content-core 0.4.0__tar.gz → 0.5.0__tar.gz

{content_core-0.4.0 → content_core-0.5.0}/.gitignore

@@ -20,4 +20,4 @@ ai_docs/
 todo.md
 WIP/
 
-*.ignore
+*.ignore

content_core-0.4.0/README.md → content_core-0.5.0/PKG-INFO

@@ -1,3 +1,37 @@
+Metadata-Version: 2.4
+Name: content-core
+Version: 0.5.0
+Summary: Extract what matters from any media source
+Author-email: LUIS NOVO <lfnovo@gmail.com>
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: aiohttp>=3.11
+Requires-Dist: bs4>=0.0.2
+Requires-Dist: dicttoxml>=1.7.16
+Requires-Dist: esperanto>=1.2.0
+Requires-Dist: google-genai>=1.10.0
+Requires-Dist: jinja2>=3.1.6
+Requires-Dist: langdetect>=1.0.9
+Requires-Dist: langgraph>=0.3.29
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: openai>=1.73.0
+Requires-Dist: openpyxl>=3.1.5
+Requires-Dist: pandas>=2.2.3
+Requires-Dist: pydub>=0.25.1
+Requires-Dist: pymupdf>=1.25.5
+Requires-Dist: python-docx>=1.1.2
+Requires-Dist: python-dotenv>=1.1.0
+Requires-Dist: python-magic>=0.4.27
+Requires-Dist: python-pptx>=1.0.2
+Requires-Dist: validators>=0.34.0
+Requires-Dist: youtube-transcript-api>=1.0.3
+Provides-Extra: docling
+Requires-Dist: asciidoc; extra == 'docling'
+Requires-Dist: docling[ocr]; extra == 'docling'
+Requires-Dist: pandas; extra == 'docling'
+Requires-Dist: pillow; extra == 'docling'
+Description-Content-Type: text/markdown
+
 # Content Core
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -25,8 +59,10 @@ The primary goal of Content Core is to simplify the process of ingesting content
 Install Content Core using `pip`:
 
 ```bash
-# Install the package
+# Install the package (without Docling)
 pip install content-core
+# Install with Docling support
+pip install content-core[docling]
 ```
 
 Alternatively, if you’re developing locally:
@@ -195,12 +231,58 @@ async def main():
     md_data = await extract_content({"file_path": "path/to/your/document.md"})
     print(md_data)
 
+    # Per-execution override with Docling
+    doc_data = await extract_content({
+        "file_path": "path/to/your/document.pdf",
+        "engine": "docling",
+        "output_format": "html"
+    })
+    print(doc_data)
+
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
 (See `src/content_core/notebooks/run.ipynb` for more detailed examples.)
 
+## Docling Integration
+
+Content Core supports an optional Docling-based extraction engine for rich document formats (PDF, DOCX, PPTX, XLSX, Markdown, AsciiDoc, HTML, CSV, Images).
+
+### Installation
+
+```bash
+# Install with Docling support
+pip install content-core[docling]
+```
+
+### Enabling Docling
+
+#### Via configuration file
+
+In your `cc_config.yaml` or custom config, set:
+```yaml
+extraction:
+  engine: docling       # 'legacy' (default) or 'docling'
+  docling:
+    output_format: markdown  # markdown | html | json
+```
+
+#### Programmatically in Python
+
+```python
+from content_core.config import set_extraction_engine, set_docling_output_format
+
+# switch engine to Docling
+set_extraction_engine("docling")
+
+# choose output format: 'markdown', 'html', or 'json'
+set_docling_output_format("html")
+
+# now use ccore.extract or ccore.ccore
+result = await cc.extract("document.pdf")
+```
+
 ## Configuration
 
 Configuration settings (like API keys for external services, logging levels) can be managed through environment variables or `.env` files, loaded automatically via `python-dotenv`.

