From f4251432a641add93d9a030d9de7e7a5d6bb9c0f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rapha=C3=ABl=20MANSUY?= <raphael.mansuy@gmail.com>
Date: Thu, 4 Dec 2025 19:14:29 +0800
Subject: [PATCH] cherry-pick aa916f28

---
 lightrag/evaluation/test_dataset.json | 44 +++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 lightrag/evaluation/test_dataset.json

diff --git a/lightrag/evaluation/test_dataset.json b/lightrag/evaluation/test_dataset.json
new file mode 100644
index 00000000..ae7069e9
--- /dev/null
+++ b/lightrag/evaluation/test_dataset.json
@@ -0,0 +1,44 @@
+{
+  "test_cases": [
+    {
+      "question": "What is LightRAG and what problem does it solve?",
+      "ground_truth": "LightRAG is a Simple and Fast Retrieval-Augmented Generation framework developed by HKUDS. It solves the problem of efficiently combining large language models with external knowledge retrieval to provide accurate, contextual responses while reducing hallucinations.",
+      "context": "general_rag_knowledge"
+    },
+    {
+      "question": "What are the main components of a RAG system?",
+      "ground_truth": "A RAG system consists of three main components: 1) A retrieval system (vector database or search engine) to find relevant documents, 2) An embedding model to convert text into vector representations, and 3) A large language model (LLM) to generate responses based on retrieved context.",
+      "context": "rag_architecture"
+    },
+    {
+      "question": "How does LightRAG improve upon traditional RAG approaches?",
+      "ground_truth": "LightRAG improves upon traditional RAG by offering a simpler API, faster retrieval performance, better integration with various vector databases, and optimized prompting strategies. It focuses on ease of use while maintaining high quality results.",
+      "context": "lightrag_features"
+    },
+    {
+      "question": "What vector databases does LightRAG support?",
+      "ground_truth": "LightRAG supports multiple vector databases including ChromaDB, Neo4j, Milvus, Qdrant, MongoDB Atlas Vector Search, and Redis. It also includes a built-in nano-vectordb for simple deployments.",
+      "context": "supported_storage"
+    },
+    {
+      "question": "What are the key metrics for evaluating RAG system quality?",
+      "ground_truth": "Key RAG evaluation metrics include: 1) Faithfulness - whether answers are factually grounded in retrieved context, 2) Answer Relevance - how well answers address the question, 3) Context Recall - completeness of retrieval, and 4) Context Precision - quality and relevance of retrieved documents.",
+      "context": "rag_evaluation"
+    },
+    {
+      "question": "How can you deploy LightRAG in production?",
+      "ground_truth": "LightRAG can be deployed in production using Docker containers, as a REST API server with FastAPI, or integrated directly into Python applications. It supports environment-based configuration, multiple LLM providers, and can scale horizontally.",
+      "context": "deployment_options"
+    },
+    {
+      "question": "What LLM providers does LightRAG support?",
+      "ground_truth": "LightRAG supports multiple LLM providers including OpenAI (GPT-3.5, GPT-4), Anthropic Claude, Ollama for local models, Azure OpenAI, AWS Bedrock, and any OpenAI-compatible API endpoint.",
+      "context": "llm_integration"
+    },
+    {
+      "question": "What is the purpose of graph-based retrieval in RAG systems?",
+      "ground_truth": "Graph-based retrieval in RAG systems enables relationship-aware context retrieval. It stores entities and their relationships as a knowledge graph, allowing the system to understand connections between concepts and retrieve more contextually relevant information beyond simple semantic similarity.",
+      "context": "knowledge_graph_rag"
+    }
+  ]
+}