Commit graph

3725 commits

Author SHA1 Message Date
vasilije
04719129a6 updated env template 2025-10-19 15:53:38 +02:00
Igor Ilic
2998802c00 fix: Resolve issue with wrong error for OpenAI 2025-10-17 11:58:14 +02:00
Igor Ilic
a210bd5905 refactor: rename chunk_batch_size to chunks_per_batch 2025-10-15 20:24:36 +02:00
Igor Ilic
3a9022a26c refactor: Rename batch size for tasks to chunk batch size 2025-10-15 20:22:29 +02:00
Igor Ilic
99dc35f23e fix: resolve issue with neo4j metrics test 2025-10-15 20:01:09 +02:00
Igor Ilic
96496f38ed refactor: Switch to using tenacity for rate limiting 2025-10-15 18:08:18 +02:00
Igor Ilic
d01523e6fc Merge branch 'embedding-rate-limiter' of github.com:topoteretes/cognee into embedding-rate-limiter 2025-10-15 17:38:44 +02:00
Igor Ilic
5663c3fe3a refactor: add batch size param to temporal graphs 2025-10-15 17:38:18 +02:00
Igor Ilic
b4cebf4435
Merge branch 'dev' into embedding-rate-limiter 2025-10-15 15:29:36 +02:00
Igor Ilic
fc4440da8c refactor: update env template 2025-10-15 14:43:21 +02:00
Igor Ilic
1b28f13743 refactor: Optimize Cognee speed 2025-10-15 13:32:17 +02:00
Igor Ilic
417015d9a9 Merge branch 'dev' into embedding-rate-limiter 2025-10-14 20:39:10 +02:00
Igor Ilic
98daadbb04 refactor: Add tenacity retry mechanism 2025-10-14 20:29:55 +02:00
Daulet Amirkhanov
c73e8964a1
Change error logging to warning for missing playwright and protego imports in bs4_crawler.py (#1536)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

`bs4_crawler.py` missing imports is not a critical issue.

It's not part of core cognee, and can be fixed by installing `pip
install "cognee[scraping]"`.

Printing `logger.error()` also breaks our integration tests, so this PR
uses `logger.warning()` instead

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 15:11:50 +01:00
Daulet Amirkhanov
ca9db23e89
fix: Resolve issue with MCP (#1546)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 15:11:31 +01:00
Igor Ilic
42ca782e59 fix: Resolve issue with MCP 2025-10-14 15:44:21 +02:00
Daulet Amirkhanov
8a0ec8ff97
Merge branch 'dev' into fix/fix-failing-cli-integrations-test 2025-10-14 14:23:23 +01:00
Igor Ilic
0b7fb562d3
Sync poetry and uv lock updates from main to dev (#1544)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 15:09:04 +02:00
Daulet Amirkhanov
3fb241bd23 Merge remote-tracking branch 'origin/main' into merge-main-into-dev 2025-10-14 13:34:29 +01:00
Igor Ilic
84a23756f5 fix: Change chunk_size ot batch_size for temporal task 2025-10-14 14:25:38 +02:00
Vasilije
b3c10a0ab0
chore: Update poetry lock (#1542)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 14:02:29 +02:00
Igor Ilic
eb631a23ad refactor: set default numbers that are more reasonable 2025-10-14 13:57:41 +02:00
Daulet Amirkhanov
04147c3eec Change error logging to warning for missing playwright and protego imports in bs4_crawler.py 2025-10-14 12:47:41 +01:00
Igor Ilic
255def5ba9 chore: Update poetry lock 2025-10-14 13:38:41 +02:00
Vasilije
9a7f7b0364
Bump kuzu to 0.11.3 (#1539)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 13:32:45 +02:00
Vasilije
803ee4b3a1
fix: Bump version from 0.3.5 to 0.3.6 (#1541)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 13:29:42 +02:00
Vasilije
0f63be1cd2
Bump version from 0.3.5 to 0.3.6 2025-10-14 13:29:17 +02:00
Vasilije
b7c32255a9
fix: bump kuzu to 0.11.3 (#1540)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-14 13:28:33 +02:00
Daulet Amirkhanov
612827b742 fix: bump kuzu to 0.11.3 2025-10-14 12:25:39 +01:00
Daulet Amirkhanov
10b35e0c3f Bump kuzu to 0.11.3 2025-10-14 12:12:26 +01:00
Vasilije
a2617d4660
chore: deletes toml and lock files from distributed directory (#1537)
<!-- .github/pull_request_template.md -->

