Merge pull request #216 from enoch3712/215-doc-refactor---document-lo…

…ader-data

adding data to sidebar docs

docs/core-concepts/document-loaders/data.md

@@ -63,30 +63,4 @@ The `DataLoaderConfig` class supports the following options:
 |--------|------|---------|-------------|
 | `content` | Any | None | Initial content to process |
 | `cache_ttl` | int | 300 | Cache time-to-live in seconds |
-| `supports_vision` | bool | True | Whether vision mode is supported |
-
-## Features
-
-- Handles pre-processed data in standard format
-- Supports raw text input
-- File and stream processing
-- Vision mode support
-- Automatic format validation
-- Caching support
-- Flexible input handling
-
-## Input Types
-
-The loader can handle:
-- Pre-formatted list of dictionaries
-- Raw text strings
-- File paths
-- IO streams
-
-## Notes
-
-- Vision mode is configurable
-- Validates input format automatically
-- Caches results based on content hash
-- Supports both file and stream-based loading
-- Preserves image data when in vision mode
+| `supports_vision` | bool | True | Whether vision mode is supported |

docs/core-concepts/document-loaders/index.md

@@ -153,6 +153,8 @@ ExtractThinker provides several specialized Document Loaders:
 ### Special Purpose
 - [Web Loader](web-loader.md): Web page extraction with custom element handling
 - [LLM Image](llm-image.md): Vision-enabled LLM processing
+- [Data](data.md): Pre-processed data handling with standardized format support
+
 
 ### Coming Soon
 - `Adobe PDF Services` <span class="coming-soon">Coming Soon</span>: Adobe's PDF extraction and analysis

mkdocs.yml

@@ -43,6 +43,7 @@ nav:
           - Markitdown: core-concepts/document-loaders/markitdown.md
           - Text: core-concepts/document-loaders/txt.md
           - Docling: core-concepts/document-loaders/docling.md
+          - Data: core-concepts/document-loaders/data.md
           - Adobe PDF Services: '#'
           - ABBYY FineReader: '#'
           - PaddleOCR: '#'