apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-04 22:02:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

refactor(embedding-cache): rename index cache to embedding cache

Browse source 
The cached payload is the indexing pipeline's embeddings (markdown is
chunked then embedded), so "embedding cache" names the expensive output
directly and removes the "index" ambiguity (DB index vs vector index vs
indexing phase). Renames the service, settings, eligibility, eviction
task, metrics, config flags (INDEX_CACHE_* -> EMBEDDING_CACHE_*), object
prefix, and the table (index_cache_embedding_sets -> embedding_cache_sets)
with its constraint and indexes. Migration 161 renamed accordingly.
This commit is contained in:
CREDO23 2026-06-12 17:00:01 +02:00
parent 8cf578d965
commit 91d947ff79
18 changed files with 93 additions and 89 deletions
Download patch file Download diff file Expand all files Collapse all files

20
surfsense_backend/alembic/versions/161_add_index_cache_embedding_sets.py → surfsense_backend/alembic/versions/161_add_embedding_cache_sets.py
View file

@ -1,4 +1,4 @@
"""add index_cache_embedding_sets table for content-addressed embedding reuse
"""add embedding_cache_sets table for content-addressed embedding reuse
Revision ID: 161
Revises: 160
@ -17,7 +17,7 @@ depends_on: str | Sequence[str] | None = None
def upgrade() -> None:
op.execute(
"""
CREATE TABLE IF NOT EXISTS index_cache_embedding_sets (
CREATE TABLE IF NOT EXISTS embedding_cache_sets (
id SERIAL PRIMARY KEY,
markdown_sha256 VARCHAR(64) NOT NULL,
embedding_model VARCHAR(255) NOT NULL,
@ -31,23 +31,23 @@ def upgrade() -> None:
times_reused BIGINT NOT NULL DEFAULT 0,
last_used_at TIMESTAMP WITH TIME ZONE NOT NULL,
created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT NOW(),
CONSTRAINT uq_index_cache_embedding_sets_key
CONSTRAINT uq_embedding_cache_sets_key
UNIQUE (markdown_sha256, embedding_model, chunker_kind, chunker_version)
);
"""
)
op.execute(
"CREATE INDEX IF NOT EXISTS ix_index_cache_embedding_sets_last_used_at "
"ON index_cache_embedding_sets(last_used_at);"
"CREATE INDEX IF NOT EXISTS ix_embedding_cache_sets_last_used_at "
"ON embedding_cache_sets(last_used_at);"
)
op.execute(
"CREATE INDEX IF NOT EXISTS ix_index_cache_embedding_sets_created_at "
"ON index_cache_embedding_sets(created_at);"
"CREATE INDEX IF NOT EXISTS ix_embedding_cache_sets_created_at "
"ON embedding_cache_sets(created_at);"
)
def downgrade() -> None:
op.execute("DROP INDEX IF EXISTS ix_index_cache_embedding_sets_created_at;")
op.execute("DROP INDEX IF EXISTS ix_index_cache_embedding_sets_last_used_at;")
op.execute("DROP TABLE IF EXISTS index_cache_embedding_sets;")
op.execute("DROP INDEX IF EXISTS ix_embedding_cache_sets_created_at;")
op.execute("DROP INDEX IF EXISTS ix_embedding_cache_sets_last_used_at;")
op.execute("DROP TABLE IF EXISTS embedding_cache_sets;")