Browse Source
FEAT: Tencent Vector search supports backward compatibility with the previous score calculation approach. (#22820)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>tags/1.7.0
wlleiiwang
3 months ago
1 changed files with 2 additions and 1 deletions
+ 2
- 1
api/core/rag/datasource/vdb/tencent/tencent_vector.py
View File
| # Compatible with version 1.1.3 and below. | # Compatible with version 1.1.3 and below. | ||||
| meta = json.loads(meta) | meta = json.loads(meta) | ||||
| score = 1 - result.get("score", 0.0) | score = 1 - result.get("score", 0.0) | ||||
| score = result.get("score", 0.0) | |||||
| else: | |||||
| score = result.get("score", 0.0) | |||||
| if score > score_threshold: | if score > score_threshold: | ||||
| meta["score"] = score | meta["score"] = score | ||||
| doc = Document(page_content=result.get(self.field_text), metadata=meta) | doc = Document(page_content=result.get(self.field_text), metadata=meta) |
Loading…