Commit graph

2375 commits

Author SHA1 Message Date
Vasilije
4d02560f1c
Cog 519 develop metadata storage integration (#35)
@borisarzentar this PR is ready, the all checks run through in the
"sister" MR targeting main:
https://github.com/topoteretes/cognee-private/pull/26
2024-11-30 17:02:18 +01:00
Vasilije
d855e2ee88
Update README.md 2024-11-30 16:36:34 +01:00
Vasilije
0da0cd761b
Update README.md 2024-11-30 16:35:04 +01:00
Igor Ilic
6b97e95e14 refactor: Split entity related exceptions into graph and database exceptions
Move and split database entity related exceptions into graph and database exceptions

Refactor COG-502
2024-11-29 17:40:48 +01:00
Igor Ilic
eb09e5ad89 refactor: Moved ingestion exceptions to ingestion module
Moved custom ingestion exceptions to ingestion module

Refactor COG-502
2024-11-29 17:15:54 +01:00
Igor Ilic
1b2bdd9b83 refactor: Update __init__.py of base exception module
Updated init file of cognee base exception module

Refactor COG-502
2024-11-29 17:07:27 +01:00
Igor Ilic
df0b4b4820 refactor: Move user and group errors to users module
Moved user and group errors to users module

Refactor #COG-502
2024-11-29 17:06:34 +01:00
Vasilije
57754b3ca0
Connect pipeline to benchmark (#42)
evals/eval_swe_bench runs the code graph pipeline, adds retrieval to the
end, then connects the whole thing with swe-bench

Some unnecessary utility functions were removed.

Note: the pipeline is called for a "graphrag" folder as an example, due
to bugs in the pipeline.
2024-11-29 17:05:37 +01:00
Rita Aleksziev
a4c56f118d Connect code graph pipeline + retriever + benchmarking 2024-11-29 15:24:49 +01:00
Igor Ilic
c702b6cae0
feat: Add singleton way of working to graph databases (#39)
Added signleton type of functioning to graph databases

Feature
2024-11-29 15:04:42 +01:00
Igor Ilic
e03de63c8c
feat: Add reusable workflows for jupyter notebooks and python examples (#40)
Add reusable workflows for:
1. Jupyer notebooks
2. Python examples

Add github actions for current python examples

Feature COG-686
2024-11-29 15:04:13 +01:00
Leon Luithlen
bc82430fb5 Merge latest COG-519 2024-11-29 14:36:03 +01:00
Igor Ilic
a345471fef test: Add dynamic steps and multimedia example python script testing in github actions
Added dynamic steps and multimedia python example scripts testing in github actions

Test COG-686
2024-11-29 13:51:09 +01:00
Igor Ilic
2389e60fc1 chore: Return example to previous state before testing error raising
Return example to normal state after confirming error raising will be caught by gh action

Chore COG-686
2024-11-29 13:48:13 +01:00
Igor Ilic
f363ece4a7 chore: Test if raised error will be caught
Test if error raised inside python example will be caught

Chore COG-686
2024-11-29 13:45:38 +01:00
Igor Ilic
c7a8d2995b test: Add reusable python example workflow
Add reusable workflow for python examples, add simple example python script test

Test COG-686
2024-11-29 13:42:04 +01:00
Igor Ilic
335b8ca0de fix: Remove creation of tables for PGVector
As PGVector is used as a vector database it doesn't need to create tables based on models

Fix COG-678
2024-11-29 13:14:25 +01:00
Igor Ilic
ea38a0f51b chore: Update all notebook github actions
Update all notebook github actions to use reusable_notebook workflow

Chore COG-686
2024-11-29 12:20:12 +01:00
Rita Aleksziev
4da1657140 merge changes from code-graph 2024-11-29 12:16:36 +01:00
Igor Ilic
eaf26b5c9e chore: Update github action regrading notebook
Update github action related to jupyter notebook

Chore COG-686
2024-11-29 12:16:28 +01:00
Igor Ilic
ce99936ed5 chore: Test github action
Test notebook github action

Chore COG-686
2024-11-29 12:14:04 +01:00
Igor Ilic
d0d033bf97 chore: Test work of github action when removing label need
Test work of github action when label is not needed

