jan.mrna/semantic_doc_search
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Removed fixed TODO comment

Browse Source
This commit is contained in:
Jan Mrna
2025-11-05 14:46:16 +01:00
parent 491d79c617
commit 1c81f18d85
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
db.py
View File

@@ -35,8 +35,6 @@ class Database:
which can then be used to obtain record. which can then be used to obtain record.
TODO For faster nearest neighbour lookup we should use something else, TODO For faster nearest neighbour lookup we should use something else,
e.g. kd-trees e.g. kd-trees
TODO The resulting db is huge (50 MB for 4 pdfs), contains a lot of duplicit uncompressed text.
We should at least de-duplicate the document path.
""" """
vectors: list[Vector] vectors: list[Vector]
records: dict[VectorBytes, Record] records: dict[VectorBytes, Record]