Spaces:
Running
Running
Initialize README
Browse files
README.md
CHANGED
@@ -1,14 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# RAG Evaluation Leaderboard
|
2 |
|
3 |
-
This leaderboard tracks different RAG (Retrieval-Augmented Generation) implementations and their performance metrics.
|
4 |
|
5 |
-
## Metrics Tracked
|
6 |
|
7 |
-
### Retrieval Metrics
|
8 |
-
- Hit Rate: Proportion of relevant documents retrieved
|
9 |
-
- MRR (Mean Reciprocal Rank): Position of first relevant document
|
10 |
|
11 |
-
### Generation Metrics
|
12 |
-
- ROUGE-1: Unigram overlap
|
13 |
-
- ROUGE-2: Bigram overlap
|
14 |
-
- ROUGE-L: Longest common subsequence
|
|
|
|
1 |
+
---
|
2 |
+
title: Test RAG leaderboard
|
3 |
+
emoji: 📚
|
4 |
+
colorFrom: gray
|
5 |
+
colorTo: purple
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 5.4.0
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
---
|
11 |
+
|
12 |
# RAG Evaluation Leaderboard
|
13 |
|
14 |
+
This leaderboard tracks different RAG (Retrieval-Augmented Generation) implementations and their performance metrics.
|
15 |
|
16 |
+
## Metrics Tracked
|
17 |
|
18 |
+
### Retrieval Metrics
|
19 |
+
- Hit Rate: Proportion of relevant documents retrieved
|
20 |
+
- MRR (Mean Reciprocal Rank): Position of first relevant document
|
21 |
|
22 |
+
### Generation Metrics
|
23 |
+
- ROUGE-1: Unigram overlap
|
24 |
+
- ROUGE-2: Bigram overlap
|
25 |
+
- ROUGE-L: Longest common subsequence
|
26 |
+
|