## Description
Deletes toml and lock files from distributed directory

## Type of Change
<!-- Please check the relevant option -->
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
None

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages

## 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.
2025-10-14 11:15:03 +02:00
hajdul88
64b43cfadd chore: deletes toml and lock files from distributed directory 2025-10-14 09:55:02 +02:00
Vasilije
c6d12e89c7
Feat/mcp add support for non standalone mode (#1523)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

With version 0.3.5 onwards, we start Cognee MCP alongside cognee ui in
`cognee-cli -ui`

Currently, cognee-mcp operates as a standalone cognee instance - with
it's own knowledge graph.

This PR
1. adds support for cognee-mcp to run in non-standalone mode as an
interface to an already running cognee backend.
2. updates `cognee-cli -ui` MCP startup

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-12 14:10:55 +02:00
Vasilije
4ac49dd27f
Merge branch 'dev' into feat/mcp-add-support-for-non-standalone-mode 2025-10-12 13:57:55 +02:00
Vasilije
1512375e52
feat: Add Docling as an ingestion option to cognee add. (#1484)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->
We are adding support for Docling documents to cognee add. I did this
the simplest way possible: converting the `DoclingDocument` early into
text, and then sending it for further processing in cognee. This avoids
adding a lot of docling-specific stuff like loaders, file types,
classes, etc. while giving us (and the users) the opportunity to handle
more different file types in our pipeline.

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-12 13:21:41 +02:00
vasilije
1e90d90a72 Merge branch 'dev' into feature/cog-2871-add-docling-as-data-ingestion-option-to-cognee-add
# Conflicts:
#	.github/workflows/examples_tests.yml
#	poetry.lock
#	uv.lock
2025-10-12 13:06:13 +02:00
Vasilije
fae0e240d3
fix: Pr 1449 (#1533)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## Type of Change
<!-- Please check the relevant option -->
- [x] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-12 12:03:02 +02:00
vasilije
5527b6e0b3 format done 2025-10-12 11:47:40 +02:00
vasilije
ca88200b7c Merge remote-tracking branch 'origin/pr-1449' into pr-1449
# Conflicts:
#	poetry.lock
#	uv.lock
2025-10-12 11:46:43 +02:00
Aniruddha Mandal
9229e1154d chore: update dependency specifications in pyproject.toml
- Changed "mistralai==1.9.10" to "mistralai>=1.9.10" for more flexible versioning.
- Removed "mistralai" from the optional dependencies under "mistral".
- Expanded the "docs" dependency to include "pdf" support.
2025-10-12 11:44:46 +02:00
Aniruddha Mandal
19fcbba7cc chore: update dependencies in pyproject.toml and uv.lock
- Added "mistralai==1.9.10" to the dependencies in pyproject.toml.
- Updated sdist entries in uv.lock to remove unnecessary upload-time fields for various packages.
- Ensured consistency in package specifications across the project files.
2025-10-12 11:44:39 +02:00
Aniruddha Mandal
06dca5bf26 Enhance MistralAdapter error handling and response validation in chat completion method 2025-10-12 11:44:36 +02:00
Aniruddha Mandal
617c1f0d71 Added Mistral support as LLM provider using litellm 2025-10-12 11:44:33 +02:00
vasilije
694ed54d07 regen lock 2025-10-12 11:41:18 +02:00
Vasilije
a4ab65768b
fix: Scraper fix (#1532)
<!-- .github/pull_request_template.md -->

## Description
<!--
Ugly fix for the scraper with try except blocks.
Needs to be refactored
For now tests will pass 
-->

## Type of Change
<!-- Please check the relevant option -->
- [X ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## 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.
2025-10-12 11:36:45 +02:00
vasilije
8f619a7b8d added poetry lock 2025-10-12 11:27:20 +02:00
vasilije
19431a41d6 tried adding cli fix 2025-10-12 11:25:41 +02:00
vasilije
0d726c0e32 small linting issues 2025-10-12 11:09:43 +02:00
vasilije
4c5de73598 small linting issues 2025-10-12 11:03:19 +02:00
vasilije
988a196479 added fixes 2025-10-12 10:54:14 +02:00