content-core 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

content_core/config.py

@@ -6,6 +6,10 @@ from dotenv import load_dotenv
 # Load environment variables from .env file
 load_dotenv()
 
+# Allowed engine values for validation
+ALLOWED_DOCUMENT_ENGINES = {"auto", "simple", "docling"}
+ALLOWED_URL_ENGINES = {"auto", "simple", "firecrawl", "jina"}
+
 
 def load_config():
     config_path = os.environ.get("CCORE_CONFIG_PATH") or os.environ.get("CCORE_MODEL_CONFIG_PATH")
@@ -33,6 +37,39 @@ def load_config():
 
 CONFIG = load_config()
 
+# Environment variable engine selectors for MCP/Raycast users
+def get_document_engine():
+    """Get document engine with environment variable override and validation."""
+    env_engine = os.environ.get("CCORE_DOCUMENT_ENGINE")
+    if env_engine:
+        if env_engine not in ALLOWED_DOCUMENT_ENGINES:
+            # Import logger here to avoid circular imports
+            from content_core.logging import logger
+            logger.warning(
+                f"Invalid CCORE_DOCUMENT_ENGINE: '{env_engine}'. "
+                f"Allowed values: {', '.join(sorted(ALLOWED_DOCUMENT_ENGINES))}. "
+                f"Using default from config."
+            )
+            return CONFIG.get("extraction", {}).get("document_engine", "auto")
+        return env_engine
+    return CONFIG.get("extraction", {}).get("document_engine", "auto")
+
+def get_url_engine():
+    """Get URL engine with environment variable override and validation."""
+    env_engine = os.environ.get("CCORE_URL_ENGINE")
+    if env_engine:
+        if env_engine not in ALLOWED_URL_ENGINES:
+            # Import logger here to avoid circular imports
+            from content_core.logging import logger
+            logger.warning(
+                f"Invalid CCORE_URL_ENGINE: '{env_engine}'. "
+                f"Allowed values: {', '.join(sorted(ALLOWED_URL_ENGINES))}. "
+                f"Using default from config."
+            )
+            return CONFIG.get("extraction", {}).get("url_engine", "auto")
+        return env_engine
+    return CONFIG.get("extraction", {}).get("url_engine", "auto")
+
 # Programmatic config overrides: use in notebooks or scripts
 def set_document_engine(engine: str):
     """Override the document extraction engine ('auto', 'simple', or 'docling')."""

content_core/content/extraction/graph.py

@@ -12,13 +12,19 @@ from content_core.common import (
     ProcessSourceState,
     UnsupportedTypeException,
 )
-from content_core.config import CONFIG  # type: ignore
+from content_core.config import get_document_engine
 from content_core.logging import logger
 from content_core.processors.audio import extract_audio_data  # type: ignore
-from content_core.processors.docling import (
-    DOCLING_SUPPORTED,  # type: ignore
-    extract_with_docling,
-)
+try:
+    from content_core.processors.docling import (
+        DOCLING_SUPPORTED,  # type: ignore
+        extract_with_docling,
+        DOCLING_AVAILABLE,
+    )
+except ImportError:
+    DOCLING_AVAILABLE = False
+    DOCLING_SUPPORTED = set()
+    extract_with_docling = None
 from content_core.processors.office import (
     SUPPORTED_OFFICE_TYPES,
     extract_office_content,
@@ -126,26 +132,30 @@ async def file_type_router_docling(state: ProcessSourceState) -> str:
     Supports 'auto', 'docling', and 'simple'.
     'auto' tries docling first, then falls back to simple if docling fails.
     """
-    engine = state.document_engine or CONFIG.get("extraction", {}).get("document_engine", "auto")
+    # Use environment-aware engine selection
+    engine = state.document_engine or get_document_engine()
+    
     if engine == "auto":
         logger.debug("Using auto engine")
-        # Try docling first; if it fails or is not supported, fallback to simple
-        if state.identified_type in DOCLING_SUPPORTED:
-            try:
-                logger.debug("Trying docling extraction")
-                return "extract_docling"
-            except Exception as e:
-                logger.warning(
-                    f"Docling extraction failed in 'auto' mode, falling back to simple: {e}"
-                )
+        # Check if docling is available AND supports the file type
+        if DOCLING_AVAILABLE and state.identified_type in DOCLING_SUPPORTED:
+            logger.debug("Using docling extraction (auto mode)")
+            return "extract_docling"
         # Fallback to simple
-        logger.debug("Falling back to simple extraction")
+        logger.debug("Falling back to simple extraction (docling unavailable or unsupported)")
         return await file_type_edge(state)
 
