Commit graph

1024 commits

Author SHA1 Message Date
Daniel Molnar
94c785d231
fix: hotfix the file uploader in the delete router. (#842)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-21 09:55:42 +02:00
hajdul88
7eee769251
Feat: Adds dashboard application to parallel modal evals (#847)
<!-- .github/pull_request_template.md -->

## Description
Adds dashboard application to parallel modal evals to enable fast
retriever development/evaluation

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: lxobr <122801072+lxobr@users.noreply.github.com>
2025-05-21 09:07:02 +02:00
Vasilije
4c52ef62aa
feat: added util logger OS (#841)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Igor Ilic <igorilic03@gmail.com>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-05-20 20:25:49 +02:00
lxobr
9d9ea63236
fix: use default threading in Fastembed (#846)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- set the parallel option to None in Fastembed's embedding function

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-20 16:05:58 +02:00
hajdul88
5c36a5dd8a
feat: Adds modal parallel evaluation for retriever development (#844)
<!-- .github/pull_request_template.md -->

## Description
Adds modal parallel evaluation for retriever development

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-20 15:16:13 +02:00
hajdul88
f8f78773dd
Fix: Fixes graph completion search limit (#839)
<!-- .github/pull_request_template.md -->

## Description
Fixes graph completion limit

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-19 13:38:09 +02:00
Vasilije
4371b9d741
fix: 812 anthropic fix (#822)
<!-- .github/pull_request_template.md -->

## Description
Fixes Anthropic bug as reported by the user
https://github.com/topoteretes/cognee/issues/812

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-16 10:52:44 +02:00
Hande
3b07f3c08d
feat: Test db examples (#817)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
2025-05-16 09:30:47 +02:00
Dmitrii Galkin
1dd179b6dd
feat: OpenAI compatible route /api/v1/responses (#792)
## Description

/api/v1/responses
In this PR manages function calls 
- search
- cognify
- prune

Next steps
- codify


## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Signed-off-by: Diego B Theuerkauf <diego.theuerkauf@tuebingen.mpg.de>
Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Diego Baptista Theuerkauf <34717973+diegoabt@users.noreply.github.com>
Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Boris <borisarzentar@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-05-16 09:17:18 +02:00
Igor Ilic
f9f18d1b0c
feat: Add columns as nodes in relational db migration (#826)
<!-- .github/pull_request_template.md -->

## Description
Add ability to map column values from relational databases to graph

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-15 07:31:31 -04:00
Boris
0f3522eea6
fix: cognee docker image (#820)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-15 10:05:27 +02:00
Igor Ilic
e3121f5b1f
docs: Update log level of CollectionNotFoundError (#819)
<!-- .github/pull_request_template.md -->

## Description
Move CollectionNotFoundError logging to be at Debug level

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-13 12:12:35 -04:00
Igor Ilic
966e337500
feat: add MCP check status tool [COG-1784] (#793)
<!-- .github/pull_request_template.md -->

## Description
Added tools to check current cognify and codify status

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-13 12:09:14 -04:00
Daniel Molnar
8ea00971ad
fix: graphiti example (#816)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-13 14:36:23 +02:00
Igor Ilic
9c131f0d14
refactor: Update lanceDB and change delete to work async (#770)
<!-- .github/pull_request_template.md -->

## Description
Update LanceDB and rewrite data points to run async

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
2025-05-12 17:35:24 +02:00
hajdul88
a78fec3a91
fix: Fixes collection search limit in brute force triplet search (#814)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-12 13:06:57 +02:00
Matea Pesic
5d415dc1a0
feat: Add Memgraph integration (#751)
<!-- .github/pull_request_template.md -->

## Description
This PR adds support for the Memgraph graph database following the
[graph database integration
guide](https://docs.cognee.ai/contributing/adding-providers/graph-db/graph-database-integration):
- Implemented `MemgraphAdapter` for interfacing with Memgraph.
- Updated `get_graph_engine.py` to return MemgraphAdapter when
appropriate.
- Added a test script:` test_memgraph.py.`
- Created a dedicated test workflow:
`.github/workflows/test_memgraph.yml.`

