Previously, the system incorrectly used OPENAI_API_KEY for all LLM providers
due to a hardcoded api_key_env fallback in config.yml. This caused authentication
errors when using non-OpenAI providers like Gemini.
Changes:
- Remove api_key_env from config.yml to let litellm handle provider-specific env vars
- Simplify get_llm_api_key() to return None, allowing litellm to auto-detect keys
- Update validate_llm_provider() to trust litellm's built-in key detection
- Update documentation to reflect the new automatic key handling
The fix leverages litellm's existing capability to automatically find the correct
environment variable for each provider (OPENAI_API_KEY, GEMINI_API_TOKEN, etc.)
without manual configuration.
ref #1291
- Add comprehensive v0.7.4 release blog post with LLMTableExtraction feature highlight
- Update blog index to feature v0.7.4 as latest release
- Update README.md to showcase v0.7.4 features alongside v0.7.3
- Accurately describe dispatcher fix as bug fix rather than major enhancement
- Include practical code examples for new LLMTableExtraction capabilities
BREAKING CHANGE: Table extraction now uses Strategy Design Pattern
This epic commit introduces a game-changing approach to table extraction in Crawl4AI:
✨ NEW FEATURES:
- LLMTableExtraction: AI-powered extraction for complex HTML tables with rowspan/colspan
- Smart Chunking: Automatically splits massive tables into optimal chunks at row boundaries
- Parallel Processing: Processes multiple chunks simultaneously for blazing-fast extraction
- Intelligent Merging: Seamlessly combines chunk results into complete tables
- Header Preservation: Each chunk maintains context with original headers
- Auto-retry Logic: Built-in resilience with configurable retry attempts
🏗️ ARCHITECTURE:
- Strategy Design Pattern for pluggable table extraction strategies
- ThreadPoolExecutor for concurrent chunk processing
- Token-based chunking with configurable thresholds
- Handles tables without headers gracefully
⚡ PERFORMANCE:
- Process 1000+ row tables without timeout
- Parallel processing with up to 5 concurrent chunks
- Smart token estimation prevents LLM context overflow
- Optimized for providers like Groq for massive tables
🔧 CONFIGURATION:
- enable_chunking: Auto-handle large tables (default: True)
- chunk_token_threshold: When to split (default: 3000 tokens)
- min_rows_per_chunk: Meaningful chunk sizes (default: 10)
- max_parallel_chunks: Concurrent processing (default: 5)
📚 BACKWARD COMPATIBILITY:
- Existing code continues to work unchanged
- DefaultTableExtraction remains the default strategy
- Progressive enhancement approach
This is the future of web table extraction - handling everything from simple tables to massive, complex data grids with merged cells and nested structures. The chunking is completely transparent to users while providing unprecedented scalability.
- fix handling of special keys in Windows msvcrt implementation
- Guard against UnicodeDecodeError from multi-byte key sequences
- Filter out non-printable characters and control sequences
- Add error handling to prevent coroutine crashes
- Add unit test to verify keyboard input handling
Key changes:
- Safe UTF-8 decoding with try/except for special keys
- Skip non-printable and multi-byte character sequences
- Add broad exception handling in keyboard listener
Test runs on Windows only due to msvcrt dependency.
This commit introduces platform-specific handling for the 'q' key press to quit the browser profiler, ensuring compatibility with both Windows and Unix-like systems. It also adds a check to see if the browser process has already exited, terminating the input listener if so.
- Implemented `msvcrt` for Windows to capture keyboard input without requiring a newline.
- Retained `termios`, `tty`, and `select` for Unix-like systems.
- Added a check for browser process termination to gracefully exit the input listener.
- Updated logger messages to use colored output for better user experience.
BREAKING CHANGE: Table extraction now uses Strategy Design Pattern
This epic commit introduces a game-changing approach to table extraction in Crawl4AI:
✨ NEW FEATURES:
- LLMTableExtraction: AI-powered extraction for complex HTML tables with rowspan/colspan
- Smart Chunking: Automatically splits massive tables into optimal chunks at row boundaries
- Parallel Processing: Processes multiple chunks simultaneously for blazing-fast extraction
- Intelligent Merging: Seamlessly combines chunk results into complete tables
- Header Preservation: Each chunk maintains context with original headers
- Auto-retry Logic: Built-in resilience with configurable retry attempts
🏗️ ARCHITECTURE:
- Strategy Design Pattern for pluggable table extraction strategies
- ThreadPoolExecutor for concurrent chunk processing
- Token-based chunking with configurable thresholds
- Handles tables without headers gracefully
⚡ PERFORMANCE:
- Process 1000+ row tables without timeout
- Parallel processing with up to 5 concurrent chunks
- Smart token estimation prevents LLM context overflow
- Optimized for providers like Groq for massive tables
🔧 CONFIGURATION:
- enable_chunking: Auto-handle large tables (default: True)
- chunk_token_threshold: When to split (default: 3000 tokens)
- min_rows_per_chunk: Meaningful chunk sizes (default: 10)
- max_parallel_chunks: Concurrent processing (default: 5)
📚 BACKWARD COMPATIBILITY:
- Existing code continues to work unchanged
- DefaultTableExtraction remains the default strategy
- Progressive enhancement approach
This is the future of web table extraction - handling everything from simple tables to massive, complex data grids with merged cells and nested structures. The chunking is completely transparent to users while providing unprecedented scalability.
- Wrap all AsyncUrlSeeder usage with async context managers
- Update URL seeding adventure example to use "sitemap+cc" source, focus on course posts, and add stream=True parameter to fix runtime error
The MemoryAdaptiveDispatcher was processing tasks sequentially despite
max_session_permit > 1 due to fetching only one task per event loop iteration.
This particularly affected raw:// URLs which complete in microseconds.
Changes:
- Replace single task fetch with greedy slot filling using get_nowait()
- Fill all available slots (up to max_session_permit) immediately
- Break on empty queue instead of waiting with timeout
This ensures proper parallelization for all task types, especially
ultra-fast operations like raw HTML processing.
- Add raw HTML URL validation alongside http/https checks
- Fix URL preprocessing logic to handle raw: and raw:// prefixes
- Update error message and add comprehensive test cases
- Remove deprecated API token authentication from all Docker examples
- Fix async job endpoints: /crawl -> /crawl/job for submission, /task/{id} -> /crawl/job/{id} for polling
- Fix sync endpoint: /crawl_sync -> /crawl (synchronous)
- Remove non-existent /crawl_direct endpoint
- Update request format to use new structure with browser_config and crawler_config
- Fix response handling for both async and sync calls
- Update extraction strategy format to use proper nested structure
- Add Ollama connectivity check before running tests
- Update test schemas and selectors for current website structures
This makes the Docker examples work out-of-the-box with the current API structure.
- Introduced a new section in SPONSORS.md to recognize the first 50 sponsors as Founding Sponsors.
- Updated README-first.md to include comprehensive project details, features, installation instructions, and advanced usage examples.
- Highlighted the recent version 0.7.0 release with new features and improvements.
- Added a sponsorship program with tiered benefits and a mission statement to promote data democratization.
- Add FUNDING.yml to enable sponsor button
- Add sponsor section to README with tier overview
- Create SPONSORS.md for sponsor recognition
- Set up 4 tiers: Believer, Builder, Growing Team, Data Infrastructure Partner
- Extract base href from <head><base> tag using XPath in _process_element method
- Use base URL as the primary URL for link normalization when present
- Add error handling with logging for malformed or problematic base tags
- Maintain backward compatibility when no base tag is present
- Add test to verify the functionality of the base tag extraction.