-    if engine == "docling" and state.identified_type in DOCLING_SUPPORTED:
-        logger.debug("Using docling engine")
-        return "extract_docling"
-    # For 'simple', use the default file type edge
+    if engine == "docling":
+        if not DOCLING_AVAILABLE:
+            raise ImportError("Docling engine requested but docling package not installed. Install with: pip install content-core[docling]")
+        if state.identified_type in DOCLING_SUPPORTED:
+            logger.debug("Using docling engine")
+            return "extract_docling"
+        # If docling doesn't support this file type, fall back to simple
+        logger.debug("Docling doesn't support this file type, using simple engine")
+        return await file_type_edge(state)
+    
+    # For 'simple' or any other engine
     logger.debug("Using simple engine")
     return await file_type_edge(state)
 
@@ -168,7 +178,9 @@ workflow.add_node("extract_audio_data", extract_audio_data)
 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)
+# Only add docling node if available
+if DOCLING_AVAILABLE:
+    workflow.add_node("extract_docling", extract_with_docling)
 
 # Add edges
 workflow.add_edge(START, "source")

content_core/processors/docling.py

@@ -2,22 +2,29 @@
 Docling-based document extraction processor.
 """
 
+from content_core.common.state import ProcessSourceState
+from content_core.config import CONFIG
+
+DOCLING_AVAILABLE = False
 try:
     from docling.document_converter import DocumentConverter
+    DOCLING_AVAILABLE = True
 except ImportError:
 
     class DocumentConverter:
         """Stub when docling is not installed."""
 
         def __init__(self):
-            raise ImportError("Docling not installed")
+            raise ImportError(
+                "Docling not installed. Install with: pip install content-core[docling] "
+                "or use CCORE_DOCUMENT_ENGINE=simple to skip docling."
+            )
 
         def convert(self, source: str):
-            raise ImportError("Docling not installed")
-
-
-from content_core.common.state import ProcessSourceState
-from content_core.config import CONFIG
+            raise ImportError(
+                "Docling not installed. Install with: pip install content-core[docling] "
+                "or use CCORE_DOCUMENT_ENGINE=simple to skip docling."
+            )
 
 # Supported MIME types for Docling extraction
 DOCLING_SUPPORTED = {

content_core/processors/url.py

@@ -5,7 +5,7 @@ from bs4 import BeautifulSoup
 from readability import Document
 
 from content_core.common import ProcessSourceState
-from content_core.config import CONFIG
+from content_core.config import get_url_engine
 from content_core.logging import logger
 from content_core.processors.docling import DOCLING_SUPPORTED
 from content_core.processors.office import SUPPORTED_OFFICE_TYPES
@@ -165,7 +165,8 @@ async def extract_url(state: ProcessSourceState):
     """
     assert state.url, "No URL provided"
     url = state.url
-    engine = state.url_engine or CONFIG.get("extraction", {}).get("url_engine", "auto")
+    # Use environment-aware engine selection
+    engine = state.url_engine or get_url_engine()
     try:
         if engine == "auto":
             if os.environ.get("FIRECRAWL_API_KEY"):

