starred/minne
1
0
Fork 0
mirror of https://github.com/perstarkse/minne.git synced 2026-04-20 16:01:22 +02:00
Code Issues Packages Projects Releases 10 Wiki Activity

evals: v3, ebeddings at the side

Browse Source 
additional indexes
This commit is contained in:
Per Stark
2025-11-26 15:00:55 +01:00
parent 226b2db43a
commit 030f0fc17d
63 changed files with 3859 additions and 1124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/migrations/definitions/20250514_142342_add_full_text_search_text_content.json
View File

@@ -1 +0,0 @@
{"schemas":"--- original\n+++ modified\n@@ -98,7 +98,7 @@\n DEFINE INDEX IF NOT EXISTS knowledge_entity_user_id_idx ON knowledge_entity FIELDS user_id;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_source_id_idx ON knowledge_entity FIELDS source_id;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_entity_type_idx ON knowledge_entity FIELDS entity_type;\n-DEFINE INDEX IF NOT EXISTS knowledge_entity_created_at_idx ON knowledge_entity FIELDS created_at; # For get_latest_knowledge_entities\n+DEFINE INDEX IF NOT EXISTS knowledge_entity_created_at_idx ON knowledge_entity FIELDS created_at;\n\n # Defines the schema for the 'message' table.\n\n@@ -157,6 +157,8 @@\n DEFINE FIELD IF NOT EXISTS require_email_verification ON system_settings TYPE bool;\n DEFINE FIELD IF NOT EXISTS query_model ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS processing_model ON system_settings TYPE string;\n+DEFINE FIELD IF NOT EXISTS embedding_model ON system_settings TYPE string;\n+DEFINE FIELD IF NOT EXISTS embedding_dimensions ON system_settings TYPE int;\n DEFINE FIELD IF NOT EXISTS query_system_prompt ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS ingestion_system_prompt ON system_settings TYPE string;\n\n","events":null}

1
common/migrations/definitions/20250606_234535_add_embedding_model_and_dimensions_to_system_settings.json
View File

@@ -1 +0,0 @@
{"schemas":"--- original\n+++ modified\n@@ -51,23 +51,23 @@\n\n # Defines the schema for the 'ingestion_task' table (used by IngestionTask).\n\n-DEFINE TABLE IF NOT EXISTS job SCHEMALESS;\n+DEFINE TABLE IF NOT EXISTS ingestion_task SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON job TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON job TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON ingestion_task TYPE string;\n+DEFINE FIELD IF NOT EXISTS updated_at ON ingestion_task TYPE string;\n\n # Custom fields from the IngestionTask struct\n # IngestionPayload is complex, store as object\n-DEFINE FIELD IF NOT EXISTS content ON job TYPE object;\n+DEFINE FIELD IF NOT EXISTS content ON ingestion_task TYPE object;\n # IngestionTaskStatus can hold data (InProgress), store as object\n-DEFINE FIELD IF NOT EXISTS status ON job TYPE object;\n-DEFINE FIELD IF NOT EXISTS user_id ON job TYPE string;\n+DEFINE FIELD IF NOT EXISTS status ON ingestion_task TYPE object;\n+DEFINE FIELD IF NOT EXISTS user_id ON ingestion_task TYPE string;\n\n # Indexes explicitly defined in build_indexes and useful for get_unfinished_tasks\n-DEFINE INDEX IF NOT EXISTS idx_job_status ON job FIELDS status;\n-DEFINE INDEX IF NOT EXISTS idx_job_user ON job FIELDS user_id;\n-DEFINE INDEX IF NOT EXISTS idx_job_created ON job FIELDS created_at;\n+DEFINE INDEX IF NOT EXISTS idx_ingestion_task_status ON ingestion_task FIELDS status;\n+DEFINE INDEX IF NOT EXISTS idx_ingestion_task_user ON ingestion_task FIELDS user_id;\n+DEFINE INDEX IF NOT EXISTS idx_ingestion_task_created ON ingestion_task FIELDS created_at;\n\n # Defines the schema for the 'knowledge_entity' table.\n\n","events":null}

1
common/migrations/definitions/20250627_120000_add_image_processing_settings.json
View File

