doctra 0.1.1__py3-none-any.whl → 0.3.0__py3-none-any.whl

doctra/utils/progress.py

@@ -0,0 +1,428 @@
+from __future__ import annotations
+
+import os
+import sys
+from typing import Optional, Dict, Any, Iterable, Iterator, Tuple
+from tqdm import tqdm
+from tqdm.auto import tqdm as tqdm_auto
+
+
+class ProgressConfig:
+    """
+    Central configuration for progress behavior, overridable via environment.
+
+    Env vars:
+    - DOCTRA_PROGRESS_DISABLE: "1" to disable progress entirely
+    - DOCTRA_PROGRESS_ASCII: "1" to force ASCII bars
+    - DOCTRA_PROGRESS_EMOJI: "0" to disable emoji prefixing
+    - DOCTRA_PROGRESS_NCOLS: integer width for bars
+    - DOCTRA_PROGRESS_EMOJI_MODE: one of {default, safe, ascii, none}
+    """
+
+    def __init__(self) -> None:
+        self.disable: bool = os.getenv("DOCTRA_PROGRESS_DISABLE", "0") == "1"
+        self.force_ascii: bool = os.getenv("DOCTRA_PROGRESS_ASCII", "0") == "1"
+        self.use_emoji: bool = os.getenv("DOCTRA_PROGRESS_EMOJI", "1") == "1"
+        self.ncols_env: Optional[int] = None
+        self.emoji_mode: str = os.getenv("DOCTRA_PROGRESS_EMOJI_MODE", "default").lower()
+        try:
+            ncols_val = os.getenv("DOCTRA_PROGRESS_NCOLS")
+            self.ncols_env = int(ncols_val) if ncols_val else None
+        except Exception:
+            self.ncols_env = None
+
+
+_PROGRESS_CONFIG = ProgressConfig()
+
+
+def _detect_environment() -> Tuple[bool, bool, bool]:
+    """
+    Returns (is_notebook, is_tty, is_windows).
+    """
+    is_notebook = "ipykernel" in sys.modules or "jupyter" in sys.modules
+    # Colab/Kaggle specifics
+    if "google.colab" in sys.modules:
+        is_notebook = True
+    if "kaggle_secrets" in sys.modules or "kaggle_web_client" in sys.modules:
+        is_notebook = True
+    is_tty = hasattr(sys.stdout, "isatty") and sys.stdout.isatty()
+    is_windows = sys.platform.startswith("win")
+    return is_notebook, is_tty, is_windows
+
+
+def _select_emoji(key: str) -> str:
+    """
+    Choose an emoji/symbol for a given key according to env and config.
+    Modes:
+      - default: rich emoji
+      - safe: single-codepoint symbols with stable width
+      - ascii: ASCII text tokens
+      - none: empty prefix
+    """
+    # Maps
+    default_map = {
+        "loading": "🔄",
+        "charts": "📊",
+        "tables": "📋",
+        "figures": "🖼️",
+        "ocr": "🔍",
+        "vlm": "🤖",
+        "processing": "⚙️",
+    }
+    safe_map = {
+        # Use BMP or geometric shapes likely to render everywhere
+        "loading": "⏳",
+        "charts": "▦",
+        "tables": "▤",
+        "figures": "▧",
+        "ocr": "🔎",
+        "vlm": "★",
+        "processing": "⚙",  # no variation selector
+    }
+    ascii_map = {
+        "loading": "[loading]",
+        "charts": "[charts]",
+        "tables": "[tables]",
+        "figures": "[figures]",
+        "ocr": "[ocr]",
+        "vlm": "[vlm]",
+        "processing": "[processing]",
+    }
+
+    # Determine effective mode
+    mode = _PROGRESS_CONFIG.emoji_mode
+    is_notebook, _, is_windows = _detect_environment()
+    if not _PROGRESS_CONFIG.use_emoji:
+        mode = "none"
+    elif mode == "default":
+        # Heuristics: prefer safe in Colab/Kaggle notebooks and Windows terminals
+        if is_windows or "google.colab" in sys.modules or "kaggle_secrets" in sys.modules:
+            mode = "safe"
+
+    if mode == "none":
+        return ""
+    if mode == "ascii":
+        return ascii_map.get(key, "")
+    if mode == "safe":
+        return safe_map.get(key, safe_map["processing"])
+    # default
+    return default_map.get(key, default_map["processing"])
+
+
+def _supports_unicode_output() -> bool:
+    """Best-effort detection whether stdout likely supports Unicode/emoji."""