content_core-0.4.0/PKG-INFO → content_core-0.5.0/README.md

@@ -1,32 +1,3 @@
-Metadata-Version: 2.4
-Name: content-core
-Version: 0.4.0
-Summary: Extract what matters from any media source
-Author-email: LUIS NOVO <lfnovo@gmail.com>
-License-File: LICENSE
-Requires-Python: >=3.10
-Requires-Dist: aiohttp>=3.11
-Requires-Dist: bs4>=0.0.2
-Requires-Dist: dicttoxml>=1.7.16
-Requires-Dist: esperanto>=1.2.0
-Requires-Dist: google-genai>=1.10.0
-Requires-Dist: jinja2>=3.1.6
-Requires-Dist: langdetect>=1.0.9
-Requires-Dist: langgraph>=0.3.29
-Requires-Dist: loguru>=0.7.3
-Requires-Dist: openai>=1.73.0
-Requires-Dist: openpyxl>=3.1.5
-Requires-Dist: pandas>=2.2.3
-Requires-Dist: pydub>=0.25.1
-Requires-Dist: pymupdf>=1.25.5
-Requires-Dist: python-docx>=1.1.2
-Requires-Dist: python-dotenv>=1.1.0
-Requires-Dist: python-magic>=0.4.27
-Requires-Dist: python-pptx>=1.0.2
-Requires-Dist: validators>=0.34.0
-Requires-Dist: youtube-transcript-api>=1.0.3
-Description-Content-Type: text/markdown
-
 # Content Core
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -54,8 +25,10 @@ The primary goal of Content Core is to simplify the process of ingesting content
 Install Content Core using `pip`:
 
 ```bash
-# Install the package
+# Install the package (without Docling)
 pip install content-core
+# Install with Docling support
+pip install content-core[docling]
 ```
 
 Alternatively, if you’re developing locally:
@@ -224,12 +197,58 @@ async def main():
     md_data = await extract_content({"file_path": "path/to/your/document.md"})
     print(md_data)
 
+    # Per-execution override with Docling
+    doc_data = await extract_content({
+        "file_path": "path/to/your/document.pdf",
+        "engine": "docling",
+        "output_format": "html"
+    })
+    print(doc_data)
+
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
 (See `src/content_core/notebooks/run.ipynb` for more detailed examples.)
 
+## Docling Integration
+
+Content Core supports an optional Docling-based extraction engine for rich document formats (PDF, DOCX, PPTX, XLSX, Markdown, AsciiDoc, HTML, CSV, Images).
+
+### Installation
+
+```bash
+# Install with Docling support
+pip install content-core[docling]
+```
+
+### Enabling Docling
+
+#### Via configuration file
+
+In your `cc_config.yaml` or custom config, set:
+```yaml
+extraction:
+  engine: docling       # 'legacy' (default) or 'docling'
+  docling:
+    output_format: markdown  # markdown | html | json
+```
+
+#### Programmatically in Python
+
+```python
+from content_core.config import set_extraction_engine, set_docling_output_format
+
+# switch engine to Docling
+set_extraction_engine("docling")
+
+# choose output format: 'markdown', 'html', or 'json'
+set_docling_output_format("html")
+
+# now use ccore.extract or ccore.ccore
+result = await cc.extract("document.pdf")
+```
+
 ## Configuration
 
 Configuration settings (like API keys for external services, logging levels) can be managed through environment variables or `.env` files, loaded automatically via `python-dotenv`.

{content_core-0.4.0 → content_core-0.5.0}/docs/processors.md

@@ -14,11 +14,11 @@ Content Core uses a modular approach to process content from different sources.
 - **Returned Data**: The input text as-is, wrapped in a structured format compatible with Content Core's output schema.
 - **Location**: `src/content_core/processors/text.py`
 
-### 2. **Web Processor**
+### 2. **Web (URL) Processor**
 - **Purpose**: Extracts content from web URLs, focusing on meaningful text while ignoring boilerplate (ads, navigation, etc.).
 - **Supported Input**: URLs (web pages).
 - **Returned Data**: Extracted text content from the web page, often in a cleaned format.
-- **Location**: `src/content_core/processors/web.py`
+- **Location**: `src/content_core/processors/url.py`
 
 ### 3. **File Processor**
 - **Purpose**: Processes local files of various types, extracting content based on file format.
@@ -35,10 +35,33 @@ Content Core uses a modular approach to process content from different sources.
 - **Returned Data**: Transcribed text from the media content.
 - **Location**: `src/content_core/processors/transcription.py`
 
+### 5. **Docling Processor**
+- **Purpose**: Use Docling library for rich document parsing (PDF, DOCX, XLSX, PPTX, Markdown, AsciiDoc, HTML, CSV, images).
+- **Supported Input**: PDF, DOCX, XLSX, PPTX, Markdown, AsciiDoc, HTML, CSV, Images (PNG, JPEG, TIFF, BMP).
+- **Returned Data**: Content converted to configured format (markdown, html, json).
+- **Location**: `src/content_core/processors/docling.py`
+- **Configuration**: Activate the Docling engine in `cc_config.yaml` or custom config:
+  ```yaml
+  extraction:
+    engine: docling       # 'legacy' (default) or 'docling'
+    docling:
+      output_format: markdown  # markdown | html | json
+  ```
+- **Programmatic Toggle**: Use helper functions in Python:
+  ```python
+  from content_core.config import set_extraction_engine, set_docling_output_format
+
+  # switch engine to Docling
+  set_extraction_engine("docling")
+
+  # choose output format
+  set_docling_output_format("html")
+  ```
+
 ## How Processors Work
 