@@ -1 +0,0 @@
{"schemas":"--- original\n+++ modified\n@@ -57,10 +57,7 @@\n DEFINE FIELD IF NOT EXISTS created_at ON ingestion_task TYPE string;\n DEFINE FIELD IF NOT EXISTS updated_at ON ingestion_task TYPE string;\n\n-# Custom fields from the IngestionTask struct\n-# IngestionPayload is complex, store as object\n DEFINE FIELD IF NOT EXISTS content ON ingestion_task TYPE object;\n-# IngestionTaskStatus can hold data (InProgress), store as object\n DEFINE FIELD IF NOT EXISTS status ON ingestion_task TYPE object;\n DEFINE FIELD IF NOT EXISTS user_id ON ingestion_task TYPE string;\n\n@@ -157,10 +154,12 @@\n DEFINE FIELD IF NOT EXISTS require_email_verification ON system_settings TYPE bool;\n DEFINE FIELD IF NOT EXISTS query_model ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS processing_model ON system_settings TYPE string;\n+DEFINE FIELD IF NOT EXISTS image_processing_model ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS embedding_model ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS embedding_dimensions ON system_settings TYPE int;\n DEFINE FIELD IF NOT EXISTS query_system_prompt ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS ingestion_system_prompt ON system_settings TYPE string;\n+DEFINE FIELD IF NOT EXISTS image_processing_prompt ON system_settings TYPE string;\n\n # Defines the schema for the 'text_chunk' table.\n\n","events":null}

1
common/migrations/definitions/20250701_000000_add_voice_processing_model_to_system_settings.json
View File

@@ -1 +0,0 @@
{"schemas":"--- original\n+++ modified\n@@ -160,6 +160,7 @@\n DEFINE FIELD IF NOT EXISTS query_system_prompt ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS ingestion_system_prompt ON system_settings TYPE string;\n DEFINE FIELD IF NOT EXISTS image_processing_prompt ON system_settings TYPE string;\n+DEFINE FIELD IF NOT EXISTS voice_processing_model ON system_settings TYPE string;\n\n # Defines the schema for the 'text_chunk' table.\n\n","events":null}

1
common/migrations/definitions/20250921_120004_fix_datetime_fields.json
View File

@@ -1 +0,0 @@
{"schemas":"--- original\n+++ modified\n@@ -18,8 +18,8 @@\n DEFINE TABLE IF NOT EXISTS conversation SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON conversation TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON conversation TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON conversation TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON conversation TYPE datetime;\n\n # Custom fields from the Conversation struct\n DEFINE FIELD IF NOT EXISTS user_id ON conversation TYPE string;\n@@ -34,8 +34,8 @@\n DEFINE TABLE IF NOT EXISTS file SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON file TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON file TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON file TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON file TYPE datetime;\n\n # Custom fields from the FileInfo struct\n DEFINE FIELD IF NOT EXISTS sha256 ON file TYPE string;\n@@ -54,8 +54,8 @@\n DEFINE TABLE IF NOT EXISTS ingestion_task SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON ingestion_task TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON ingestion_task TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON ingestion_task TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON ingestion_task TYPE datetime;\n\n DEFINE FIELD IF NOT EXISTS content ON ingestion_task TYPE object;\n DEFINE FIELD IF NOT EXISTS status ON ingestion_task TYPE object;\n@@ -71,8 +71,8 @@\n DEFINE TABLE IF NOT EXISTS knowledge_entity SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON knowledge_entity TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON knowledge_entity TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON knowledge_entity TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON knowledge_entity TYPE datetime;\n\n # Custom fields from the KnowledgeEntity struct\n DEFINE FIELD IF NOT EXISTS source_id ON knowledge_entity TYPE string;\n@@ -102,8 +102,8 @@\n DEFINE TABLE IF NOT EXISTS message SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON message TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON message TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON message TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON message TYPE datetime;\n\n # Custom fields from the Message struct\n DEFINE FIELD IF NOT EXISTS conversation_id ON message TYPE string;\n@@ -167,8 +167,8 @@\n DEFINE TABLE IF NOT EXISTS text_chunk SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON text_chunk TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON text_chunk TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON text_chunk TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON text_chunk TYPE datetime;\n\n # Custom fields from the TextChunk struct\n DEFINE FIELD IF NOT EXISTS source_id ON text_chunk TYPE string;\n@@ -191,8 +191,8 @@\n DEFINE TABLE IF NOT EXISTS text_content SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON text_content TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON text_content TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON text_content TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON text_content TYPE datetime;\n\n # Custom fields from the TextContent struct\n DEFINE FIELD IF NOT EXISTS text ON text_content TYPE string;\n@@ -215,8 +215,8 @@\n DEFINE TABLE IF NOT EXISTS user SCHEMALESS;\n\n # Standard fields\n-DEFINE FIELD IF NOT EXISTS created_at ON user TYPE string;\n-DEFINE FIELD IF NOT EXISTS updated_at ON user TYPE string;\n+DEFINE FIELD IF NOT EXISTS created_at ON user TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON user TYPE datetime;\n\n # Custom fields from the User struct\n DEFINE FIELD IF NOT EXISTS email ON user TYPE string;\n","events":null}

