SUDOZOVCHIK/vk_hackathon
1
0
Fork 0
forked from zovos/vk_hackathon
Code Pull requests Activity

Revert CHUNK_SIZE to 256/128 baseline (score 0.5094)

Browse source
This commit is contained in:
q 2026-04-18 19:57:31 +03:00
parent 0fbf69e359
commit 9750868ea8
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
index/main.py
View file

@ -73,8 +73,8 @@ class SparseVector(BaseModel):
values: list[float] values: list[float]
CHUNK_SIZE = 512 CHUNK_SIZE = 256
OVERLAP_SIZE = 192 OVERLAP_SIZE = 128
SPARSE_MODEL_NAME = "Qdrant/bm25" SPARSE_MODEL_NAME = "Qdrant/bm25"
FASTEMBED_CACHE_PATH = "/models/fastembed" FASTEMBED_CACHE_PATH = "/models/fastembed"