Igor Ilic
1088b58f11
fix: Add missing await to create_database ( #162 )
...
Added missing await for database creation in PGVectorAdapter
Fix #COG-170
2024-10-22 20:15:36 +02:00
Igor Ilic
0c6f019838
refactor: Remove broad exception handling from PGVectorAdapter
...
Removed broad exception handling for the search function in PGVectorAdapter
Refactor #COG-170
2024-10-22 15:41:07 +02:00
Igor Ilic
dc46304a8d
fix: Add missing await statement to LanceDBAdapter and PGVectorAdapter
...
Added missing await statement to batch search for LanceDB and PGVector adapters
Fix #COG-170
2024-10-22 15:15:45 +02:00
Igor Ilic
d30c337370
refactor: Use SQLAlchemyAdapter create_database
...
Added reusing of sqlalchemy adapters create_database method instead of directly writing code for database creation
Refactor #COG-170
2024-10-22 14:23:36 +02:00
Igor Ilic
c7ed46ddaa
fix: Change to new syntax for vector_engine_provider
...
Syntax changed for vector_engine_provider to vector_db_provider
Fix #COG-170
2024-10-22 12:57:17 +02:00
Igor Ilic
88ded6e1a8
Merge branch 'main' of github.com:topoteretes/cognee into COG-170-PGvector-adapter
2024-10-22 12:41:18 +02:00
Boris
2f832b190c
fix: various fixes for the deployment
...
* fix: remove groups from UserRead model
* fix: add missing system dependencies for postgres
* fix: change vector db provider environment variable name
* fix: WeaviateAdapter retrieve bug
* fix: correctly return data point objects from retrieve method
* fix: align graph object properties
* feat: add node example
2024-10-22 11:26:48 +02:00
Igor Ilic
4a73505e23
refactor: Move create_db_and_tables module from vectors to pgvector
...
Moved create_db_and_tables module to pgvector so it only handles pgvector related db creation
Refactor #COG-170
2024-10-22 10:29:35 +02:00
Igor Ilic
71c1374859
refactor: Move serialize_datetime function
...
Move serialize_datetime function to be in it's own file
Refactor #COG-170
2024-10-22 10:19:39 +02:00
Igor Ilic
05e4ef349e
fix: Fix pruning of postgres database
...
Fixed issue with newly added tables not being pruned from postgres database
Fix #COG-170
2024-10-21 14:28:57 +02:00
Igor Ilic
240c660eac
refactor: Change raw SQL queries to SQLalchemy ORM for PGVectorAdapter
...
Changed raw SQL quries to use SQLalchemy ORM for PGVectorAdapter
Refactor #COG-170
2024-10-21 12:59:24 +02:00
Igor Ilic
d2772d22b8
refactor: Formatting change for create_vector_engine
...
Change formatting for connection string for PGVectorAdapter
Refactor #COG-170
2024-10-18 15:03:28 +02:00
Igor Ilic
7f7b015ea3
refactor: Add formatting to create_vector_engine
...
Added formatting for PGVector part of create_vector_engine
Refactor #COG-170
2024-10-18 15:00:51 +02:00
Igor Ilic
2cd255768e
refactor: Add formatting to PGVector Adapter
...
Formatted PGVectorAdapter
Refactor #COG-170
2024-10-18 14:46:33 +02:00
Igor Ilic
325e6cd654
refactor: Rewrite search query
...
Optimize search query for PGVector
Refactor #COG-170
2024-10-18 13:33:40 +02:00
Igor Ilic
02cd2408d6
feat: Add batch search to PGVectorAdapter
...
Added batch search to PGVectorAdapter
Feature #COG-170
2024-10-17 18:11:11 +02:00
Igor Ilic
aa26eabdbb
refactor: Remove echo for database
...
Removed echoing of database operations
Refactor #COG-170
2024-10-17 17:26:26 +02:00
Igor Ilic
9b9ae6c8aa
refactor: Remove unused env parameter
...
Remove VECTOR_DB_NAME env parameter as it's not needed
Refactor #COG-170
2024-10-17 17:13:40 +02:00
Igor Ilic
9fbf2d857f
feat: Add PGVector support
...
Added first working iteration of PGVector for cognee, some important funcionality is still missing, but the core is there. Also some refactoring will be necessary.
Feature: #COG-170
2024-10-17 17:05:38 +02:00
Igor Ilic
268396abdc
feature: Checkpoint during pgvector integration development
...
Saving state of pgvector integration development so far
Feature #COG-170
2024-10-11 17:11:05 +02:00
Igor Ilic
c62dfdda9b
feat: Add PGVectorAdapter
...
Added PGVectorAdapter
Feature #COG-170
2024-10-11 15:00:28 +02:00
Igor Ilic
d68a3be32e
feat: Add config support for pgvector
...