{content_core-1.2.0.dist-info → content_core-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 1.2.0
+Version: 1.2.1
 Summary: Extract what matters from any media source. Available as Python Library, macOS Service, CLI and MCP Server
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
@@ -112,11 +112,17 @@ summary = await cc.summarize_content(result, context="explain to a child")
 Install Content Core using `pip`:
 
 ```bash
-# Install the package
+# Basic installation (PyMuPDF + BeautifulSoup/Jina extraction)
 pip install content-core
 
-# Install with MCP server support
+# With enhanced document processing (adds Docling)
+pip install content-core[docling]
+
+# With MCP server support
 pip install content-core[mcp]
+
+# Full installation
+pip install content-core[docling,mcp]
 ```
 
 Alternatively, if you’re developing locally:
@@ -526,8 +532,21 @@ Example `.env`:
 ```plaintext
 OPENAI_API_KEY=your-key-here
 GOOGLE_API_KEY=your-key-here
+
+# Engine Selection (optional)
+CCORE_DOCUMENT_ENGINE=auto  # auto, simple, docling
+CCORE_URL_ENGINE=auto       # auto, simple, firecrawl, jina
 ```
 
+### Engine Selection via Environment Variables
+
+For deployment scenarios like MCP servers or Raycast extensions, you can override the extraction engines using environment variables:
+
+- **`CCORE_DOCUMENT_ENGINE`**: Force document engine (`auto`, `simple`, `docling`)
+- **`CCORE_URL_ENGINE`**: Force URL engine (`auto`, `simple`, `firecrawl`, `jina`)
+
+These variables take precedence over config file settings and provide explicit control for different deployment scenarios.
+
 ### Custom Prompt Templates
 
 Content Core allows you to define custom prompt templates for content processing. By default, the library uses built-in prompts located in the `prompts` directory. However, you can create your own prompt templates and store them in a dedicated directory. To specify the location of your custom prompts, set the `PROMPT_PATH` environment variable in your `.env` file or system environment.

