Commit graph

3481 commits

Author SHA1 Message Date
Igor Ilic
74f7a65110
test: Use smaller files than Alice for tests. (#1474)
<!-- .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.
-->
Alice in wonderland expensive to process, plus Azure OpenAI flags it as
inappropriate content. Changed this to a smaller file about quantum
computers.

## 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.

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Update vector search limit-none tests to use local quantum/NLP files
and add `test_data/Quantum_computers.txt`, adjusting queries
accordingly.
> 
> - **Tests**:
> - **Vector engine limit-none coverage**
(`test_vector_engine_search_none_limit`):
> - Replace `examples/data/alice_in_wonderland.txt` with
`tests/test_data/Quantum_computers.txt` and
`tests/test_data/Natural_language_processing.txt` across
`cognee/tests/test_chromadb.py`, `cognee/tests/test_lancedb.py`, and
`cognee/tests/test_pgvector.py`.
> - Update query to "Tell me about Quantum computers" and keep assertion
verifying no implicit `limit` (ensure `len(result) > 15`).
>   - **Test data**:
>     - Add `cognee/tests/test_data/Quantum_computers.txt`.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
af1603c8f9. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
2025-09-29 12:21:16 +02:00
Igor Ilic
240925c5d4
Merge branch 'dev' into feature/cog-2837-rework-limit0-for-vector-adapters 2025-09-29 10:41:50 +02:00
Igor Ilic
e3c2c776d0
Chore: Merge main to dev branch (#1478)
<!-- .github/pull_request_template.md -->

## Description
Merge main to dev branch

## 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.

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Standardizes vector search to accept `limit=None` (fetch all/count),
updates adapters/interface and retrievers, and adds tests plus minor
logging/doc assets.
> 
> - **Vector search API**:
> - Change `limit` to `Optional[int]` in `vector_db_interface` and
adapters (`ChromaDBAdapter`, `LanceDBAdapter`, `PGVectorAdapter`,
`NeptuneAnalyticsAdapter`).
> - Behavior: `limit=None` fetches all/collection count; early-return on
`limit<=0`; minor logging copy/level tweaks; `PGVector` counts via
`func.count`.
> - **Retrievers**:
> - Switch internal calls to `limit=None` (`CogneeGraph`,
`temporal_retriever`, brute-force triplet search).
> - **Tests**:
> - Add `limit=None` coverage for ChromaDB, LanceDB (new suite), and
PGVector; assert results exceed default caps.
> - **Examples/Docs**:
> - Demo script prunes before run; add tutorial notebook and data
assets; remove one markdown article.
> - **Misc**: LLM utils demote a log line to `debug`.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
7403e31738. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
2025-09-29 10:41:18 +02:00
Vasilije
7403e31738
Merge branch 'dev' into merge-main-vol6 2025-09-28 15:29:23 +02:00
Vasilije
6da6da5a62
Aws session token support - MSR97 (#1364)
<!-- .github/pull_request_template.md -->

## Description
PR from contributor MSR97

## 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.
2025-09-28 15:28:27 +02:00
Vasilije
3b101ae8f1
refactor: Make relational database search more effective (#1477)
<!-- .github/pull_request_template.md -->

## Description
Enhance search results of relational db data by adding more information
on data type and content

PR also includes schema migration done by contributor ( Geoff-Robin )
from contribute to win competition

## 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
- [x] Performance improvement
- [ ] Other (please specify):

## 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.
2025-09-28 15:23:59 +02:00
Vasilije
af1603c8f9
Merge branch 'main' into feature/cog-2837-rework-limit0-for-vector-adapters 2025-09-28 15:23:27 +02:00
Vasilije
738935e9d9
feat: start mcp in ui cli command (#1472)
<!-- .github/pull_request_template.md -->

## Overall UI

<img width="1908" height="881" alt="Screenshot 2025-09-25 at 22 21 35"
src="https://github.com/user-attachments/assets/a3e26827-8e1a-47d1-8ac6-346387d6407f"
/>

## MCP connection - live

<img width="1519" height="691" alt="Screenshot 2025-09-25 at 22 22 02"
src="https://github.com/user-attachments/assets/2314242f-0998-4401-99e1-cfc745d40728"
/>

## MCP connection - disconnected

<img width="1520" height="698" alt="Screenshot 2025-09-25 at 22 22 11"
src="https://github.com/user-attachments/assets/ef13bb5e-6d50-4248-8d4c-8845becb1582"
/>


## 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.
2025-09-28 15:23:10 +02:00
Daulet Amirkhanov
0fac104fc7 fix: update UI server startup message to reflect dynamic frontend port 2025-09-27 20:11:39 +01:00
Daulet Amirkhanov
c0d2abdf5e feat: implement MCP connection health check in header component 2025-09-27 19:31:56 +01:00
Daulet Amirkhanov
dc1669a948 feat: add CORS middleware support for SSE and HTTP transports in MCP server 2025-09-27 19:31:39 +01:00
Vasilije
a70d2875ce
fix: Update README.md to change the URL issue of hosted solution (#1479)
<!-- .github/pull_request_template.md -->

## Description
Updated the README file to include the correct URL to the hosted
solution. Previously it tried to go as param after GitHub URL, instead I
included 'https'.

