Mirrors/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-16 11:57:51 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Tika 3.1.0.0 sends a lot of blank lines which degrades the RAG results, strip them.

Browse Source
This commit is contained in:
Iván Baldo
2025-03-25 14:53:14 -03:00
parent 4906af9319
commit 115e46a6a2
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/open_webui/retrieval/loaders/main.py
View File

@@ -105,7 +105,7 @@ class TikaLoader:
if r.ok: if r.ok:
raw_metadata = r.json() raw_metadata = r.json()
text = raw_metadata.get("X-TIKA:content", "<No text content found>") text = raw_metadata.get("X-TIKA:content", "<No text content found>").strip()
if "Content-Type" in raw_metadata: if "Content-Type" in raw_metadata:
headers["Content-Type"] = raw_metadata["Content-Type"] headers["Content-Type"] = raw_metadata["Content-Type"]