From a934becfcca6746a456b7842f8e4b350dc3ae3db Mon Sep 17 00:00:00 2001
From: anouarbm <anouarbnmoussa@gmail.com>
Date: Sat, 1 Nov 2025 21:40:22 +0100
Subject: [PATCH] feat: add optional Langfuse observability integration

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 626b42bc409378ecb8a9983171cede3f7d04f579)
---
 lightrag/llm/openai.py | 12 +++++++++++-
 pyproject.toml         | 17 +----------------
 2 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/lightrag/llm/openai.py b/lightrag/llm/openai.py
index 025a094e..c87ddbe1 100644
--- a/lightrag/llm/openai.py
+++ b/lightrag/llm/openai.py
@@ -13,8 +13,18 @@ import pipmaster as pm  # Pipmaster for dynamic library install
 if not pm.is_installed("openai"):
     pm.install("openai")
 
+# Try to import Langfuse for LLM observability (optional)
+# Falls back to standard OpenAI client if not available
+try:
+    from langfuse.openai import AsyncOpenAI
+    LANGFUSE_ENABLED = True
+    logger.info("Langfuse observability enabled for OpenAI client")
+except ImportError:
+    from openai import AsyncOpenAI
+    LANGFUSE_ENABLED = False
+    logger.debug("Langfuse not available, using standard OpenAI client")
+
 from openai import (
-    AsyncOpenAI,
     APIConnectionError,
     RateLimitError,
     APITimeoutError,
diff --git a/pyproject.toml b/pyproject.toml
index 29f7c58e..8eabb37c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -24,8 +24,6 @@ dependencies = [
     "aiohttp",
     "configparser",
     "future",
-    "google-api-core>=2.0.0,<3.0.0",
-    "google-genai>=1.0.0,<2.0.0",
     "json_repair",
     "nano-vectordb",
     "networkx",
@@ -61,8 +59,6 @@ api = [
     "tenacity",
     "tiktoken",
     "xlsxwriter>=3.1.0",
-    "google-api-core>=2.0.0,<3.0.0",
-    "google-genai>=1.0.0,<2.0.0",
     # API-specific dependencies
     "aiofiles",
     "ascii_colors",
@@ -98,7 +94,7 @@ offline-storage = [
     "pymilvus>=2.6.2,<3.0.0",
     "pymongo>=4.0.0,<5.0.0",
     "asyncpg>=0.29.0,<1.0.0",
-    "qdrant-client>=1.11.0,<2.0.0",
+    "qdrant-client>=1.7.0,<2.0.0",
 ]
 
 offline-llm = [
@@ -110,8 +106,6 @@ offline-llm = [
     "aioboto3>=12.0.0,<16.0.0",
     "voyageai>=0.2.0,<1.0.0",
     "llama-index>=0.9.0,<1.0.0",
-    "google-api-core>=2.0.0,<3.0.0",
-    "google-genai>=1.0.0,<2.0.0",
 ]
 
 offline = [
@@ -119,15 +113,6 @@ offline = [
     "lightrag-hku[offline-docs,offline-storage,offline-llm]",
 ]
 
-evaluation = [
-    # RAG evaluation dependencies (RAGAS framework)
-    "ragas>=0.3.7",
-    "datasets>=4.3.0",
-    "httpx>=0.28.1",
-    "pytest>=8.4.2",
-    "pytest-asyncio>=1.2.0",
-]
-
 observability = [
     # LLM observability and tracing dependencies
     "langfuse>=3.8.1",