Commit graph

43 commits

Author SHA1 Message Date
hajdul88
4a5d5f70d0 feat: adds feedback weights to edges 2025-08-19 16:50:21 +02:00
hajdul88
fc43ac7a01 feat: adds user feedback search type 2025-08-18 17:54:49 +02:00
hajdul88
fd9aaf57b1
feature: Adds doctype handling to delete (audio, image, unstructured) (#1239)
<!-- .github/pull_request_template.md -->

## Description
feature: Adds doctype handling to delete (audio, image, unstructured)

## 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.
2025-08-12 19:01:06 +02:00
hajdul88
4e816ad80b
fix: changing deletion logic to use document id instead of content hash (#1210)
<!-- .github/pull_request_template.md -->

## Description
Changing deletion logic to use document id instead of content hash

## 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.
2025-08-06 16:54:35 +02:00
Igor Ilic
b54e843951
Add neo4j multi db support (#1207)
<!-- .github/pull_request_template.md -->

## Description
Add multi db support for Neo4j Enterprise 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.

---------

Signed-off-by: Raj2604 <rajmandhare26@gmail.com>
Co-authored-by: vasilije <vas.markovic@gmail.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Daulet Amirkhanov <damirkhanov01@gmail.com>
Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Matea Pesic <80577904+matea16@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions@users.noreply.github.com>
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
Co-authored-by: Raj Mandhare <96978537+Raj2604@users.noreply.github.com>
Co-authored-by: Pedro Thompson <thompsonp17@hotmail.com>
Co-authored-by: Pedro Henrique Thompson Furtado <pedrothompson@petrobras.com.br>
2025-08-06 10:44:45 +02:00
vasilije
df17ae7720 added fix to weighted edges 2025-08-02 21:09:58 +02:00
Vasilije
1885ab9e88
chore: Cog 2354 add logging (#1115)
<!-- .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: hajdul88 <52442977+hajdul88@users.noreply.github.com>
2025-07-24 13:27:27 +02:00
Boris Arzentar
68adf6877b
fix: handle queue error 2025-07-07 13:54:22 +02:00
Boris Arzentar
f8f1bb3576
fix: add queue for data points saving 2025-07-04 18:26:22 +02:00
Boris Arzentar
00dd3b8d97
fix: run cognee distributed with modal 2025-07-04 15:28:05 +02:00
Boris Arzentar
86bd3e4a5a
Merge remote-tracking branch 'origin/dev' into feat/modal-parallelization 2025-07-02 11:28:22 +02:00
Kevin Hill
28f2414915
feat: Make graph authentication optional for Neo4j and Memgraph
Introduces optional authentication for Neo4j and Memgraph adapter handling.

---

**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: codegen-sh[bot] <131295404+codegen-sh[bot]@users.noreply.github.com>
Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
2025-06-25 18:23:27 +02:00
hajdul88
82c0279f45
Fix: adds and invokes Neo4jAdapter initialize for schema setup (#933)
<!-- .github/pull_request_template.md -->

## Description
adds and invokes Neo4jAdapter initialize for schema setup

## 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.
2025-06-09 13:40:30 +02:00
Tomaz Bratanic
e8487a06b5
Neo4j base node label (#903)
Adds base node label to Neo4j Adapter

## 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: Boris <boris@topoteretes.com>
Co-authored-by: vasilije <vas.markovic@gmail.com>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Matea Pesic <80577904+matea16@users.noreply.github.com>
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
Co-authored-by: Daniel Molnar <soobrosa@gmail.com>
Co-authored-by: Diego Baptista Theuerkauf <34717973+diegoabt@users.noreply.github.com>
Co-authored-by: Dmitrii Galkin <36552323+dm1tryG@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: lxobr <122801072+lxobr@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions@users.noreply.github.com>
2025-06-05 18:15:40 +02:00
Daniel Molnar
b5ebed1f7d
Docstring infrastructure. (#880)
<!-- .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.
2025-05-28 17:47:31 +02:00
hajdul88
965033e161
Feat: Adds subgraph retriever to graph based completion searches (#874)
<!-- .github/pull_request_template.md -->

## Description
Adds subgraph retriever to graph based completion searches

## 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.
2025-05-27 11:40:47 +02:00
Boris Arzentar
2a853e604e fix: deadlock retry adapt for class 2025-04-24 17:30:25 +02:00
Boris Arzentar
36507502ef fix: add deadlock retry for neo4j and content policy filter allback for openai models 2025-04-24 17:21:23 +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
9f587a01a4
feat: Relational db to graph db [COG-1468] (#644)
<!-- .github/pull_request_template.md -->

## Description
Add ability to migrate relational database to graph database

## 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
2025-03-26 11:40:06 +01:00
Daniel Molnar
73db1a5a53
fix: human readable logs (#658)
<!-- .github/pull_request_template.md -->

## Description
Introducing scructlog.

## 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
2025-03-25 11:54:40 +01:00
Boris
5345626e6a
fix: add proper node labels (#607)
<!-- .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


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Improved backend data organization with automatic categorization of
stored items for enhanced search and retrieval.
- Launched a product recommendation system that analyzes customer data
and preferences to suggest top products.
- Introduced a sample dataset showcasing customer profiles, preferences,
and product interactions for demonstration purposes.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-06 13:30:13 +01:00
alekszievr
e56d86b410
feat: Implement optional neo4j metrics and improve tests [cog-1262] (#556)
<!-- .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


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Enhanced graph analytics now offer detailed metrics—including shortest
path lengths, diameter, and clustering coefficients—to provide deeper
insights.
- Added new functions for creating connected test graphs and validating
metrics against predefined ground truth values.
- Introduced a new JSON file containing metrics for connected and
disconnected graph structures.

