dict[str, str] | None:

{docslight-0.1.2 → docslight-0.1.3}/docslight.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docslight
-Version: 0.1.2
+Version: 0.1.3
 Summary: Lightweight ComPDF document parsing and extraction SDK
 Author-email: ComPDF AI <support@compdf.com>
 License-Expression: MIT
@@ -87,14 +87,13 @@ Extract specific fields:
 docslight extract invoice.pdf --fields invoice_number,total_amount
 ```
 
-Launch the local Web UI workbench:
+Launch the local API server:
 
 ```bash
-pip install "docslight[web]"
 docslight web
-# Open http://127.0.0.1:8000
+# Health: http://127.0.0.1:8000/api/health
 
-# Or run the same Web UI directly as a module
+# Or run the same API server directly as a module
 python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 ```
 
@@ -104,7 +103,7 @@ python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 - **Parse → Markdown** — Convert PDF, DOCX, PPTX, XLSX, and images (PNG, JPG, TIFF, BMP, WebP) to clean Markdown
 - **Extract → JSON** — Pull structured data by field list, JSON Schema, or structured template (key-value + table extraction)
 - **CLI first** — Full-featured command-line interface, script-friendly
-- **Web UI** — Local Flask workbench with drag-and-drop, live preview with bbox highlights, and a Fields Builder UI
+- **API server** — Local Flask backend exposing parse, extract, preview, health, and system-info endpoints
 - **Batch processing** — `parse_batch()` / `extract_batch()` for multiple files
 - **Local LLM extraction** — Ollama or any OpenAI-compatible provider for offline extraction
 - **Document types** — Classify and route documents by type for cloud extraction
@@ -117,7 +116,7 @@ python -m docslight.web_app --host 0.0.0.0 --port 8000 --debug
 | Core SDK & CLI | `pip install docslight` |
 | + Local parsing (OCR, Office) | `pip install "docslight[local]"` |
 | + Local LLM extraction | `pip install "docslight[local,local-llm]"` |
-| + Web UI workbench | `pip install "docslight[web]"` |
+| + API server | `pip install "docslight[web]"` |
 
 > Local CPU parsing is experimental. Validate accuracy and latency on your own documents before production use.
 
@@ -209,7 +208,7 @@ client = DocSlight(
 
 ```python
 results = client.parse_batch(["doc1.pdf", "doc2.pdf", "doc3.pdf"])
-for r in results:[release.ps1](scripts/release.ps1)
+for r in results:
     print(r.to_markdown()[:200])
 ```
 
@@ -229,25 +228,24 @@ docslight extract "D:\pdf\invoice\1.pdf" --mode local --fields invoice_number --
 # Extract with schema
 docslight extract invoice.pdf --schema schema.json
 
-# Web UI
+# API server
 docslight web --host 127.0.0.1 --port 8000
 ```
 
-## Web UI Workbench
+## API Server
 
-DocSlight Workbench is a local Flask app for visual document processing.
+DocSlight includes a local Flask API server for document processing. Frontend assets are not bundled in this package.
 
 ```bash
-pip install "docslight[web]"
 docslight web
 python -m docslight.web_app
 ```
 
-- **Parse & Extract tabs** — Switch between parsing and extraction workflows
-- **Drag-and-drop upload** — PDF, images, DOCX, PPTX, XLSX
-- **Live preview** — PDF page rendering with bbox highlight overlays
-- **Fields Builder** — Structured UI for building key-value and table extraction templates
-- **Download results** — One-click download of Markdown or JSON output
+- `GET /api/health`
+- `GET /api/system-info`
+- `POST /api/parse`
+- `POST /api/extract`
+- `POST /api/preview`
 
 ## Environment Variables
 

{docslight-0.1.2 → docslight-0.1.3}/docslight.egg-info/SOURCES.txt

@@ -31,12 +31,15 @@ docslight/providers/ollama.py
 docslight/providers/openai_compatible.py
 docslight/schemas/__init__.py
 docslight/schemas/fields.py
-docslight/static/styles.css
-docslight/static/app/common.js
-docslight/static/app/docslight-extract.json
-docslight/static/app/extract.js
-docslight/static/app/i18n.js
-docslight/static/app/parse.js
-docslight/templates/base.html
-docslight/templates/extract.html
-docslight/templates/parse.html
+tests/test_cli.py
+tests/test_cli_entrypoint.py
+tests/test_client.py
+tests/test_cloud_client.py
+tests/test_config_result.py
+tests/test_examples.py
+tests/test_local_llm.py
+tests/test_local_loader_parser.py
+tests/test_local_office_loader.py
+tests/test_local_pipeline.py
+tests/test_schema_helpers.py
+tests/test_web_app.py

{docslight-0.1.2 → docslight-0.1.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "docslight"
-version = "0.1.2"
+version = "0.1.3"
 description = "Lightweight ComPDF document parsing and extraction SDK"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -65,12 +65,9 @@ docslight = "docslight.cli:main"
 [tool.setuptools.packages.find]
 include = ["docslight*"]
 
-[tool.setuptools.package-data]
-docslight = ["templates/**/*", "static/**/*"]
-
-[tool.ruff]
-line-length = 88
-target-version = "py310"
+[tool.ruff]
+line-length = 88
+target-version = "py310"
 
 [tool.ruff.lint]
 select = ["E", "F", "I", "UP", "B"]