Added config support for using pgvector
Feature #COG-170
2024-10-11 13:23:11 +02:00
Boris
dc187a81d7
feat: migrate search to tasks ( #144 )
...
* fix: don't return anything on health endpoint
* feat: add alembic migrations
* feat: align search types with the data we store and migrate search to tasks
2024-10-07 14:41:35 +02:00
Igor Ilic
fcd60861ba
fix: Fix Jupyter Notebook ( #142 )
...
* fix: resolve issue with dlt sqlalchemy usage
Cognee database configuration information was not handled properly by dlt, a new dlt handler
moudle was made to handle database configuration propagation.
* fix: resolve issue with jupyter notebook
cognee add function uses old way of working in the notebook, updated it to
work with the latest state of the cognee add function which doesn't return output.
* fix: Remove empty DB_PATH argument from .env.template
Empty value for DB_PATH in the .env file overrides default value for path intended to be used by cognee.
---------
2024-10-07 12:58:54 +02:00
Boris Arzentar
2e70c23de8
fix: log db path
2024-10-01 20:39:22 +02:00
Boris
a9433e9283
feat: add sqlalchemy as dlt destination ( #137 )
...
* feat: add sqlalchemy as dlt destination
* Fix the demo, update Readme
* fix: add 1.5 notebook
---------
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
2024-09-21 15:58:28 +02:00
Boris
e1a0b55a21
feat: user authentication in routes ( #133 )
...
* feat: require logged in user in routes
2024-09-08 21:12:49 +02:00
Boris
94a674a088
feat: split document reader from chunker ( #131 )
...
* fix: abstract chunking into a separate class
* fix: yield merged text from text chunker
* fix: split python version tests
* fix: change postgres live check
* fix: remove unnecessary code
* fix: update checkout action
* fix: update setup-python action
* fix: add PG_USER env variable
* fix: make sure relationship_name is used everywhere
* fix: remove duplicate import
2024-08-19 14:36:10 +02:00
Vasilije
1c9bbd7a43
Refactor of the tasks
2024-08-08 17:08:19 +02:00
Vasilije
2e367198cd
Task updates and updates to SQLAlchemy Adapter
2024-08-07 18:21:14 +02:00
Vasilije
a782286b93
Task updates and updates to SQLAlchemy Adapter
2024-08-07 12:36:02 +02:00
Boris Arzentar
ed6e8eb0d2
fix: wait for postgres to be ready before tests
2024-08-06 16:11:48 +02:00
Boris Arzentar
cb9bfa27ea
fix: search results preview
2024-08-06 15:23:36 +02:00
Boris Arzentar
709a10c50c
fix: add dataset and data models
2024-08-05 23:42:36 +02:00
Vasilije
b5a3b69e49
Fixes to the sqlalchemy adapter
2024-08-05 10:54:59 +02:00
Vasilije
7d3e124e4f
Fixes to the sqlalchemy adapter
2024-08-05 10:31:52 +02:00
Vasilije
085ca5ece8
Fixes to the users
2024-08-05 10:05:00 +02:00
Vasilije
07e2bc1b39
Fixes to the pipeline
2024-08-05 09:56:45 +02:00
Boris Arzentar
401167bb0f
fix: enable sqlalchemy adapter
2024-08-04 22:23:28 +02:00
Boris Arzentar
2717272403
Merge remote-tracking branch 'origin/main' into COG-206
2024-08-01 14:25:28 +02:00
Boris
26bca0184f
feat: add entity and entity type nodes to vector db ( #126 )
...
* feat: add entity and entity type nodes to vector db
* fix: use uuid5 as entity ids
* fix: id -> uuid and LanceDB collection model
2024-08-01 14:21:39 +02:00
Vasilije
797e7baba3
Updates to searches
2024-07-27 15:27:00 +02:00
Vasilije
7930586017
Fixes to the ACL model
2024-07-27 12:48:03 +02:00
Vasilije
b4d1a739be
Fixes to the ACL model
2024-07-27 12:45:15 +02:00
Vasilije
218d322c75
Fixes to the ACL model
2024-07-27 10:09:01 +02:00
Boris
5182051168
feat: expose cognee.pipelines ( #125 )
...
* fix: expose cognee.pipelines and fix batch task config
* fix: neo4j neighbours
2024-07-27 10:01:44 +02:00
Vasilije
9616545de9
Exposed user management
2024-07-26 16:14:57 +02:00
Vasilije
e7b0e712b7
Fixes to translation services
2024-07-24 16:59:58 +02:00
Vasilije
36e156e80a
Fixes to the model and adding the read info to the graph
2024-07-23 15:12:37 +02:00
Vasilije
14e1eba363
Fixes for user flow with group management
2024-07-23 13:43:08 +02:00