Chore COG-686
2024-11-29 12:06:25 +01:00
Rita Aleksziev
8f241fa6c5 convert edge to string 2024-11-29 12:05:52 +01:00
Igor Ilic
6e8ca2f0e6 test: Attempt to fix event propagation issue
Trying to resolve issue of propagating github events to reusable workflow

Test COG-686
2024-11-29 12:04:31 +01:00
Igor Ilic
e72a84c1c3 test: Resolve issue with notebook location
Reusable workflows must be in the workflows github folder

Test COG-686
2024-11-29 11:53:26 +01:00
0xideas
56673d360c
Cog 692 run swe bench on ec2 (#25)
Mainly a tutorial and some small improvements to the evaluation code
itself
2024-11-29 11:50:21 +01:00
Igor Ilic
d586336596 test: Fix issue with notebook action
Resolve issue with wrongly defined notebook action

Test COG-686
2024-11-29 11:46:20 +01:00
Leon Luithlen
a5ae9185cd Replicate PR 33 2024-11-29 11:40:51 +01:00
Igor Ilic
a2b4c5b9eb feat: Add reusable workflows for jupyter notebooks
Add reusable workflows for Jupyer notebooks

Feature COG-686
2024-11-29 11:36:20 +01:00
Leon Luithlen
d9fc740ec0 Fix merge conflicts 2024-11-29 11:33:05 +01:00
Leon Luithlen
b46af5a6f6 Update eval_swe_bench 2024-11-29 11:31:03 +01:00
Leon Luithlen
618d476c30 Add code formating to usermod command 2024-11-29 11:30:39 +01:00
Leon Luithlen
5036f3a85f Add -y to setup_ubuntu_instance.sh commands and update EC2_README 2024-11-29 11:30:39 +01:00
Leon Luithlen
1bfa3a0ea3 Rebase onto code-graph 2024-11-29 11:30:30 +01:00
Igor Ilic
be5cb86cb2 feat: Add singleton way of working to graph databases
Added signleton type of functioning to graph databases

Feature
2024-11-28 22:15:53 +01:00
Igor Ilic
b56a1dee59 refactor: formatting fix for PR
Fixed formatting for files in pull request

Refactor COG-678
2024-11-28 20:23:27 +01:00
Rita Aleksziev
996b3a658b add custom metric implementation 2024-11-28 16:53:33 +01:00
Rita Aleksziev
8edfe7c5a4 feat/connect code graph pipeline to benchmarking 2024-11-28 16:52:54 +01:00
Igor Ilic
56367cb0c3 feat: Add Dlt support for Sqlite
Added support for using sqlite with dlt

Feature COG-678
2024-11-28 16:50:30 +01:00
Leon Luithlen
3e1949d895 Remove unnecessary nesting in embed_text and add DummyEmbeddingEngine 2024-11-28 15:42:20 +01:00
Igor Ilic
9bd3011264 feat: Make relational databases work as singleton
Moved dlt pipeline to run in it's own fuction so it doesn't use get_relational_database.
Dlt has it's own async event loop and object can't be shared between event loops

Feature COG-678
2024-11-28 12:59:04 +01:00
Leon Luithlen
5c9fd44680 Fix DummyLLMAdapter 2024-11-28 12:26:01 +01:00
hajdul88
6339295d6b
Deleting old files that are duplicated due to the different branches (#36) 2024-11-28 12:21:51 +01:00
hajdul88
72a8bc43a1 Deleting code_graph_pipeline not working entrypoint
From now on eval_swe_bench contains and rung the updated version of the pipeline
2024-11-28 12:19:08 +01:00
hajdul88
c094898d15 fix: deletes duplicated retriever instances 2024-11-28 12:12:36 +01:00
Leon Luithlen
a2ff42332e DummyLLMAdapter WIP 2024-11-28 11:49:28 +01:00
Leon Luithlen
d4e77636b5 Revert spaces around args 2024-11-28 09:18:49 +01:00
Leon Luithlen
15802237e9 Get metadata from metadata table 2024-11-28 09:18:49 +01:00
Leon Luithlen
cd0e505ac0 WIP 2024-11-28 09:18:49 +01:00
Leon Luithlen
1679c746a3 Move class and functions to data.models 2024-11-28 09:18:49 +01:00