1
common/migrations/definitions/20251022_120302_add_scratchpad_table.json
View File

@@ -1 +0,0 @@
{"schemas":"--- original\n+++ modified\n@@ -137,6 +137,30 @@\n DEFINE INDEX IF NOT EXISTS relates_to_metadata_source_id_idx ON relates_to FIELDS metadata.source_id;\n DEFINE INDEX IF NOT EXISTS relates_to_metadata_user_id_idx ON relates_to FIELDS metadata.user_id;\n\n+# Defines the schema for the 'scratchpad' table.\n+\n+DEFINE TABLE IF NOT EXISTS scratchpad SCHEMALESS;\n+\n+# Standard fields from stored_object! macro\n+DEFINE FIELD IF NOT EXISTS created_at ON scratchpad TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS updated_at ON scratchpad TYPE datetime;\n+\n+# Custom fields from the Scratchpad struct\n+DEFINE FIELD IF NOT EXISTS user_id ON scratchpad TYPE string;\n+DEFINE FIELD IF NOT EXISTS title ON scratchpad TYPE string;\n+DEFINE FIELD IF NOT EXISTS content ON scratchpad TYPE string;\n+DEFINE FIELD IF NOT EXISTS last_saved_at ON scratchpad TYPE datetime;\n+DEFINE FIELD IF NOT EXISTS is_dirty ON scratchpad TYPE bool DEFAULT false;\n+DEFINE FIELD IF NOT EXISTS is_archived ON scratchpad TYPE bool DEFAULT false;\n+DEFINE FIELD IF NOT EXISTS archived_at ON scratchpad TYPE option<datetime>;\n+DEFINE FIELD IF NOT EXISTS ingested_at ON scratchpad TYPE option<datetime>;\n+\n+# Indexes based on query patterns\n+DEFINE INDEX IF NOT EXISTS scratchpad_user_idx ON scratchpad FIELDS user_id;\n+DEFINE INDEX IF NOT EXISTS scratchpad_user_archived_idx ON scratchpad FIELDS user_id, is_archived;\n+DEFINE INDEX IF NOT EXISTS scratchpad_updated_idx ON scratchpad FIELDS updated_at;\n+DEFINE INDEX IF NOT EXISTS scratchpad_archived_idx ON scratchpad FIELDS archived_at;\n+\n DEFINE TABLE OVERWRITE script_migration SCHEMAFULL\n PERMISSIONS\n FOR select FULL\n","events":null}

1
common/migrations/definitions/20251122_151002_remove_legacy_embedding_fields.json Normal file
View File

