Commit graph

4042 commits

Author SHA1 Message Date
Vasilije
4b7d5f8dcd
Release v0.3.7 (#1621)
<!-- .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.
2025-10-22 22:24:39 +02:00
vasilije
1f49ca265f added lock file 2025-10-22 22:24:04 +02:00
Vasilije
262687f8db
chore: bump fastapi minimum version to 0.116.2 (#1622)
<!-- .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.
-->

In `uv.lock`, we've already been using fastapi version 0.119.0 for a
while.

However, with #1586 changes we can't allow fastapi to be lower than
0.116.2.

See https://github.com/fastapi/fastapi/pull/14077

## 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.
2025-10-22 22:00:36 +02:00
Daulet Amirkhanov
aa6df96066 update poetry.lock 2025-10-22 20:56:25 +01:00
Daulet Amirkhanov
629f672af9 chore: bump fastapi minimum version to 0.116.2 2025-10-22 20:34:52 +01:00
Vasilije
5611c8f7fc
chore: merge dev to main (#1607)
<!-- .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.
2025-10-22 21:05:10 +02:00
Vasilije
4db41ca1da
fix: Ensure consistent data storage by explicitly using \n for newlines when storing files (#1601)
<!-- .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.
-->

`LocalFileStorage.store(...)` when storing strings, uses system defaults
for newlines.

It is universally `\n` in Unix and MacOS, but for Windows by default its
`\r\n` (ancient Windows standard)

This results in hash mismatch, although content is identical.

Windows can work with `\n`, so this PR explicitly uses `\n` for newline
encoding

## 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.
2025-10-22 21:04:42 +02:00
Vasilije
407550dada
Chore: update deprecated exceptions (#1586)
<!-- .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.
-->

Logs are getting polluted with these starlette deprecation warnings.

This PR replaces the depracated status code

## 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.
2025-10-22 21:04:29 +02:00
Vasilije
91d43a36b4
Rerun and update notebooks with latest cognee (#1616)
<!-- .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.
-->

This PR reruns notebooks with latest cognee and updates outputs

## 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.
2025-10-22 21:04:05 +02:00
Daulet Amirkhanov
eee39b238b fix: handle newlines explicitly when storing files 2025-10-22 19:34:37 +01:00
Daulet Amirkhanov
56d464cfa8 rerun and update notebooks with latest cognee 2025-10-22 19:05:01 +01:00
Vasilije
d0af7c3274
Merge branch 'dev' into main 2025-10-22 19:58:38 +02:00
Vasilije
c7d0f64cb1
fix: Refactor web parsing (#1575)
<!-- .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.
-->

This PR is an iteration over #1552:

1. Refactors `preferred_loaders` from dicts, to a list that can contain
strings (name of the loader) or dicts (`{loader_name: {arg1: val1}}`),
i.e. - `[{"loader_name_one": {"arg1": "val1"}}, "loader_name_two"]`
2. Adds default extraction rules for html parsing
3. Adds unit tests that cover the changes + unit test for tavily

## 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
- [x] 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.
2025-10-22 19:09:19 +02:00
Vasilije
411f27aeaf
fix: search without prior cognify (#1570)
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin

## Description

#1548 did not handle multi-tenant case, where graph db context is set
further downstream.

This version adds empty graph logging/handling that works for
multi-tenant case
2025-10-22 19:04:56 +02:00
Vasilije
0d4ee8335c
Merge branch 'dev' into revert-1567-revert-1548-fix/search-without-prior-cognify 2025-10-22 19:04:48 +02:00
Vasilije
68e757edf4
chore:changes temporal tests llm provider to openai (#1584)
<!-- .github/pull_request_template.md -->

## Description
Changes temporal test secrets

## 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 -->
- [ ] **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.
2025-10-22 19:01:13 +02:00
Daulet Amirkhanov
3e2dbd1846 Update deprecated Exception status codes 2025-10-22 17:38:41 +01:00
hajdul88
22d3c20b90 chore:changes temporal tests llm provider to openai 2025-10-22 18:29:09 +02:00
Daulet Amirkhanov
90118562d8 cognee.add() - add more explicit check for empty preferred_loaders param 2025-10-22 17:19:46 +01:00
Daulet Amirkhanov
bfffc52064 ruff format 2025-10-22 17:10:58 +01:00
Vasilije
55cb63d60e
Merge branch 'dev' into refactor/update-web-parsing 2025-10-22 18:10:56 +02:00
vasilije
340fca3383 ruff format 2025-10-22 18:10:43 +02:00
Daulet Amirkhanov
a499bd4d3f ruff format 2025-10-22 17:10:39 +01:00
Daulet Amirkhanov
6f5915a362
Merge branch 'dev' into revert-1567-revert-1548-fix/search-without-prior-cognify 2025-10-22 17:06:11 +01:00
Vasilije
6c9b3d6385
Merge branch 'dev' into refactor/update-web-parsing 2025-10-22 18:05:54 +02:00
Vasilije
dfba2f80db
Update code for Ollama API compatibility with newer version (#1578)
<!-- .github/pull_request_template.md -->
## Description

