From 70a318c6391c338bc3a11330c0d931e6d081db5c Mon Sep 17 00:00:00 2001 From: tangwang Date: Sat, 20 Dec 2025 14:56:47 +0800 Subject: [PATCH] fix bug --- embeddings/text_encoder.py | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/embeddings/text_encoder.py b/embeddings/text_encoder.py index 8d6d3ac..c4ff1b3 100644 --- a/embeddings/text_encoder.py +++ b/embeddings/text_encoder.py @@ -113,7 +113,19 @@ class BgeEncoder: uncached_indices: List[int] = [] uncached_texts: List[str] = [] - # Prepare request data for uncached texts + # Process response + # Each element can be np.ndarray or None (表示该文本没有可用的向量) + embeddings: List[Optional[np.ndarray]] = [None] * len(sentences) + + for i, text in enumerate(sentences): + cached = self._get_cached_embedding(text, 'en') # Use 'en' as default language for title embedding + if cached is not None: + embeddings[i] = cached + else: + uncached_indices.append(i) + uncached_texts.append(text) + + # Prepare request data for uncached texts (after cache check) request_data = [] for i, text in enumerate(uncached_texts): request_item = { @@ -127,18 +139,6 @@ class BgeEncoder: request_item["name_ru"] = None request_data.append(request_item) - - # Process response - # Each element can be np.ndarray or None (表示该文本没有可用的向量) - embeddings: List[Optional[np.ndarray]] = [None] * len(sentences) - - for i, text in enumerate(sentences): - cached = self._get_cached_embedding(text, 'en') # Use 'en' as default language for title embedding - if cached is not None: - embeddings[i] = cached - else: - uncached_indices.append(i) - uncached_texts.append(text) # If there are uncached texts, call service if uncached_texts: -- libgit2 0.21.2