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Boris <boris@topoteretes.com>
2025-05-10 13:55:37 +02:00
Boris
9729547f5a
feat: abstract logging tool integration (#787)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
2025-04-30 12:58:56 +02:00
Boris
5970d964cf
feat: pass context argument to tasks that require it (#788)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
2025-04-30 12:32:40 +02:00
Boris
cd9c4897a4
feat: remove get_distance_from_collection_names and adapt search (#766)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-30 11:11:07 +02:00
Igor Ilic
773752a4be
feat: Add detailed log handling options for Cognee exceptions [COG-1983] (#782)
<!-- .github/pull_request_template.md -->

## Description
Add log handling options for cognee exceptions

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-28 22:46:18 +02:00
Igor Ilic
a627841e72
fix: networkx id type change [COG-1876] (#786)
<!-- .github/pull_request_template.md -->

## Description
Switch typing from str to UUID for NetworkX node_id

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-28 13:32:02 +02:00
Igor Ilic
6109bf5ea5
feat: Add uv and poetry support to Cognee [COG-1572] (#780)
<!-- .github/pull_request_template.md -->

## Description
Add support for UV and for Poetry package management

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-28 12:27:43 +02:00
Vasilije
5aca3f091e
fix: Doesn't drop entire PG database, just cleans public schema - Cog 1947 (#760)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
2025-04-26 00:00:45 +02:00
Boris Arzentar
5daa99183f Merge remote-tracking branch 'origin/main' into dev 2025-04-23 13:28:01 +02:00
Igor Ilic
f404386df5
fix: hotfix 0.1.38 (#765)
<!-- .github/pull_request_template.md -->

## Description
- db_engine was not dynamically gathered, with this a change in system
directory will be handled correctly
- Added top_k to all search types
- Reduced delete test threshold 
- Updated MCP version and info

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Boris <boris@topoteretes.com>
2025-04-23 12:04:48 +02:00
Igor Ilic
60da1c899e
fix: graph prompt path (#769)
<!-- .github/pull_request_template.md -->

## Description
Fix graph prompt path

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Evain Arthur <arthur.evain35@gmail.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Boris <boris@topoteretes.com>
2025-04-23 12:03:51 +02:00
hajdul88
c5cba01d3c
fix: fixes cases when llm generates inconsistent output (#773)
<!-- .github/pull_request_template.md -->

## Description
Fixes cases when the llm generated edge list contains nodes that don't
exist in the nodelist

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-23 11:55:37 +02:00
Daniel Molnar
22f106c2fe
feat: expose document deletion via the API (#768)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
Co-authored-by: Boris <boris@topoteretes.com>
2025-04-23 09:28:14 +02:00
Vasilije
bb7eaa017b
feat: Group DataPoints into NodeSets (#680)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: lxobr <122801072+lxobr@users.noreply.github.com>
Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
2025-04-19 20:21:04 +02:00
Boris
675b66175f
test: make search unit tests deterministic (#726)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Daniel Molnar <soobrosa@gmail.com>
2025-04-18 21:55:24 +02:00
Boris
751eca7aaf
fix: cognee ui with new visualization (#733)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-04-18 15:23:51 +02:00
Igor Ilic
ba2de9bb22
fix: HuggingFace tokenizer (#752)
<!-- .github/pull_request_template.md -->

## Description
Resolve issue noticed by [RyabykinIlya](https://github.com/RyabykinIlya)
where too many HuggingFace requests have been sent due to the embedding
engine not working as a singleton per config