 Content Core automatically selects the appropriate processor based on the input type:
-- If a URL is provided, the Web Processor is used.
+- If a URL is provided, the Web (URL) Processor is used.
 - If a file path is provided, the File Processor determines the file type and delegates to specialized handlers (like the Media Transcription Processor for audio/video).
 - If raw text is provided, the Text Processor handles it directly.
 

{content_core-0.4.0 → content_core-0.5.0}/docs/usage.md

@@ -76,6 +76,60 @@ To simplify setup, we suggest copying the provided sample files:
 
 This will allow you to quickly start with customized settings without needing to create the files from scratch.
 
+### Docling Engine
+
+Content Core supports an optional Docling engine for advanced document parsing. To enable:
+
+#### In YAML config
+Add under the `extraction` section:
+```yaml
+extraction:
+  engine: docling        # legacy (default) or docling
+  docling:
+    output_format: html  # markdown | html | json
+```
+
+#### Programmatically in Python
+```python
+from content_core.config import set_extraction_engine, set_docling_output_format
+
+# toggle to Docling
+set_extraction_engine("docling")
+
+# pick format
+set_docling_output_format("json")
+```
+
+#### Per-Execution Overrides
+You can override the extraction engine and Docling output format on a per-call basis by including `engine` and `output_format` in your input:
+
+```python
+from content_core.content.extraction import extract_content
+
+# override engine and format for this document
+result = await extract_content({
+    "file_path": "document.pdf",
+    "engine": "docling",
+    "output_format": "html"
+})
+print(result.content)
+```
+
+Or using `ProcessSourceInput`:
+
+```python
+from content_core.common.state import ProcessSourceInput
+from content_core.content.extraction import extract_content
+
+input = ProcessSourceInput(
+    file_path="document.pdf",
+    engine="docling",
+    output_format="json"
+)
+result = await extract_content(input)
+print(result.content)
+```
+
 ## Support
 
 If you have questions or encounter issues while using the library, open an issue in the repository or contact the support team.

{content_core-0.4.0 → content_core-0.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "content-core"
-version = "0.4.0"
+version = "0.5.0"
 description = "Extract what matters from any media source"
 readme = "README.md"
 homepage = "https://github.com/lfnovo/content-core"
@@ -31,6 +31,9 @@ dependencies = [
     "validators>=0.34.0",
 ]
 
+[project.optional-dependencies]
+docling = ["docling[ocr]", "Pillow", "pandas", "asciidoc"]
+
 [project.scripts]
 ccore = "content_core:ccore"
 cclean = "content_core:cclean"

content_core-0.5.0/src/content_core/cc_config.yaml

@@ -0,0 +1,35 @@
+# Content Core main configuration
+# Copy this file to your project root or set CCORE_CONFIG_PATH to its location
+
+speech_to_text:
+  provider: openai
+  model_name: whisper-1
+
+default_model:
+  provider: openai
+  model_name: gpt-4o-mini
+  config:
+    temperature: 0.5
+    top_p: 1
+    max_tokens: 2000
+
+cleanup_model:
+  provider: openai
+  model_name: gpt-4o-mini
+  config:
+    temperature: 0
+    max_tokens: 8000
+    output_format: json
+
+summary_model:
+  provider: openai
+  model_name: gpt-4o-mini
+  config:
+    temperature: 0
+    top_p: 1
+    max_tokens: 2000
+
+extraction:
+  engine: legacy  # change to 'docling' to enable Docling engine
+  docling:
+    output_format: markdown  # markdown | html | json

