Commit graph

2304 commits

Author SHA1 Message Date
Igor Ilic
f5cd39c09d
fix: Resolve failing test for RAG_COMPLETION, add RAG_COMPLETION to MCP (#706)
<!-- .github/pull_request_template.md -->

## Description
Resolve failing test for RAG_COMPLETION, add RAG_COMPLETION to MCP

## 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>
2025-04-07 18:13:15 +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
lxobr
8207dc8643
feat: make graph creation prompt configurable (#686)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- Added new graph creation prompts
- Exposed graph creation prompts in .cognify via get_default tasks
- Exposed graph creation prompts in eval framework
## 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>
2025-04-03 11:14:33 +02:00
Igor Ilic
b618e97f98
chore: Remove outdated nodejs example, add specific versioning for mcp (#698)
<!-- .github/pull_request_template.md -->

## Description
Remove outdated nodejs example, add specific versioning for mcp

## 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.
2025-04-03 10:53:44 +02:00
Boris
0ce6fad24a
feat: pipeline tasks needs mapping (#690)
<!-- .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.
2025-04-03 10:52:59 +02:00
Vasilije
567b45efa6
feat: Add Benchmark results (#697)
<!-- .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>
2025-04-02 18:48:56 +02:00
Vasilije
67e980f22e
feat: Add default user from config (#682)
<!-- .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>
2025-04-02 14:48:10 +02:00
Boris Arzentar
0f8bec1f07 version: v0.1.36 2025-04-02 12:49:51 +02:00
James
edea54c5c3
fix: convert file path to str (#693)
## Description

fix int unable find method .split, not sure why its a int

## 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.
2025-04-02 12:35:19 +02:00
Daniel Molnar
ef2bd5c1e3
feat: follow extras in Docker (#694)
<!-- .github/pull_request_template.md -->

## Description
Explicit is better than implicit.
https://peps.python.org/pep-0020/#the-zen-of-python

## 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.
2025-04-02 09:53:33 +02:00
Igor Ilic
6898e8f766
Fix codify mcp (#696)
<!-- .github/pull_request_template.md -->

## Description
- Redirect all Cognee output to stderr for MCP ( as stdout is used to
communicate between MCP Client and server )
- Add test for CODE search type
- Resolve missing optional GUI dependency

## 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.
2025-04-02 06:38:17 +02:00
Igor Ilic
be90fd30d6
chore: Remove frontend from docker-compose (#691)
<!-- .github/pull_request_template.md -->

## Description
Until we release a stable and usable frontend commenting it out of
docker compose

## 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.
2025-04-01 17:04:16 +02:00
Hande
5b9fd04597
docs: fix demo videos (#689)
<!-- .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.
2025-04-01 15:38:03 +02:00
Igor Ilic
7367005f25
fix: Fix mcp server start log messages (#692)
<!-- .github/pull_request_template.md -->

## Description
Change log messages so they are more understandable to mcp 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.
2025-04-01 15:18:24 +02:00
Igor Ilic
ff0878dba8
Fix logging [COG-1747] (#687)
<!-- .github/pull_request_template.md -->

## Description
Add fixes for logger, specifically:
- Add handler when users don't have microseconds
- Resolve issue with multiprocess logging

## 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.
2025-03-31 19:26:07 +02:00
Vasilije
4f72b597c9
ontology notebook added (#671)
<!-- .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
2025-03-31 18:59:23 +02:00
Hande
df37e0eda4
docs: add demo videos to readme (#688)
<!-- .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.
2025-03-31 18:57:05 +02:00
Hande
512385fafa
docs: update sample output (#685)
<!-- .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.
2025-03-31 18:00:51 +02:00
vasilije
c72d16c934 fix lock 2025-03-30 17:59:41 +02:00
Boris Arzentar
c385e7f189 version: v0.1.35 2025-03-29 19:30:12 +01:00
Boris Arzentar
738fc9ba8e feat: add LoggerInterface 2025-03-29 19:14:16 +01:00
Boris
ce6208af44
fix: send UUID node ids instead of strings (#679)
<!-- .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.
2025-03-29 19:12:18 +01:00
Boris
daed8d51f5
fix: add pipeline_name to PipelineRun and change logging default to ERROR (#675)
<!-- .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.
2025-03-29 14:55:34 +01:00
hajdul88
119fa1eb73
feat: adds graph completion retriever fix (#676)
<!-- .github/pull_request_template.md -->

