(burr) branch main updated: Use UTF-8 for adaptive CRAG docs (#852)

[je...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

jernejfrank pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/burr.git


The following commit(s) were added to refs/heads/main by this push:
     new 71d4fd3e Use UTF-8 for adaptive CRAG docs (#852)
71d4fd3e is described below

commit 71d4fd3e0c0afbc5162ad59dd94f14de0f7a19ee
Author: Rolly Calma <11...@users.noreply.github.com>
AuthorDate: Mon Jul 27 00:30:49 2026 +0800

    Use UTF-8 for adaptive CRAG docs (#852)
---
 examples/adaptive-crag/application.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/examples/adaptive-crag/application.py b/examples/adaptive-crag/application.py
index 912402e1..1e5c2f95 100644
--- a/examples/adaptive-crag/application.py
+++ b/examples/adaptive-crag/application.py
@@ -101,8 +101,9 @@ def load_burr_docs(
         files_iter = file_names
     docs = []
     for file in files_iter:
+        doc_path = (burr_docs_dir / Path(file).name).with_suffix(".txt")
         docs += merge_short_docs(
-            docs=(burr_docs_dir / Path(file).name).with_suffix(".txt").read_text().split("\n\n"),
+            docs=doc_path.read_text(encoding="utf-8").split("\n\n"),
             file_name=Path(file).stem,
             doc_thresh=doc_thresh,
         )