## 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)
- [x] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **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
- [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.
2025-09-27 10:35:21 +02:00
Zameel Hassan
a97005ed90
fix: Update README.md to change the URL issue of hosted solution 2025-09-27 12:11:31 +05:30
Igor Ilic
17fb3b49ef refactor: add visualization to schema migration 2025-09-27 01:15:30 +02:00
Igor Ilic
f93d30ae77 refactor: refactor schema migration 2025-09-27 00:41:58 +02:00
Igor Ilic
8ff58f0278 Merge branch 'enchanced_database_schema_ingestion_task' into relational-db-search 2025-09-27 00:19:33 +02:00
Igor Ilic
920bc78f15 refactor: Remove unused code 2025-09-27 00:18:57 +02:00
Geoff-Robin
2921021ca3 improved code readability by splitting code blocks under conditional statements into separate functions 2025-09-27 00:16:44 +02:00
Geoff-Robin
656894370e Edited test_relation_db_migration.py to include schema_only ingestion testcase 2025-09-27 00:16:44 +02:00
Geoff-Robin
67f948a145 solved nitpick comments 2025-09-27 00:16:44 +02:00
Geoff-Robin
e7bcf9043f solved more nitpick comments 2025-09-27 00:16:44 +02:00
Geoff-Robin
df8b80d4a9 solved more nitpick comments 2025-09-27 00:16:44 +02:00
Geoff-Robin
1e59f1594c solved more nitpick comments 2025-09-27 00:16:44 +02:00
Geoff-Robin
93c733e687 solved more nitpick comments 2025-09-27 00:16:44 +02:00
Geoff-Robin
7ec066111e Solved address configuration key inconsistency. 2025-09-27 00:16:44 +02:00
Geoff-Robin
60016a6b09 more nitpick comments solved 2025-09-27 00:16:44 +02:00
Geoff-Robin
7cf4a0daeb id mismatch risk negated 2025-09-27 00:16:44 +02:00
Geoff-Robin
1ba9e1df31 done with ruff checks 2025-09-27 00:16:44 +02:00
Geoff-Robin
51dfac359d Removed print statements used while debugging 2025-09-27 00:16:44 +02:00
Geoff-Robin
f5bb91e49d added description attribute to every schema model 2025-09-27 00:16:44 +02:00
Geoff-Robin
17df14363c integrated schema only ingestion 2025-09-27 00:16:44 +02:00
Geoff-Robin
a43f19cc59 ingest_database_schema with a slight alteration with return value as Dict[str,List[DataPoint] | DataPoint]] 2025-09-27 00:16:44 +02:00
Geoff-Robin
9d801f5fe0 Done creating models.py and ingest_database_schema.py 2025-09-27 00:16:44 +02:00
Igor Ilic
5528097e29 Merge branch 'main' into merge-main-vol6 2025-09-27 00:06:33 +02:00
Igor Ilic
39fa0180f3 refactor: Make relational database search more effective 2025-09-26 22:42:39 +02:00
Daulet Amirkhanov
143d9433b1 refactor: remove text parameter from subprocess call in UI startup 2025-09-26 17:53:17 +01:00
Daulet Amirkhanov
b7441f81cd feat: add health check endpoint to MCP server 2025-09-26 16:29:14 +01:00
Vasilije
241a4a1a66
Update README.md 2025-09-26 17:03:30 +02:00
Daulet Amirkhanov
056da96995 feat: add logging distinction for mcp/backend/frontend processes for clearer output 2025-09-26 14:32:15 +01:00
Daulet Amirkhanov
c518f149f2 refactor: streamline UI server startup and port availability checks 2025-09-26 14:26:43 +01:00
Daulet Amirkhanov
a68401ee70 chore: update MCP status text to connected/disconnected 2025-09-26 13:08:14 +01:00
Andrej Milicevic
bee16ea49d test: Use smaller files than Alice for tests. 2025-09-26 11:05:57 +02:00
Boris
31d1be598f
Merge branch 'dev' into feat/add-mcp-to-saas-ui 2025-09-26 10:32:15 +02:00
Boris
726d4d8535
fix: limit onnxruntime version (#1473)
<!-- .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.
2025-09-26 10:21:20 +02:00
Boris Arzentar
1deab2d54e
fix: limit onnxruntime version 2025-09-26 09:57:53 +02:00
Daulet Amirkhanov
80da553185 format: ruff format 2025-09-25 22:04:41 +01:00
Daulet Amirkhanov
921c4481f0 feat: start cognee-mcp as part of cognee -ui 2025-09-25 22:04:06 +01:00
Daulet Amirkhanov
38e3f11533 fix: update entrypoint script to use cognee-mcp module 2025-09-25 20:42:40 +01:00
Vasilije
235f28aefe
refactor: Rework limit=0 for vector adapters (#1450)
<!-- .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.
-->
Until now, limit=0 in vector search meant that there is no limit and we
should return everything. This caused confusion and errors, so now it is
reworked so that limit=None means no limit on the search. If someone
puts limit=0, there will be no results returned, as it makes more sense
and is less error prone.

## 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):

## Changes Made
<!-- List the specific changes made in this PR -->
- 
- 
- 

## Testing
<!-- Describe how you tested your changes -->

## 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

## Related Issues
<!-- Link any related issues using "Fixes #issue_number" or "Relates to
#issue_number" -->

## Additional Notes
<!-- Add any additional notes, concerns, or context for reviewers -->

## 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.
2025-09-25 21:13:41 +02:00
Vasilije
8246a6a02f
fix: Remove creation of default user during search (#1455)
<!-- .github/pull_request_template.md -->

## Description
Removed default user creation during brute force search. Even when a
user is provided to search it's not forwarded to the Retrievers, the
retrievers always created a default user and sent telemetry as the
default user which is inaccurate, they also create a default user even
when there shouldn't be one.

if this information is necessary for telemetry we should forward the
user information that was sent through search through the retrievers and
not always create a default user

## 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)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Changes Made
Removed user as parameter from brute force search, removed default user
creation that was supplied as parameter to brute force search

## Testing
Ran simple example, waiting for CI/CD results

## 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.
2025-09-25 21:11:42 +02:00