## Description
Adds graph completion retriever fix

## 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
2025-03-28 17:39:56 +01:00
Igor Ilic
f6747128a2
fix: Resolve issue with MCP server communication (#674)
<!-- .github/pull_request_template.md -->

## Description
- Fixes MCP server communication issue by switching to sys.stderr ( as
is default for python loggin )
- Adds needed api optional dependency for fastapi users
- Removes lock file as a new one will need to be made after new Cognee
release with api optional dependency
- Adds log file location to MCP tool call answer

## 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
2025-03-28 17:30:24 +01:00
Igor Ilic
2611d89094
feat: Add logging to file [COG-1715] (#672)
<!-- .github/pull_request_template.md -->

## Description
Add logging to logs file

## 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
2025-03-28 16:13:56 +01:00
Dmitrii Galkin
de5b7f2044
feat: Natural Language Retriever (text2cypher) (#663)
<!-- .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

I added one example "get all connected nodes to entity"

---------

Co-authored-by: Boris <boris@topoteretes.com>
2025-03-27 15:44:39 +01:00
Boris
ebf1f81b35
fix: code cleanup [COG-781] (#667)
<!-- .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
2025-03-26 18:32:43 +01:00
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
hajdul88
897a1f3081
Feat: Adds ontology scientific paper demo (#662)
<!-- .github/pull_request_template.md -->

## Description
Adds ontology demo 2

## 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>
2025-03-25 17:21:29 +01:00
alekszievr
936fcf7cd7
chore: handle empty distance list in brute force search [cog-1424] (#654)
<!-- .github/pull_request_template.md -->

## Description
- handle empty distance list in brute force search
- unit tests

## 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>
2025-03-25 15:50:02 +01:00
Hande
14237f64e2
docs: add graph visualization (#665)
<!-- .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: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
2025-03-25 11:57:51 +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
d192d1fe20
chore: remove unused dependencies and make some optional (#661)
<!-- .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
2025-03-25 10:19:52 +01:00
Vasilije
08b326550a
Update README.md 2025-03-24 19:23:16 +01:00
Vasilije
75ffb1c5f6
Update README.md 2025-03-24 19:21:34 +01:00
Igor Ilic
7bf30f7373
fix: Cognee backend fixes (#659)
<!-- .github/pull_request_template.md -->

## Description
Cognee backend fixes

## 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 handling of `tenant_id` in JWT payload for enhanced type
safety.
- Unique identifier generation for datasets now considers the owner ID,
allowing for multiple users to share the same dataset name.

- **Bug Fixes**
- Disabled user role permissions in the permission check logic
temporarily during a rework.

- **Refactor**
  - Simplified dependencies by removing unnecessary model imports.
- Updated parameter name from `tenant` to `tenant_id` for clarity in JWT
creation.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-20 21:51:35 +01:00
lxobr
ee88fcf5d3
feat: reimplement resolve_edges_to_text with cleaner formatting (#652)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- Optimized to deduplicate nodes appearing in multiple triplets,
avoiding redundant text repetition
- Reimplemented `resolve_edges_to_text` with cleaner formatting
  - Added `_top_n_words` method for extracting frequent words from text
- Created `_get_title` function to generate titles from text content
based on first words and word frequency
  - Extracted node processing logic to `_get_nodes` helper method
  - Created dedicated `stop_words` utility with common English stopwords

## 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

## Summary by CodeRabbit

- **New Features**
- Improved text output formatting that organizes content into clearly
defined sections for enhanced readability.
- Enhanced text processing capabilities, including refined title
generation and key phrase extraction.
- Introduced a comprehensive utility for managing common stop words,
further optimizing text analysis.
  
- **Bug Fixes**
- Updated tests to ensure accurate validation of new functionalities and
improved existing test coverage.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
2025-03-20 14:52:04 +01:00
alekszievr
164cb581ec
test: test retrievers [cog-1433] (#635)
<!-- .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

- **Chores**
	- Removed unused code to streamline internal processes.
  
- **Tests**
- Added a comprehensive suite of tests to validate core retrieval and
search functionalities.
- Improved validation of response generation, context handling, and
error scenarios to ensure consistent and reliable performance.