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Signed-off-by: Ryabykin Ilya <ryabykinia@sibur.ru>
Co-authored-by: greshish <ryabykinia@yandex.ru>
Co-authored-by: Ryabykin Ilya <ryabykinia@sibur.ru>
2025-04-17 17:07:36 +02:00
Daniel Molnar
9ba12b25ef
feat: add delete by document (#668)
<!-- .github/pull_request_template.md -->

## Description
Delete by document.

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin
2025-04-17 15:42:10 +02:00
Igor Ilic
af276b8999
feat: Add initial cognee pipeline simplification [COG-1705] (#670)
<!-- .github/pull_request_template.md -->

## Description
Simplify Cognee pipeline usage for users

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin
2025-04-17 14:02:12 +02:00
Igor Ilic
da332e85fe
Add top k [COG-1862] (#743)
<!-- .github/pull_request_template.md -->

## Description
Add ability to define top-k for Cognee search types Insights, RAG and
GRAPH Completion

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-17 14:01:35 +02:00
hajdul88
f13607cf18
fix: Index graph edges embedding error (#750)
<!-- .github/pull_request_template.md -->

## Description
Fixes the embedding error for index graph edges

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-17 12:48:27 +02:00
hajdul88
0121a2b5fc
feature: Adds S3 functionality (#731)
<!-- .github/pull_request_template.md -->

## Description
Adds S3 support


## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-17 08:56:40 +02:00
Igor Ilic
a036787ad1
Embedding string fix [COG-1900] (#742)
<!-- .github/pull_request_template.md -->

## Description
Allow embedding of big strings to support full row embedding in SQL
databases

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-16 22:39:06 +02:00
Vasilije
4e9ca94e78
feat: Adding rate limiting (#709)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-04-16 12:03:46 +02:00
lxobr
d1eab97102
feature: tighten run_tasks_base (#730)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- Extracted run_tasks_base function into a new file run_tasks_base.py.
- Extracted four executors that execute core logic based on the task
type.
- Extracted a task handler/wrapper that safely executes the core logic
with logging and telemetry.
- Fixed the inconsistency with the batches of size 1.

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-16 09:19:03 +02:00
Igor Ilic
22b363b297
tests: Add gh action to test relational db migration [COG-1591] (#718)
<!-- .github/pull_request_template.md -->

## Description
Add relational db migration action 

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-11 14:02:44 +02:00
Boris
9536395468
Revert "feat: pipeline tasks needs mapping" (#717)
Reverts topoteretes/cognee#690

I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-10 12:10:12 +02:00
Vasilije
c3d33e728e
feat: New tests (#678)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin

---------

Co-authored-by: Daniel Molnar <soobrosa@gmail.com>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
2025-04-10 10:52:48 +02:00
Igor Ilic
6f4c117005
fix: Resolve issue with missing name if no attribute (#707)
<!-- .github/pull_request_template.md -->

## Description
Resolve issue with missing name if no attribute

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-08 11:46:18 +02:00
Hande
0ca8ef2448
test: relational db migration (#695)
<!-- .github/pull_request_template.md -->

## Description
test for database migration

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-04-07 18:37:44 +02:00
Igor Ilic
c4a6c94675
fix: Resolve duplicate chunk issue for PGVector [COG-895] (#705)
<!-- .github/pull_request_template.md -->

## Description
Resolve issues with duplicate chunks for PGVector

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-07 18:03:36 +02:00
Vasilije
cd0d321eda
feat: Rename COMPLETION to RAG_COMPLETION (#701)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-07 11:46:48 +02:00
lxobr
e12242b9d0
fix: get default tasks (#700)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- Fixed get_no_summary_tasks and get_just_chunks_tasks to work with the
new tasks and pipelines
- Chore: fixed the pokemon example to work with the new tasks and
pipelines

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-07 08:46:02 +02:00
Igor Ilic
f4856b4413
Mcp add search (#702)
<!-- .github/pull_request_template.md -->

## Description
- Fix Ollama endpoint issue
- Fix COMPLETION and GRAPH COMPLETION MCP use

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-04 19:11:07 +02:00