+    try:
+        enc = getattr(sys.stdout, "encoding", None) or ""
+        enc_lower = enc.lower()
+        if "utf" in enc_lower:
+            return True
+    except Exception:
+        pass
+
+    # Heuristics for common notebook environments that support emoji
+    env = os.environ
+    if any(k in env for k in ("COLAB_GPU", "GCE_METADATA_HOST", "KAGGLE_KERNEL_RUN_TYPE", "JPY_PARENT_PID")):
+        return True
+
+    # On modern Windows terminals with UTF-8 code page, assume yes
+    if sys.platform.startswith("win"):
+        # If user opted-in to force ASCII, respect it
+        if _PROGRESS_CONFIG.force_ascii:
+            return False
+        # Try to detect WT/Terminal/VSCode which usually handle Unicode
+        if any(k in env for k in ("WT_SESSION", "TERM_PROGRAM", "VSCODE_PID")):
+            return True
+
+    return False
+
+
+def create_beautiful_progress_bar(
+    total: int,
+    desc: str,
+    leave: bool = True,
+    position: Optional[int] = None,
+    **kwargs
+) -> tqdm:
+    """
+    Create a beautiful and interactive tqdm progress bar with enhanced styling.
+    
+    Features:
+    - Colorful progress bars with gradients
+    - Emoji icons for different operations
+    - Better formatting and spacing
+    - Interactive features
+    - Responsive design
+    
+    :param total: Total number of items to process
+    :param desc: Description text for the progress bar
+    :param leave: Whether to leave the progress bar after completion
+    :param position: Position of the progress bar (for multiple bars)
+    :param kwargs: Additional tqdm parameters
+    :return: Configured tqdm progress bar instance
+    """
+    
+    # Enhanced styling parameters - notebook-friendly format
+    is_notebook, is_tty, is_windows = _detect_environment()
+    if is_notebook:
+        # Simpler format for notebooks to avoid display issues
+        bar_format = "{desc}: {percentage:3.0f}%|{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}]"
+    else:
+        # Full format for terminal
+        bar_format = (
+            "{l_bar}{bar:30}| {n_fmt}/{total_fmt} "
+            "[{elapsed}<{remaining}, {rate_fmt}{postfix}]"
+        )
+    
+    # Color schemes based on operation type
+    color_schemes = {
+        "loading": {"colour": "cyan", "ncols": 100},
+        "charts": {"colour": "green", "ncols": 100},
+        "tables": {"colour": "blue", "ncols": 100},
+        "figures": {"colour": "magenta", "ncols": 100},
+        "ocr": {"colour": "yellow", "ncols": 100},
+        "vlm": {"colour": "red", "ncols": 100},
+        "processing": {"colour": "white", "ncols": 100},
+    }
+    
+    # Determine color scheme based on description
+    desc_lower = desc.lower()
+    if "loading" in desc_lower or "model" in desc_lower:
+        color_scheme = color_schemes["loading"]
+    elif "chart" in desc_lower:
+        color_scheme = color_schemes["charts"]
+    elif "table" in desc_lower:
+        color_scheme = color_schemes["tables"]
+    elif "figure" in desc_lower:
+        color_scheme = color_schemes["figures"]
+    elif "ocr" in desc_lower:
+        color_scheme = color_schemes["ocr"]
+    elif "vlm" in desc_lower:
+        color_scheme = color_schemes["vlm"]
+    else:
+        color_scheme = color_schemes["processing"]
+    
+    # Emoji categories
+    emoji_categories = {"loading", "charts", "tables", "figures", "ocr", "vlm", "processing"}
+    
+    # Add appropriate emoji to description (can be disabled)
+    if _PROGRESS_CONFIG.use_emoji:
+        prefix_key = next((k for k in emoji_categories if k in desc_lower), "processing")
+        prefix = _select_emoji(prefix_key)
+        if prefix:
+            desc = f"{prefix} {desc}"
+    
+    # Enhanced tqdm configuration
+    tqdm_config = {
+        "total": total,
+        "desc": desc,
+        "leave": leave,
+        "bar_format": bar_format,
+        "ncols": _PROGRESS_CONFIG.ncols_env or color_scheme["ncols"],
+        # Prefer Unicode unless user forces ASCII or environment lacks Unicode support
+        "ascii": _PROGRESS_CONFIG.force_ascii or not _supports_unicode_output(),