{content_core-1.2.0.dist-info → content_core-1.2.1.dist-info}/RECORD

@@ -1,6 +1,6 @@
 content_core/__init__.py,sha256=t4xFo9f3uB2FD1tdR-7ruhMW9_ciJawQReK6iFXWfR0,6531
 content_core/cc_config.yaml,sha256=hjTt5z1Z9b5LShVIqNT3OiAnTAdmr0LB5y8RTyH-fNA,1119
-content_core/config.py,sha256=OBwI58W4Twr00UiYD2mdw_rZDcuXxjBanE0IoA8ox-M,2601
+content_core/config.py,sha256=3XAsMF3EhDJ6aCpzk1UZG_m3-SFdYe3cHiDPH7eVGwQ,4312
 content_core/logging.py,sha256=oeRdWKknEolptopxF1IvnEGEc0ZUw45QXYUEZ71GcdY,438
 content_core/models.py,sha256=Kt6tWdAX87eQ2tL6eTwcHU7_NIRnN4exP4RzV2WrMig,881
 content_core/models_config.yaml,sha256=Yr-GS94ffxnkaWojUfpErUMM7m_MShsYjR6QuDjMzwo,444
@@ -15,7 +15,7 @@ content_core/content/__init__.py,sha256=7IxfLTUHKyHjoT4MfWM2PX2J3QBeYcuERzE9vFeF
 content_core/content/cleanup/__init__.py,sha256=wymD24WLDDdsZrv-5WhparSiHBK9SJCcqBHmokuZqk4,121
 content_core/content/cleanup/core.py,sha256=AXUGUWxGob8si5uKRnDrreOcHV_gbGJr4YnRsNm2GX0,531
 content_core/content/extraction/__init__.py,sha256=TaYw6CAcG62GZfsJxeZ6VJDLP85BU2a7_G271v6WWPk,446
-content_core/content/extraction/graph.py,sha256=Nn2iaQc6YJ4Qt8WKTolwUQUNNqUlwpV8YnijESGvnD0,7605
+content_core/content/extraction/graph.py,sha256=sjk6NpzOMOzMbUOM0bqrDSlB3cLQzboviLDNbj48pjY,8074
 content_core/content/identification/__init__.py,sha256=x4n8JIjDwmPvAopEEEcmZjlozg-zGbMq_s9VYdBjzYU,169
 content_core/content/summary/__init__.py,sha256=ReKCZWKfDtqlInKeh87Y1DEfiNzVWabGybEz3hS2FrI,114
 content_core/content/summary/core.py,sha256=kEabpETljzUb-yf0NcVWTOuCtayESo74gGBVDX7YTFs,550
@@ -24,19 +24,19 @@ content_core/mcp/server.py,sha256=ql0uXHkIbZlHQUhUQ4CaRnj19xT6t8ErydWntFgmtUg,70
 content_core/notebooks/run.ipynb,sha256=WPBNcQUNXR5MldNMghVcU4vE4ibrVmlANa80baQn8TA,371078
 content_core/notebooks/urls.ipynb,sha256=gSmiSzmbol_Li36w8tpUsy5QgRbrnBx94Ry2zHwMvwY,7107
 content_core/processors/audio.py,sha256=Mie20g_2Akhw6BHBVo3sHMpDRYUkqBI72lEDakscx3s,5729
-content_core/processors/docling.py,sha256=dkXehsQdfyWXfrK1K_6Pye50ABM7DxMk6TMguabM9Pc,2151
+content_core/processors/docling.py,sha256=lf_NHh255gn4d2EymJYqyH2QiAgQDiJCY3t6Ne7R9rU,2507
 content_core/processors/office.py,sha256=DXkfmjqUhmhP6rJaO5Z5Y9sv-iK0zaPZ3waynFIPtsk,12153
 content_core/processors/pdf.py,sha256=TTDhfV2INtXumFDjLJFNMRfpbJ_tqwIcSBDzuThKxJI,10617
 content_core/processors/text.py,sha256=kKHA60-NYjLmCTYUnk8TdJxQQ0Shkg-K61Ezqaelz7k,1158
-content_core/processors/url.py,sha256=6WT8Sw2VHiKyhgWXi_jZjKjwnT_QPSPcH4P99RKbjgU,7521
+content_core/processors/url.py,sha256=YoWw2CjZbqSKBi1CpY0Qowu4hfqGVGJjLZEXUjz7wxs,7536
 content_core/processors/video.py,sha256=3WnZwTswvTLm8PtQhKwoqJ2BH6YZi62dMUjALwJiebo,5196
 content_core/processors/youtube.py,sha256=MOeZboVfM9_C87L5mnUVvsbQeKoznwJoYn1wP1_hA_U,7869
 content_core/tools/__init__.py,sha256=DuJmd7fE-NpDvLP8IW1XY5MUkAQcdks52rn2jk4N8jQ,231
 content_core/tools/cleanup.py,sha256=5IdKedsFyRQMdYzgFSKtsfyxJldbroXQXHesHICNENI,523
 content_core/tools/extract.py,sha256=-r2_jsuMMXyXxGVqWhh1ilNPo_UMYAbw3Pkp1FzPy5g,577
 content_core/tools/summarize.py,sha256=DPfeglLWB08q8SvHrsKpOKZ35XjduUDs2J02ISwjdj0,596
-content_core-1.2.0.dist-info/METADATA,sha256=wAEQSfn6tTd4hQwAZY8sKeB5e7QpHm6qeTz2akFZwWw,18881
-content_core-1.2.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-content_core-1.2.0.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
-content_core-1.2.0.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
-content_core-1.2.0.dist-info/RECORD,,
+content_core-1.2.1.dist-info/METADATA,sha256=1LpANnMvECxIekt6kKQr0hnZ1ULGaD2xEmhRh_uzTdk,19676
+content_core-1.2.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+content_core-1.2.1.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
+content_core-1.2.1.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
+content_core-1.2.1.dist-info/RECORD,,