- Add --docling CLI flag for easier setup
- Add numpy version constraints
- Exclude docling on macOS (fork-safety)
(cherry picked from commit c246eff725)
- Add --docling CLI flag for easier setup
- Add numpy version constraints
- Exclude docling on macOS (fork-safety)
(cherry picked from commit a24d8181c2)
Add 5 markdown documents that users can index to reproduce evaluation results.
Changes:
- Add sample_documents/ folder with 5 markdown files covering LightRAG features
- Update sample_dataset.json with 3 improved, specific test questions
- Shorten and correct evaluation README (removed outdated info about mock responses)
- Add sample_documents reference with expected ~95% RAGAS score
Test Results with sample documents:
- Average RAGAS Score: 95.28%
- Faithfulness: 100%, Answer Relevance: 96.67%
- Context Recall: 88.89%, Context Precision: 95.56%
(cherry picked from commit a172cf893d)
**Lint Fixes (ruff)**:
- Sort imports alphabetically (I001)
- Add blank line after import traceback (E302)
- Add trailing comma to dict literals (COM812)
- Reformat writer.writerow for readability (E501)
**Rename test_dataset.json → sample_dataset.json**:
- Avoids .gitignore pattern conflict (test_* is ignored)
- More descriptive name - it's a sample/template, not actual test data
- Updated all references in eval_rag_quality.py and README.md
Resolves lint-and-format CI check failure.
Addresses reviewer feedback about test dataset naming.
(cherry picked from commit 5cdb4b0ef2)
This contribution adds optional Langfuse support for LLM observability and tracing.
Langfuse provides a drop-in replacement for the OpenAI client that automatically
tracks all LLM interactions without requiring code changes.
Features:
- Optional Langfuse integration with graceful fallback
- Automatic LLM request/response tracing
- Token usage tracking
- Latency metrics
- Error tracking
- Zero code changes required for existing functionality
Implementation:
- Modified lightrag/llm/openai.py to conditionally use Langfuse's AsyncOpenAI
- Falls back to standard OpenAI client if Langfuse is not installed
- Logs observability status on import
Configuration:
To enable Langfuse tracing, install the observability extras and set environment variables:
```bash
pip install lightrag-hku[observability]
export LANGFUSE_PUBLIC_KEY="your_public_key"
export LANGFUSE_SECRET_KEY="your_secret_key"
export LANGFUSE_HOST="https://cloud.langfuse.com" # or your self-hosted instance
```
If Langfuse is not installed or environment variables are not set, LightRAG
will use the standard OpenAI client without any functionality changes.
Changes:
- Modified lightrag/llm/openai.py (added optional Langfuse import)
- Updated pyproject.toml with optional 'observability' dependencies
Dependencies (optional):
- langfuse>=3.8.1
(cherry picked from commit 626b42bc40)
Previously, configure_vchordrq would fail silently when probes was empty
(the default), preventing epsilon from being configured. Now each parameter
is handled independently with conditional execution, and configuration
errors fail-fast instead of being swallowed.
This fixes the documented epsilon setting being impossible to use in the
default configuration.
(cherry picked from commit 3096f844fb)
* Unify empty workspace behavior by changing workspace from "_" to ""
* Fixed incorrect empty workspace detection in get_all_update_flags_status()
(cherry picked from commit d54d0d55d9)
- Add _default_workspace to global vars
- Set _default_workspace to None on cleanup
- Ensure complete resource cleanup
- Fix missing workspace finalization
(cherry picked from commit 6d6716e9f8)
• Add workspace param to get_namespace_data
• Update docstring with proper usage example
• Simplify demo to show correct workflow
• Remove confusing before/after comparison
• Clarify tool should run after init
(cherry picked from commit 393f880311)
- Fast path for clean data (no sanitization)
- Slow path sanitizes during encoding
- Reload shared memory after sanitization
- Custom encoder avoids deep copies
- Comprehensive test coverage
(cherry picked from commit 777c987371)
- Snapshot JSON data before yielding batches
- Release lock during batch processing
- Exclude source type from target selection
- Add detailed docstring for lock behavior
- Filter available storage types properly
(cherry picked from commit 5be04263b2)
• Add MongoDB env requirements
• Support config.ini fallback
• Warn on missing env vars
• Check available storage count
• Show config source info
(cherry picked from commit 1a91bcdb5f)
• Move rag_semaphore to wrap full function
• Increase RAG concurrency to 2x eval limit
• Prevent memory buildup from slow evals
• Keep eval_semaphore for RAGAS control
(cherry picked from commit e5abe9dd3d)
• Split RAG gen and eval stages
• Add rag_semaphore for stage 1
• Add eval_semaphore for stage 2
• Improve concurrency control
• Update connection pool limits
(cherry picked from commit 83715a3ac1)
- Batch index existence checks into single query (16+ queries -> 1 query)
- Batch timestamp column checks into single query (8 queries -> 1 query)
- Batch field length checks into single query (5 queries -> 1 query)
Performance improvement: ~70-80% faster initialization (35s -> 5-10s)
Key optimizations:
1. check_tables(): Use ANY($1) to check all indexes at once
2. _migrate_timestamp_columns(): Batch all column type checks
3. _migrate_field_lengths(): Batch all field definition checks
All changes are backward compatible with no schema or API changes.
Reduces database round-trips by batching information_schema queries.
(cherry picked from commit 2f22336ace)