+        "dynamic_ncols": True,  # Responsive width
+        "smoothing": 0.3,  # Smooth progress updates
+        "mininterval": 0.1,  # Minimum update interval
+        "maxinterval": 1.0,  # Maximum update interval
+        "position": position,
+        **kwargs
+    }
+    
+    # Enhanced environment detection
+    is_notebook, is_terminal, is_windows = _detect_environment()
+    
+    # Add color only for terminal environments (not notebooks)
+    if not is_notebook and is_terminal:
+        tqdm_config["colour"] = color_scheme["colour"]
+    
+    # Respect global disable
+    if _PROGRESS_CONFIG.disable:
+        tqdm_config["disable"] = True
+
+    # Try creating the progress bar with Unicode, fallback to ASCII on failure (e.g., Windows code page)
+    if is_notebook:
+        tqdm_config.pop("colour", None)
+        try:
+            return tqdm_auto(**tqdm_config)
+        except Exception:
+            tqdm_config["ascii"] = True
+            return tqdm_auto(**tqdm_config)
+    else:
+        try:
+            return tqdm(**tqdm_config)
+        except Exception:
+            tqdm_config["ascii"] = True
+            return tqdm(**tqdm_config)
+
+
+def create_multi_progress_bars(
+    descriptions: list[str],
+    totals: list[int],
+    positions: Optional[list[int]] = None
+) -> list[tqdm]:
+    """
+    Create multiple beautiful progress bars for concurrent operations.
+    
+    :param descriptions: List of descriptions for each progress bar
+    :param totals: List of totals for each progress bar
+    :param positions: Optional list of positions for each bar
+    :return: List of configured tqdm progress bar instances
+    """
+    if positions is None:
+        positions = list(range(len(descriptions)))
+    
+    bars = []
+    for desc, total, pos in zip(descriptions, totals, positions):
+        bar = create_beautiful_progress_bar(
+            total=total,
+            desc=desc,
+            position=pos,
+            leave=True
+        )
+        bars.append(bar)
+    
+    return bars
+
+
+def update_progress_with_info(
+    bar: tqdm,
+    increment: int = 1,
+    info: Optional[Dict[str, Any]] = None
+) -> None:
+    """
+    Update progress bar with additional information.
+    
+    :param bar: tqdm progress bar instance
+    :param increment: Number to increment the progress
+    :param info: Optional dictionary of information to display
+    """
+    if info:
+        # Format info as postfix
+        postfix_parts = []
+        for key, value in info.items():
+            if isinstance(value, float):
+                postfix_parts.append(f"{key}: {value:.2f}")
+            else:
+                postfix_parts.append(f"{key}: {value}")
+        
+        bar.set_postfix_str(", ".join(postfix_parts))
+    
+    bar.update(increment)
+
+
+def create_loading_bar(desc: str = "Loading", **kwargs) -> tqdm:
+    """
+    Create a special loading progress bar for model initialization.
+    
+    :param desc: Description for the loading operation
+    :param kwargs: Additional tqdm parameters
+    :return: Configured loading progress bar
+    """
+    return create_beautiful_progress_bar(
+        total=1,
+        desc=desc,
+        leave=True,
+        **kwargs
+    )
+
+
+def create_processing_bar(
+    total: int,
+    operation: str,
+    **kwargs
+) -> tqdm:
+    """
+    Create a processing progress bar for data operations.
+    
+    :param total: Total number of items to process
+    :param operation: Type of operation (charts, tables, figures, etc.)
+    :param kwargs: Additional tqdm parameters
+    :return: Configured processing progress bar
+    """
+    desc = f"{operation.title()} (processing)"
+    return create_beautiful_progress_bar(
+        total=total,
+        desc=desc,
+        leave=True,
+        **kwargs
+    )
+
+
+def create_notebook_friendly_bar(
+    total: int,
+    desc: str,
+    **kwargs
+) -> tqdm:
+    """
+    Create a notebook-friendly progress bar with minimal formatting.
+    
+    This function creates progress bars specifically optimized for Jupyter notebooks
+    to avoid display issues and ANSI code problems.