While testing Cognee with the latest version of Ollama, I discovered two
breaking changes that prevented proper functionality:

1. **Ollama API key change**: The embeddings API response key has been
updated from `embedding` to `embeddings` in newer Ollama versions
2. **Vector dimension handling**: The `create_lance_data_point` method
was receiving vectors as nested lists `[[...]]` instead of a flat list.
Added validation to flatten the vector when this occurs.

These changes ensure compatibility with the latest Ollama release while
maintaining the expected behavior.


## 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**
- [x] 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
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] 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.
2025-10-22 18:02:56 +02:00
Vasilije
9d515d4e82
Merge branch 'dev' into main 2025-10-22 18:02:36 +02:00
Daulet Amirkhanov
9abb78efc6
Merge branch 'dev' into revert-1567-revert-1548-fix/search-without-prior-cognify 2025-10-22 16:41:38 +01:00
Daulet Amirkhanov
66345988a9
Merge branch 'dev' into refactor/update-web-parsing 2025-10-22 16:41:01 +01:00
Andrej Milićević
ec84253a87
test: Fix baml ci tests (#1576)
<!-- .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.
-->
The model, endpoint, and API key for BAML tests were changed because
they had issues with the new endpoint. Now they use OpenAI.

## 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.
2025-10-22 08:36:20 -07:00
Chinmay Bhosale
18c45acff0
Merge pull request #2 from chinu0609/fix-for-newer-version-ollama
Fix for newer version ollama
2025-10-22 20:59:26 +05:30
chinu0609
e6ab4bbeee fix: reverting the lancedb chnage 2025-10-22 20:58:45 +05:30
chinu0609
7b31b86f10 fix: reverting the lancedb chnage 2025-10-22 20:55:59 +05:30
Daulet Amirkhanov
73e81542b5 tests: remove redundant test 2025-10-22 16:23:41 +01:00
Chinmay Bhosale
8b9e30408c
Merge pull request #1 from chinu0609/fix-for-newer-version-ollama
fix: Update code for Ollama API compatibility with newer version
2025-10-22 20:06:49 +05:30
chinu0609
b47cb7462d fix: Update code for Ollama API compatibility with newer version 2025-10-22 19:55:45 +05:30
hajdul88
8d9ee07083 chore: regenerating lock files 2025-10-22 15:31:57 +02:00
hajdul88
8e59b1e933
Merge branch 'dev' into fix-baml-ci-tests 2025-10-22 15:00:17 +02:00
Daulet Amirkhanov
e4cbbcbf51 Add hint log for when data is added but not cognified 2025-10-22 13:21:51 +01:00
Daulet Amirkhanov
ee7db762e6 log warning and early exit when graph is empty and is queried 2025-10-22 13:21:51 +01:00
Daulet Amirkhanov
44345e7cf3 Revert "Revert "fix: search without prior cognify"" 2025-10-22 13:21:51 +01:00
Daulet Amirkhanov
b9afc54233 add test cases for tavily 2025-10-22 13:15:56 +01:00
Daulet Amirkhanov
925323fb35 add test for cognee.add() when tavily is used 2025-10-22 13:15:56 +01:00
Daulet Amirkhanov
5288ab4ab4 tests: fix failing tests 2025-10-22 13:15:56 +01:00
Daulet Amirkhanov
ab6a0ef11c beautilful soup loader: define default comprehensive extraction_rules 2025-10-22 13:15:56 +01:00
Daulet Amirkhanov
344fbbdc29 refactor: make prefererred_loaders easier to define on user facing api 2025-10-22 13:15:55 +01:00
Andrej Milicevic
1d1c7d21f7 change model 2025-10-22 14:06:43 +02:00
Andrej Milicevic
a7c74de208 changed temperature for baml 2025-10-22 13:11:26 +02:00
Andrej Milicevic
bb756a0e19 remove api version 2025-10-22 12:42:23 +02:00
Andrej Milicevic
1ecea0a955 change endpoint 2025-10-22 12:39:31 +02:00