- **Improvements**
- Updated how graphs are projected to consistently use undirected
representations, ensuring more accurate and reliable metric
calculations.
- Streamlined metric consistency checks across different graph
processing methods for robust, reliable results.
- Simplified testing logic by consolidating metric assertions into a
single function call.

- **Chores**
- Removed unnecessary secret variables from the workflow configuration,
potentially affecting access to certain resources.
	- Updated secret management to include the new `OPENAI_API_KEY`.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-02-19 16:24:59 +01:00
Boris
f75e35c337
fix: custom model pipeline (#508)
<!-- .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


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit


- **New Features**
• Graph visualizations now allow exporting to a user-specified file path
for more flexible output management.
• The text embedding process has been enhanced with an additional
tokenizer option for improved performance.
• A new `ExtendableDataPoint` class has been introduced for future
extensions.
• New JSON files for companies and individuals have been added to
facilitate testing and data processing.

- **Improvements**
• Search functionality now uses updated identifiers for more reliable
content retrieval.
• Metadata handling has been streamlined across various classes by
removing unnecessary type specifications.
• Enhanced serialization of properties in the Neo4j adapter for improved
handling of complex structures.
• The setup process for databases has been improved with a new
asynchronous setup function.

- **Chores**
• Dependency and configuration updates improve overall stability and
performance.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-02-08 02:00:15 +01:00
alekszievr
8396fed9a1
feat: metrics in neo4j adapter [COG-1082] (#487)
<!-- .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


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Enhanced graph management capabilities allow users to verify graph
existence, project complete graphs, and remove graphs, delivering more
comprehensive graph insights.
  
- **Refactor**
  - Adjusted default task behavior for streamlined performance.
- Updated timestamp handling to ensure accurate and consistent record
tracking.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-02-07 15:58:43 +01:00
alekszievr
2858a674f5
feat: Calculate graph metrics for networkx graph [COG-1082] (#484)
<!-- .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


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Enabled an option to retrieve more detailed metrics, providing
comprehensive analytics for graph and descriptive data.

- **Refactor**
- Standardized the way metrics are obtained across components for
consistent behavior and improved data accuracy.
  
- **Chore**
- Made internal enhancements to support optional detailed metric
calculations, streamlining system performance and ensuring future
scalability.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-02-03 18:05:53 +01:00
alekszievr
5119992fd8
feat: Add graph metrics getter in graph db interface and adapters [COG-1082] (#483)
Dummy implementation of graph metrics to demonstrate how the interface
will look like

<!-- .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


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Introduced asynchronous functionality for retrieving comprehensive
graph metrics, including counts and connectivity details, across
different systems.
  
- **Refactor**
- Streamlined metrics processing and storage by shifting to direct
retrieval from the graph engine.
- Updated naming conventions for the `GraphMetrics` database table and
reorganized module imports to enhance internal consistency.
  
- **Chores**
- Removed dataset deletion functionalities while introducing the ability
to store descriptive metrics.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2025-02-03 15:25:04 +01:00
hajdul88
f843c256e4
feat: Use unwind for batch edge save and add unit tests for get_graph_from_model
* feat: adds some unit tests for get_graph_from_model

* feat: updates neo4j add_edges cypher and deletes shallow get_graph_from_model

* fix: fixing merge conflict false resolve

* chore: deletes old only_root unit test
2025-01-31 13:14:04 +01:00
vasilije
0a02886d76 Update format 2025-01-16 13:28:35 +01:00
hajdul88
124a26335e feat: changes model independent edge method 2025-01-14 13:58:56 +01:00
hajdul88
c351047c36 feat: adds cognee node and edge embeddings for graphiti graph 2025-01-13 17:22:59 +01:00
Rita Aleksziev
872bc89648 Format with Ruff 0.9.0 2025-01-10 15:11:00 +01:00
vasilije
60c8fd103b ruff format 2025-01-05 19:09:08 +01:00
hajdul88
0101d43b8d feat: Adds graph node filtering by feature 2024-11-20 15:13:38 +01:00
hajdul88
e988a67466 Fixes LanceDB datapoint add 2024-11-11 19:28:17 +01:00
Boris
52180eb6b5
feat: COG-184 add falkordb (#192)
* feat: add falkordb adapter

---------

Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
2024-11-11 18:20:52 +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 Arzentar
ed6e8eb0d2 fix: wait for postgres to be ready before tests 2024-08-06 16:11:48 +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
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
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
Vasilije
59feaa3e4e add test for linter 2024-05-26 08:37:23 +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