+    
+    :param total: Total number of items to process
+    :param desc: Description text for the progress bar
+    :param kwargs: Additional tqdm parameters
+    :return: Configured notebook-friendly progress bar
+    """
+    # Force notebook mode
+    if _PROGRESS_CONFIG.disable:
+        kwargs["disable"] = True
+    else:
+        kwargs["disable"] = False
+    # Prefer Unicode in notebooks if supported
+    if "ascii" not in kwargs:
+        kwargs["ascii"] = _PROGRESS_CONFIG.force_ascii or not _supports_unicode_output()
+    
+    # Emoji categories
+    emoji_categories = {"loading", "charts", "tables", "figures", "ocr", "vlm", "processing"}
+    
+    # Add appropriate emoji to description
+    desc_lower = desc.lower()
+    if _PROGRESS_CONFIG.use_emoji:
+        prefix_key = next((k for k in emoji_categories if k in desc_lower), "processing")
+        prefix = _select_emoji(prefix_key)
+        if prefix:
+            desc = f"{prefix} {desc}"
+    
+    # Simple format for notebooks
+    bar_format = "{desc}: {percentage:3.0f}%|{bar}| {n_fmt}/{total_fmt}"
+    
+    tqdm_config = {
+        "total": total,
+        "desc": desc,
+        "leave": True,
+        "bar_format": bar_format,
+        "ncols": _PROGRESS_CONFIG.ncols_env or 80,
+        "ascii": kwargs.get("ascii", False),
+        "dynamic_ncols": False,  # Fixed width for notebooks
+        "smoothing": 0.1,  # Faster updates
+        "mininterval": 0.05,
+        "maxinterval": 0.5,
+        **kwargs
+    }
+    
+    return tqdm_auto(**tqdm_config)
+
+
+def progress_for(iterable: Iterable[Any], desc: str, total: Optional[int] = None, leave: bool = True, **kwargs) -> Iterator[Any]:
+    """
+    Wrap an iterable with a configured progress bar.
+    Respects env config and auto-detects notebook vs terminal.
+    """
+    if _PROGRESS_CONFIG.disable:
+        for item in iterable:
+            yield item
+        return
+
+    is_notebook, _, _ = _detect_environment()
+    bar_factory = create_notebook_friendly_bar if is_notebook else create_beautiful_progress_bar
+    with bar_factory(total=total if total is not None else 0, desc=desc, leave=leave, **kwargs) as bar:
+        if total is None:
+            # Unknown total: manual increments
+            for item in iterable:
+                yield item
+                bar.update(1)
+        else:
+            for item in iterable:
+                yield item
+                bar.update(1)

doctra/utils/structured_utils.py

@@ -1,49 +1,49 @@
-from __future__ import annotations
-from typing import Any, Dict, Optional
-import json
-
-try:
-    from pydantic import BaseModel  # type: ignore
-except Exception:  # pydantic not strictly required for normalization
-    class BaseModel:  # fallback stub
-        pass
-
-def to_structured_dict(obj: Any) -> Optional[Dict[str, Any]]:
-    """
-    Accepts a VLM result that might be:
-      - JSON string
-      - dict
-      - Pydantic BaseModel (v1 .dict() or v2 .model_dump())
-    Returns a normalized dict with keys: title, headers, rows — or None.
-    """
-    if obj is None:
-        return None
-
-    # JSON string from VLM
-    if isinstance(obj, str):
-        try:
-            obj = json.loads(obj)
-        except Exception:
-            return None
-
-    # Pydantic model
-    if isinstance(obj, BaseModel):
-        try:
-            return obj.model_dump()  # pydantic v2
-        except Exception:
-            try:
-                return obj.dict()    # pydantic v1
-            except Exception:
-                return None
-
-    # Plain dict
-    if isinstance(obj, dict):
-        title = obj.get("title") or "Untitled"
-        headers = obj.get("headers") or []
-        rows = obj.get("rows") or []
-        # Basic shape checks
-        if not isinstance(headers, list) or not isinstance(rows, list):
-            return None
-        return {"title": title, "headers": headers, "rows": rows}
-
-    return None
+from __future__ import annotations
+from typing import Any, Dict, Optional
+import json
+
+try:
+    from pydantic import BaseModel  # type: ignore
+except Exception:  # pydantic not strictly required for normalization
+    class BaseModel:  # fallback stub
+        pass
+
+def to_structured_dict(obj: Any) -> Optional[Dict[str, Any]]:
+    """
+    Accepts a VLM result that might be:
+      - JSON string
+      - dict
+      - Pydantic BaseModel (v1 .dict() or v2 .model_dump())
+    Returns a normalized dict with keys: title, headers, rows — or None.
