mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2025-12-20 20:29:06 +00:00
009590c080
* feat: better highlight * feat(search): add long_summary to search vector for improved search results - Update search vector to include long_summary with weight B (between title A and webvtt C) - Modify SearchController to fetch long_summary and prioritize its snippets - Generate snippets from long_summary first (max 2), then from webvtt for remaining slots - Add comprehensive tests for long_summary search functionality - Create migration to update search_vector_en column in PostgreSQL This improves search quality by including summarized content which often contains key topics and themes that may not be explicitly mentioned in the transcript. * fix: address code review feedback for search enhancements - Fix test file inconsistencies by removing references to non-existent model fields - Comment out tests for unimplemented features (room_ids, status filters, date ranges) - Update tests to only use currently available fields (room_id singular, no room_name/processing_status) - Mark future functionality tests with @pytest.mark.skip - Make snippet counts configurable - Add LONG_SUMMARY_MAX_SNIPPETS constant (default: 2) - Replace hardcoded value with configurable constant - Improve error handling consistency in WebVTT parsing - Use different log levels for different error types (debug for malformed, warning for decode, error for unexpected) - Add catch-all exception handler for unexpected errors - Include stack trace for critical errors All existing tests pass with these changes. * fix: correct datetime test to include required duration field * feat: better highlight * feat: search room names * feat: acknowledge deleted room * feat: search filters fix and rank removal * chore: minor refactoring * feat: better matches frontend * chore: self-review (vibe) * chore: self-review WIP * chore: self-review WIP * chore: self-review WIP * chore: self-review WIP * chore: self-review WIP * chore: self-review WIP * chore: self-review WIP * remove swc (vibe) * search url query sync (vibe) * search url query sync (vibe) * better casts and cap while * PR review + simplify frontend hook * pr: remove search db timeouts * cleanup tests * tests cleanup * frontend cleanup * index declarations * refactor frontend (self-review) * fix search pagination * clear "x" for search input * pagination max pages fix * chore: cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * lockfile * pr review
42 lines
1.2 KiB
Python
42 lines
1.2 KiB
Python
"""add_search_optimization_indexes
|
|
|
|
Revision ID: b1c33bd09963
|
|
Revises: 9f5c78d352d6
|
|
Create Date: 2025-08-14 17:26:02.117408
|
|
|
|
"""
|
|
|
|
from typing import Sequence, Union
|
|
|
|
from alembic import op
|
|
|
|
# revision identifiers, used by Alembic.
|
|
revision: str = "b1c33bd09963"
|
|
down_revision: Union[str, None] = "9f5c78d352d6"
|
|
branch_labels: Union[str, Sequence[str], None] = None
|
|
depends_on: Union[str, Sequence[str], None] = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
# Add indexes for actual search filtering patterns used in frontend
|
|
# Based on /browse page filters: room_id and source_kind
|
|
|
|
# Index for room_id + created_at (for room-specific searches with date ordering)
|
|
op.create_index(
|
|
"idx_transcript_room_id_created_at",
|
|
"transcript",
|
|
["room_id", "created_at"],
|
|
if_not_exists=True,
|
|
)
|
|
|
|
# Index for source_kind alone (actively used filter in frontend)
|
|
op.create_index(
|
|
"idx_transcript_source_kind", "transcript", ["source_kind"], if_not_exists=True
|
|
)
|
|
|
|
|
|
def downgrade() -> None:
|
|
# Remove the indexes in reverse order
|
|
op.drop_index("idx_transcript_source_kind", "transcript", if_exists=True)
|
|
op.drop_index("idx_transcript_room_id_created_at", "transcript", if_exists=True)
|