Commit graph

39 commits

Author SHA1 Message Date
Igor Ilic
de1ba5cd7c feat: Add cascade deletion for datasets and data
Added cascade deletion so when a dataset or data is deleted the connection in the dataset_data table is also deleted

Feature #COG-455
2024-11-01 12:55:20 +01:00
Igor Ilic
eca1b9fddd feat: Add data deletion endpoint
Add ability to delete data instance through endpoint

Feature #COG-455
2024-10-28 14:40:49 +01:00
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
Boris
58db1ac2c8
chore: increase the lib version (#138) 2024-09-21 17:57:35 +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
920fc0232c Enable different chunking methods 2024-08-08 20:20:25 +02:00
Vasilije
1070a09806 Enable different chunking methods 2024-08-08 20:19:40 +02:00
Vasilije
7c7b8a319b Enable different chunking methods 2024-08-08 20:12:34 +02:00
Vasilije
e80d39167b Enable different chunking methods 2024-08-08 19:59:26 +02:00
Vasilije
85160da387 Refactor of the tasks 2024-08-08 13:37:55 +02:00
Vasilije
2e367198cd Task updates and updates to SQLAlchemy Adapter 2024-08-07 18:21:14 +02:00
Vasilije
1087a7edda Move tasks 2024-08-07 07:31:31 +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
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
36e156e80a Fixes to the model and adding the read info to the graph 2024-07-23 15:12:37 +02:00
Boris
86c7aa23a8
fix: remove keybert import (#120) 2024-07-20 17:08:03 +02:00
Boris Arzentar
6ef4bbe862 chore: remove unused dependencies 2024-07-20 16:59:25 +02:00
Boris
14555a25d0
feat: pipelines and tasks (#119)
* feat: simple graph pipeline

* feat: implement incremental graph generation

* fix: various bug fixes

* fix: upgrade weaviate-client

---------

Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
2024-07-20 16:49:00 +02:00
Boris Arzentar
eac6ffac1a fix: remove dspy dependency 2024-06-30 12:25:30 +02:00
Boris Arzentar
7c66364899 test: add weaviate integration test 2024-06-12 22:32:13 +02:00
Vasilije
c9b2a06dff rewrote configs 2024-06-10 13:40:05 +02:00
Boris Arzentar
f79631d5da fix: allow alternative vector db engine to be used 2024-06-06 12:31:55 +02:00
Boris Arzentar
4fb3dc31a4 fix: enable sdk and fix config 2024-06-03 14:03:24 +02:00
Boris Arzentar
aef78c4a8f fix: set config before using it 2024-05-27 14:18:39 +02:00
Boris Arzentar
624a0ac873 fix: run frontend production build in docker 2024-05-27 12:03:52 +02:00
Vasilije
cddf836fce Updates to the configs 2024-05-26 11:46:49 +02:00
Boris Arzentar
84c0c8cab5 feat: add llm config 2024-05-22 22:36:30 +02:00
Vasilije
79311ee510 fix deployment 2024-05-17 10:09:43 +02:00
Boris
219afbce68
feat: add lancedb vector storage [COG-176] (#90)
* feat: integrate lancedb

* fix: use futures in weaviate adapter to enable async behaviour
2024-05-03 10:35:41 +02:00
Vasilije
fec7010274
Merge branch 'main' into feat/code-knowledge-graph 2024-04-28 17:10:56 +02:00
Vasilije
212e5dcf78
Cog 174 (#84)
* Add telemetry

* test: add github action test

* fix: create graph only once

* fix: handle graph file not existing while deleting it

* fix: close qdrant connection in methods

---------

Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
2024-04-26 00:16:03 +02:00
Boris Arzentar
f655ee8194 Intermidiate commit 2024-04-24 19:35:36 +02:00
Boris Arzentar
b2aecf833b fix: add max_tokens to all ExtractKnowledgeGraph calls 2024-04-20 20:16:33 +02:00
Vasilije
bb679c2dd7
Improve processing, update networkx client, and Neo4j, and dspy (#69)
* Update cognify and the networkx client to prepare for running in Neo4j

* Fix for openai model

* Add the fix to the infra so that the models can be passed to the library. Enable llm_provider to be passed.

* Auto graph generation now works with neo4j

* Added fixes for both neo4j and networkx

* Explicitly name semantic node connections

* Added updated docs, readme, chunkers and updates to cognify

* Make docs build trigger only when changes on it happen

* Update docs, test git actions

* Separate cognify logic into tasks

* Introduce dspy knowledge graph extraction

---------
Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
2024-04-20 19:05:40 +02:00