+    """
+    if obj is None:
+        return None
+
+    # JSON string from VLM
+    if isinstance(obj, str):
+        try:
+            obj = json.loads(obj)
+        except Exception:
+            return None
+
+    # Pydantic model
+    if isinstance(obj, BaseModel):
+        try:
+            return obj.model_dump()  # pydantic v2
+        except Exception:
+            try:
+                return obj.dict()    # pydantic v1
+            except Exception:
+                return None
+
+    # Plain dict
+    if isinstance(obj, dict):
+        title = obj.get("title") or "Untitled"
+        headers = obj.get("headers") or []
+        rows = obj.get("rows") or []
+        # Basic shape checks
+        if not isinstance(headers, list) or not isinstance(rows, list):
+            return None
+        return {"title": title, "headers": headers, "rows": rows}
+
+    return None

doctra/version.py

@@ -1,2 +1,2 @@
 """Version information for Doctra."""
-__version__ = '0.1.1'
+__version__ = '0.3.0'

{doctra-0.1.1.dist-info → doctra-0.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: doctra
-Version: 0.1.1
+Version: 0.3.0
 Summary: Parse, extract, and analyze documents with ease
 Home-page: https://github.com/AdemBoukhris457/Doctra
 Author: Adem Boukhris
@@ -241,6 +241,8 @@ Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == "openai"
 Provides-Extra: gemini
 Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.40.0; extra == "anthropic"
 Provides-Extra: dev
 Requires-Dist: pytest>=6.0; extra == "dev"
 Requires-Dist: pytest-cov>=2.0; extra == "dev"
@@ -329,7 +331,7 @@ parser = StructuredPDFParser()
 # Parser with VLM for structured data extraction
 parser = StructuredPDFParser(
     use_vlm=True,
-    vlm_provider="openai",  # or "gemini"
+    vlm_provider="openai",  # or "gemini" or "anthropic" or "openrouter"
     vlm_api_key="your_api_key_here"
 )
 
@@ -344,7 +346,7 @@ parser = StructuredPDFParser(
     # VLM Settings
     use_vlm=True,
     vlm_provider="openai",
-    vlm_model="gpt-4o",
+    vlm_model="gpt-5",
     vlm_api_key="your_api_key",
     
     # Layout Detection Settings
@@ -406,7 +408,7 @@ parser = ChartTablePDFParser(
     # VLM Settings
     use_vlm=True,
     vlm_provider="openai",
-    vlm_model="gpt-4o",
+    vlm_model="gpt-5",
     vlm_api_key="your_api_key",
     
     # Layout Detection Settings
@@ -545,7 +547,7 @@ parser = StructuredPDFParser(
     use_vlm=True,
     vlm_provider="openai",
     vlm_api_key="your_openai_api_key",
-    vlm__model="gpt-4o",
+    vlm__model="gpt-5",
     layout_model_name="PP-DocLayout_plus-L",
     dpi=300,  # Higher DPI for better quality
     min_score=0.5,  # Higher confidence threshold
@@ -623,4 +625,41 @@ parser.display_pages_with_boxes("document.pdf")
 - **Pandas**: Data manipulation
 - **OpenPyXL**: Excel file generation
 - **Google Generative AI**: For Gemini VLM integration
-- **OpenAI**: For GPT-4 VLM integration
+- **OpenAI**: For GPT-5 VLM integration
+
+## 🖥️ Web Interface (Gradio)
+
+You can try Doctra in a simple web UI powered by Gradio.
+
+### Run locally
+
+```bash
+pip install -U gradio
+python gradio_app.py
+```
+
+Then open the printed URL (default `http://127.0.0.1:7860`).
+
+Notes:
+- If using VLM, set the API key field in the UI or export `VLM_API_KEY`.
+- Outputs are saved under `outputs/<pdf_stem>/` and previewed in the UI.
+
+### Deploy on Hugging Face Spaces
+
+1) Create a new Space (type: Gradio, SDK: Python).
+
+2) Add these files to the Space repo:
+   - Your package code (or install from PyPI).
+   - `gradio_app.py` (entry point).