These improvements enhance overall system stability and maintainability,
contributing to a smoother experience for end-users.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: vasilije <vas.markovic@gmail.com>
2025-03-20 10:18:21 +01:00
Igor Ilic
ede344be5d
fix: Run mcp cognify and codify as background async task [COG-1647] (#655)
…t issues

<!-- .github/pull_request_template.md -->

## Description
Resolve issue with MCP timeout by switching cognify and codify to run as
background async tasks

## 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 feedback messages now inform users when operations are
running in the background, providing an estimated wait time of up to 4
minutes.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-19 20:37:53 +01:00
hajdul88
4bd17bd82c
feat: Updated helm chart image (#656)
<!-- .github/pull_request_template.md -->

## Description
Updates helm chart image

## 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

- **Chores**
- Updated the Docker image reference for the cognee application service
to use the new, more official source for deployments.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-19 18:49:30 +01:00
alekszievr
8dd575e004
chore: move ec2 setup file and remove extra steps [cog-1585] (#653)
<!-- .github/pull_request_template.md -->

## Description
This .sh file can be used for EC2 deployment as explained in
https://github.com/topoteretes/cognee-docs/pull/58

## 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

- **Documentation**
- Removed outdated guidance for setting up evaluation environments,
streamlining the visible instructions.

- **Chores**
- Updated the Ubuntu setup process to install Python 3.12, ensuring the
virtual environment uses the latest version and enhancing overall
performance.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-19 15:02:55 +01:00
hajdul88
1c65682242
feat: adds cypher search to retrievers module (#648)
<!-- .github/pull_request_template.md -->

## Description
Exposes the query method of the adapter in the search interface for Kuzu
and Neo4j (cypher compatible adapters)

## 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 a new cypher-based search option that expands the app's
search functionality.
  - Enabled asynchronous processing for advanced query execution.
- Enhanced error messaging for unsupported search types and query
execution issues.
- Added a new enumeration value for `CYPHER` to support the new search
type.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-19 15:01:40 +01:00
hajdul88
24e0805f50
chore: deletes error log when there is no collection. Using dynamic c… (#651)
…ollection handling its not an error

<!-- .github/pull_request_template.md -->

## Description
Deletes error logging from ChromaDB 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


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

## Summary by CodeRabbit

- **Refactor**
- Updated internal error handling to ensure more consistent responses
during unforeseen issues. This change streamlines the system’s approach
to managing errors, reducing unnecessary internal error logs while
maintaining reliable operations and a stable user experience. These
refinements contribute to improved system stability and efficient error
management. Internal operations are now better optimized to handle
unexpected scenarios gracefully.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-18 11:17:23 +01:00
alekszievr
219b68c6b0
chore: Remove old eval files [cog-1567] (#649)
<!-- .github/pull_request_template.md -->

## Description
Removed old, unused eval files. 
- swe-bench eval files are kept here as swe-bench eval is not handled by
the new eval framework
- EC2_readme and cloud/setup_ubuntu_instance.sh will be removed (and
moved to the docs website) as part of another task

## 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
2025-03-17 19:19:39 +01:00
Igor Ilic
9b9fe48843
chore: Temporarily remove embedding env vars for code graph action (#647)
<!-- .github/pull_request_template.md -->

## Description
Temporarily remove embedding env variables for code graph action so the
action can run

## 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

- **Chores**
- Removed legacy secret configuration from the testing workflow to
streamline the CI process and enhance maintainability.
- **Improvements**
  - Updated the argument name in the code graph pipeline for clarity.
- Enhanced the handling of results in the example script to support
asynchronous processing.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-17 14:58:03 +01:00
lxobr
cad9e0ce44
Feat: cog 1491 pipeline steps in eval (#641)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- Created get_default_tasks_by_indices to filter default tasks by
specific indices
- Added get_no_summary_tasks function to skip summarization tasks
- Added get_just_chunks_tasks function for chunk extraction and data
points only
- Added NO_SUMMARIES and JUST_CHUNKS to the TaskGetters enum
## 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**
- The evaluation configuration now includes expanded task retrieval
options. Users can choose customized modes that bypass summarization or
focus solely on extracting data chunks, offering a more tailored
evaluation experience.
- Enhanced asynchronous task processing brings increased flexibility and
smoother performance during task selection.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-14 14:20:39 +01:00