From e54c0e39b58ebdc15cbf6ad4db88c2f4394ca315 Mon Sep 17 00:00:00 2001
From: dylan <xuhao296@qq.com>
Date: Fri, 11 Apr 2025 17:01:49 +0800
Subject: [PATCH] fix bug [ERROR][Exception]: 8 vs. 9 (#6955)

### What problem does this PR solve?

Sometimes, the **s** in **chunks (s, a)** is an empty string. This
causes the condition **if s and len(a) > 0** in the line **chunks = [(s,
a) for s, a in chunks if s and len(a) > 0]** to fail, which changes the
length of the new chunks. As a result, the final assertion **assert
len(chunks) - end == n_clusters, "{} vs. {}".format(len(chunks) - end,
n_clusters)** fails and raises a confusing error like 7 vs. 8

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
---
 rag/raptor.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/rag/raptor.py b/rag/raptor.py
index 99155e19..d09ea571 100644
--- a/rag/raptor.py
+++ b/rag/raptor.py
@@ -77,11 +77,11 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
         return optimal_clusters
 
     async def __call__(self, chunks, random_state, callback=None):
-        layers = [(0, len(chunks))]
-        start, end = 0, len(chunks)
         if len(chunks) <= 1:
             return []
         chunks = [(s, a) for s, a in chunks if s and len(a) > 0]
+        layers = [(0, len(chunks))]
+        start, end = 0, len(chunks)
 
         async def summarize(ck_idx: list[int]):
             nonlocal chunks