+   - `requirements.txt` with at least:
+
+```text
+doctra
+gradio
+```
+
+3) Set a secret named `VLM_API_KEY` if you want VLM features.
+
+4) In Space settings, set `python gradio_app.py` as the run command (or rely on auto-detect).
+
+The Space will build and expose the same interface for uploads and processing.

{doctra-0.1.1.dist-info → doctra-0.3.0.dist-info}/RECORD

@@ -1,29 +1,32 @@
-doctra/__init__.py,sha256=-Pkx0Vh4Hz3EQvLaxlL6Mo4lVig59FTN5LvUcxThn4U,519
-doctra/version.py,sha256=tiyU44F2UjL7SjuX_aL4-UZ5m_D9WOmXSUZQnjpR8PM,60
+doctra/__init__.py,sha256=ST_c2GWBoB0y_wpL1qsOeK4bR1RyJhMMn6I5VjVRI6Y,613
+doctra/version.py,sha256=hnuLMAgAv9rqQndLE3xdEZsa3vwZ4eZ2RVbRJjlJu8Y,60
 doctra/cli/__init__.py,sha256=4PTujjYRShOOUlZ7PwuWckShPWLC4v4CYIhJpzgyv1k,911
-doctra/cli/main.py,sha256=O3Bgov3rtf58AJHmuojJaptrH17X1mw19iTplId3gGo,35327
-doctra/cli/utils.py,sha256=QuttjEtBiFrOHmqZz4mjbf3GWZe26lYChPwa23Loz_4,11314
+doctra/cli/main.py,sha256=o_W1b5kx3xaTbWK6l4IYi0YLwffKBj5pQKflnlaG2Fw,35611
+doctra/cli/utils.py,sha256=IghiUZQCOmXODC5-5smHGz2KeV4xqbP4avmA1Mggln0,11800
 doctra/engines/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 doctra/engines/layout/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 doctra/engines/layout/layout_models.py,sha256=vuTzjWd3FD-SkFPngktmUVhOJ6Xvff6ufwFEq796PQs,3162
-doctra/engines/layout/paddle_layout.py,sha256=Yf6_OtBq_RSup8CSDofJUZxM_bJMBlCC0eSv5ib1uNk,9364
+doctra/engines/layout/paddle_layout.py,sha256=P2-Gk8wHpWoA5Jpmo_3OLI59zWq3HeAOBOUKKVdXu8I,6792
 doctra/engines/ocr/__init__.py,sha256=h6bFiveGXdI59fsKzCqOXki3C74DCndEmvloOtMqnR0,133
 doctra/engines/ocr/api.py,sha256=YOBKDLExXpvSiOsc_TDJasaMPxzdVx1llQCtYlsruWo,1280
 doctra/engines/ocr/path_resolver.py,sha256=2_7Nsekt3dCDU3oVsgdr62iMrlAhbGNfYwgh4G7S3pA,1492
 doctra/engines/ocr/pytesseract_engine.py,sha256=Imz2uwju6himkBiS8CH7DLxBRe-LtmMYZiOdb_6PoQw,2911
 doctra/engines/vlm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 doctra/engines/vlm/outlines_types.py,sha256=qL-G6MNiA5mxp1qAPVEFhOANp4NqVt_MQKseJCr_xXE,970
-doctra/engines/vlm/provider.py,sha256=ws-04Jhuvg0a3vXzz8cfMWIiwldoIFs3i_qSb2Q6enA,2137
-doctra/engines/vlm/service.py,sha256=cONhekqKfGo2fe-2g7YT89BHxytdjGhCSFyU3sJUzWI,4966
+doctra/engines/vlm/provider.py,sha256=aE8Eo1U-8XqAimakNlT0-T4etIyCV8rZ3DwxdqbFeTc,3131
+doctra/engines/vlm/service.py,sha256=Jwws2Jw68-IdHyvEWks4UCoP7Olhqt8IpXfCv5Z7Ml4,4724
 doctra/exporters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 doctra/exporters/excel_writer.py,sha256=U5Eb5SF7_ll1QveUapSWSkCRt3OEoisKEVUQ_7X8Wjo,7762
+doctra/exporters/html_writer.py,sha256=OlW24Eg5bZcjldRHtd3GDD7RrajuRXj43EJpXIJkYf8,38810