@@ -0,0 +1 @@
{"schemas":"--- original\n+++ modified\n@@ -85,31 +85,30 @@\n\n DEFINE FIELD IF NOT EXISTS user_id ON knowledge_entity TYPE string;\n\n-# Indexes based on build_indexes and query patterns\n-# The INDEX definition correctly specifies the vector properties\n-# HNSW index now defined on knowledge_entity_embedding table for better memory usage \n-# DEFINE INDEX IF NOT EXISTS idx_embedding_entities ON knowledge_entity FIELDS embedding HNSW DIMENSION 1536;\n+-- Indexes based on build_indexes and query patterns\n+-- HNSW index now defined on knowledge_entity_embedding table for better memory usage\n+-- DEFINE INDEX IF NOT EXISTS idx_embedding_entities ON knowledge_entity FIELDS embedding HNSW DIMENSION 1536;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_source_id_idx ON knowledge_entity FIELDS source_id;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_user_id_idx ON knowledge_entity FIELDS user_id;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_entity_type_idx ON knowledge_entity FIELDS entity_type;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_created_at_idx ON knowledge_entity FIELDS created_at;\n\n-# Defines the schema for the 'knowledge_entity_embedding' table.\n-# Separate table to optimize HNSW index creation memory usage\n+-- Defines the schema for the 'knowledge_entity_embedding' table.\n+-- Separate table to optimize HNSW index creation memory usage\n\n DEFINE TABLE IF NOT EXISTS knowledge_entity_embedding SCHEMAFULL;\n\n-# Standard fields\n+-- Standard fields\n DEFINE FIELD IF NOT EXISTS created_at ON knowledge_entity_embedding TYPE datetime;\n DEFINE FIELD IF NOT EXISTS updated_at ON knowledge_entity_embedding TYPE datetime;\n DEFINE FIELD IF NOT EXISTS user_id ON knowledge_entity_embedding TYPE string;\n\n-# Custom fields\n+-- Custom fields\n DEFINE FIELD IF NOT EXISTS entity_id ON knowledge_entity_embedding TYPE record<knowledge_entity>;\n DEFINE FIELD IF NOT EXISTS embedding ON knowledge_entity_embedding TYPE array<float>;\n\n-# Indexes\n-# DEFINE INDEX IF NOT EXISTS idx_embedding_knowledge_entity_embedding ON knowledge_entity_embedding FIELDS embedding HNSW DIMENSION 1536;\n+-- Indexes\n+-- DEFINE INDEX IF NOT EXISTS idx_embedding_knowledge_entity_embedding ON knowledge_entity_embedding FIELDS embedding HNSW DIMENSION 1536;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_embedding_entity_id_idx ON knowledge_entity_embedding FIELDS entity_id;\n DEFINE INDEX IF NOT EXISTS knowledge_entity_embedding_user_id_idx ON knowledge_entity_embedding FIELDS user_id;\n\n@@ -220,8 +219,8 @@\n DEFINE INDEX IF NOT EXISTS text_chunk_source_id_idx ON text_chunk FIELDS source_id;\n DEFINE INDEX IF NOT EXISTS text_chunk_user_id_idx ON text_chunk FIELDS user_id;\n\n-# Defines the schema for the 'text_chunk_embedding' table.\n-# Separate table to optimize HNSW index creation memory usage\n+-- Defines the schema for the 'text_chunk_embedding' table.\n+-- Separate table to optimize HNSW index creation memory usage\n\n DEFINE TABLE IF NOT EXISTS text_chunk_embedding SCHEMAFULL;\n\n@@ -235,8 +234,8 @@\n DEFINE FIELD IF NOT EXISTS chunk_id ON text_chunk_embedding TYPE record<text_chunk>;\n DEFINE FIELD IF NOT EXISTS embedding ON text_chunk_embedding TYPE array<float>;\n\n-# Indexes\n-# DEFINE INDEX IF NOT EXISTS idx_embedding_text_chunk_embedding ON text_chunk_embedding FIELDS embedding HNSW DIMENSION 1536;\n+-- Indexes\n+-- DEFINE INDEX IF NOT EXISTS idx_embedding_text_chunk_embedding ON text_chunk_embedding FIELDS embedding HNSW DIMENSION 1536;\n DEFINE INDEX IF NOT EXISTS text_chunk_embedding_chunk_id_idx ON text_chunk_embedding FIELDS chunk_id;\n DEFINE INDEX IF NOT EXISTS text_chunk_embedding_user_id_idx ON text_chunk_embedding FIELDS user_id;\n DEFINE INDEX IF NOT EXISTS text_chunk_embedding_source_id_idx ON text_chunk_embedding FIELDS source_id;\n","events":null}

2
common/migrations/definitions/_initial.json
View File

File diff suppressed because one or more lines are too long