{content_core-0.4.0 → content_core-0.5.0}/src/content_core/common/state.py

@@ -13,12 +13,16 @@ class ProcessSourceState(BaseModel):
     identified_provider: Optional[str] = ""
     metadata: Optional[dict] = Field(default_factory=lambda: {})
     content: Optional[str] = ""
+    engine: Optional[str] = Field(default=None, description="Override extraction engine: 'legacy' or 'docling'")
+    output_format: Optional[str] = Field(default=None, description="Override Docling output format: 'markdown', 'html', or 'json'")
 
 
 class ProcessSourceInput(BaseModel):
     content: Optional[str] = ""
     file_path: Optional[str] = ""
     url: Optional[str] = ""
+    engine: Optional[str] = None
+    output_format: Optional[str] = None
 
 
 class ProcessSourceOutput(BaseModel):

content_core-0.5.0/src/content_core/config.py

@@ -0,0 +1,46 @@
+import os
+import pkgutil
+import os  # needed for load_config env/path checks
+import yaml
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+def load_config():
+    config_path = os.environ.get("CCORE_CONFIG_PATH") or os.environ.get("CCORE_MODEL_CONFIG_PATH")
+    if config_path and os.path.exists(config_path):
+        try:
+            with open(config_path, "r") as file:
+                return yaml.safe_load(file)
+        except Exception as e:
+            print(f"Erro ao carregar o arquivo de configuração de {config_path}: {e}")
+            print("Usando configurações padrão internas.")
+
+    default_config_data = pkgutil.get_data("content_core", "models_config.yaml")
+    if default_config_data:
+        base = yaml.safe_load(default_config_data)
+    else:
+        base = {}
+    # load new cc_config.yaml defaults
+    cc_default = pkgutil.get_data("content_core", "cc_config.yaml")
+    if cc_default:
+        docling_cfg = yaml.safe_load(cc_default)
+        # merge extraction section
+        base["extraction"] = docling_cfg.get("extraction", {})
+    return base
+
+
+CONFIG = load_config()
+
+# Programmatic config overrides: use in notebooks or scripts
+def set_extraction_engine(engine: str):
+    """Override the extraction engine ('legacy' or 'docling')."""
+    CONFIG.setdefault("extraction", {})["engine"] = engine
+
+def set_docling_output_format(fmt: str):
+    """Override Docling output_format ('markdown', 'html', or 'json')."""
+    extraction = CONFIG.setdefault("extraction", {})
+    docling_cfg = extraction.setdefault("docling", {})
+    docling_cfg["output_format"] = fmt

{content_core-0.4.0 → content_core-0.5.0}/src/content_core/content/extraction/graph.py

@@ -20,10 +20,12 @@ from content_core.processors.text import extract_txt
 from content_core.processors.url import extract_url, url_provider
 from content_core.processors.video import extract_best_audio_from_video
 from content_core.processors.youtube import extract_youtube_transcript
+from content_core.processors.docling import extract_with_docling, DOCLING_SUPPORTED  # type: ignore
 
 import aiohttp
 import tempfile
 from urllib.parse import urlparse
+from content_core.config import CONFIG  # type: ignore
 
 
 async def source_identification(state: ProcessSourceState) -> Dict[str, str]:
@@ -110,6 +112,17 @@ async def download_remote_file(state: ProcessSourceState) -> Dict[str, Any]:
     return {"file_path": tmp, "identified_type": mime}
 
 
+async def file_type_router_docling(state: ProcessSourceState) -> str:
+    """
+    Route to Docling if enabled and supported; otherwise use legacy file type edge.
+    """
+    # allow per-execution override of engine via state.engine
+    engine = state.engine or CONFIG.get("extraction", {}).get("engine", "legacy")
+    if engine == "docling" and state.identified_type in DOCLING_SUPPORTED:
+        return "extract_docling"
+    return await file_type_edge(state)
+
+
 # Create workflow
 workflow = StateGraph(
     ProcessSourceState, input=ProcessSourceInput, output=ProcessSourceState
@@ -128,6 +141,7 @@ workflow.add_node("extract_audio", extract_audio)
 workflow.add_node("extract_youtube_transcript", extract_youtube_transcript)
 workflow.add_node("delete_file", delete_file)
 workflow.add_node("download_remote_file", download_remote_file)
+workflow.add_node("extract_docling", extract_with_docling)
 
 # Add edges
 workflow.add_edge(START, "source")
@@ -142,7 +156,7 @@ workflow.add_conditional_edges(
 )
 workflow.add_conditional_edges(
     "file_type",
-    file_type_edge,
+    file_type_router_docling,
 )
 workflow.add_conditional_edges(
     "url_provider",

content_core-0.5.0/src/content_core/notebooks/docling.ipynb

@@ -0,0 +1,27 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from docling.document_converter import DocumentConverter\n",
+    "\n",
+    "\n",
+    "source = \"/Users/luisnovo/dev/projetos/content-core/tests/input_content/file.docx\"\n",
+    "source_url = \"https://arxiv.org/pdf/2408.09869\"  # PDF path or URL\n",
+    "converter = DocumentConverter()\n",
+    "result = converter.convert(source)\n",
+    "print(result.document.export_to_markdown())"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}