 doctra/exporters/image_saver.py,sha256=zsPoQ0CwoE643ui4iZMdXk96kv5mU8L_zC2JfF22N1A,1639
 doctra/exporters/markdown_table.py,sha256=4_OJIwG_WoIPYBzJx1njy_3tNVdkK6QKSP-P9r-b0zw,2030
 doctra/exporters/markdown_writer.py,sha256=L7EjF2MB8jYX7XkZ3a3NeeEC8gnb0qzRPTzIN9tdfuw,1027
 doctra/parsers/__init__.py,sha256=8M6LVzcWGpuTIK_1SMXML3ll7zK1CTHXGI5qXvqdm-A,206
 doctra/parsers/layout_order.py,sha256=W6b-T11H907RZ2FaZwNvnYhmvH11rpUzxC5yLkdf28k,640
-doctra/parsers/structured_pdf_parser.py,sha256=g0k9XsSJRVnJg4omrEC1Ef1MWZZ3Ve2OnXjMoc6IScU,19953
-doctra/parsers/table_chart_extractor.py,sha256=A-rjazOmx6d_8CbZXdebE4NsYYqiQP0wQktTfCp_pwI,12669
+doctra/parsers/structured_pdf_parser.py,sha256=fbDIQ6VFv1phFPC3lKgcjtCp0AdNA8Ny1dK0F726Pww,21357
+doctra/parsers/table_chart_extractor.py,sha256=JuoScqCQbPdQjy4ak77OcZHSPYKGHF4H39fEW6gF3eo,15323
+doctra/ui/__init__.py,sha256=XzOOKeGSBnUREuDQiCIWds1asFSa2nypFQTJXwclROA,85
+doctra/ui/app.py,sha256=FYDlEG_2pfp7SSHnA04NRNUhOcI-BJPh3qAf5dw5D6g,45903
 doctra/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 doctra/utils/bbox.py,sha256=R2-95p0KiWvet3TH27TQVvCar7WJg6z0u3L21iEDF-A,674
 doctra/utils/constants.py,sha256=ZWOvNDrvETbQ_pxHiX7vUW4J5Oj8_qnov0QacUOBizI,189
@@ -31,10 +34,11 @@ doctra/utils/file_ops.py,sha256=3IS0EQncs6Kaj27fcg2zxQX3xRSvtItIsyKGLYgeOgw,815
 doctra/utils/io_utils.py,sha256=L1bWV4-ybs2j_3ZEN7GfQVgdC73JKVECVnpwKbP0dy0,219
 doctra/utils/ocr_utils.py,sha256=Doa1uYBg3kRgRYd2aPq9fICHgHfrM_efdhZfI7jl6OM,780
 doctra/utils/pdf_io.py,sha256=c8EY47Z1iqVtlLFHS_n0qGuXJ5ERFaMUd84ivXV0b9E,706
+doctra/utils/progress.py,sha256=sNEjTdN32J1-eXFPqwZRw2EZQ1SXSesXBd5StJvtlmc,14481
 doctra/utils/quiet.py,sha256=5XPS-1CtJ0sVk6qgSQctdhr_wR8mP1xoJLoUbmkXROA,387
-doctra/utils/structured_utils.py,sha256=EdNhCUDLKvYcLqXbTGveNtIRGyQ3yzYhTh-zy_awwM4,1450
-doctra-0.1.1.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
-doctra-0.1.1.dist-info/METADATA,sha256=NI9kwistJwaI6sYQ0vp5df-4302_EpSG7QUnk2OpocM,26751
-doctra-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-doctra-0.1.1.dist-info/top_level.txt,sha256=jI7E8jHci2gP9y0GYaWxlg9jG0O5n3FjHJJPLXDXMds,7
-doctra-0.1.1.dist-info/RECORD,,
+doctra/utils/structured_utils.py,sha256=J-qTqo8eCjm36FaRJ_I482LFgYCpm3eukZm-gbNnchw,1401
+doctra-0.3.0.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
+doctra-0.3.0.dist-info/METADATA,sha256=tdfVsN0nDj_WcpptBvJvWF2tzdgp_0SfeeYya7oTqgU,27794
+doctra-0.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+doctra-0.3.0.dist-info/top_level.txt,sha256=jI7E8jHci2gP9y0GYaWxlg9jG0O5n3FjHJJPLXDXMds,7
+doctra-0.3.0.dist-info/RECORD,,