- Add KaTeX extensions (mhchem for chemistry, copy-tex for copying)
- Add CASCADE to AGE extension for PostgreSQL
- Remove future dependency, replace passlib with bcrypt
- Fix Jina embedding configuration and provider defaults
- Update gunicorn help text and bump API version to 0258
- Documentation and README updates
Add citation tracking and display system across backend and frontend components.
Backend changes include citation.py for document attribution, enhanced query routes
with citation metadata, improved prompt templates, and PostgreSQL schema updates.
Frontend includes CitationMarker component, HoverCard UI, QuerySettings refinements,
and ChatMessage enhancements for displaying document sources. Update dependencies
and docker-compose test configuration for improved development workflow.
Added support for structured output (JSON mode) from the OpenAI API in `openai.py` and `azure_openai.py`.
When `response_format` is used to request structured data, the new logic checks for the `message.parsed` attribute. If it exists, it's serialized into a JSON string as the final content. If not, the code falls back to the existing `message.content` handling, ensuring backward compatibility.
The stream and timeout parameters were moved from **kwargs to explicit
parameters in a previous commit, but were not being passed to the OpenAI
API, causing streaming responses to fail and fall back to non-streaming
mode.Fixes the issue where stream=True was being silently ignored, resulting
in unexpected non-streaming behavior.
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
- Add enable_cot parameter to all LLM APIs
- Implement CoT for OpenAI with <think> tags
- Log warnings for unsupported providers
- Enable CoT in query operations
- Handle streaming and non-streaming CoT
