Skip to content

Conversation

timfdev
Copy link

@timfdev timfdev commented Aug 12, 2025

pydantic-ai and ag-ui-protocol

need pydantic >= 2.10 and >=2.11.2 respectively, this breaks some of the unit tests

…s allowed token count. Make conflicting libraries pydantic-ai and ag-ui optional; disabling agent route if not installed. Make search routes async and fix small bugs in query building.
Copy link

codspeed-hq bot commented Aug 16, 2025

CodSpeed Performance Report

Merging #1028 will not alter performance

Comparing llm-integration (816ead4) with main (98706ec)

🎉 Hooray! pytest-codspeed just leveled up to 4.0.0!

A heads-up, this is a breaking change and it might affect your current performance baseline a bit. But here's the exciting part - it's packed with new, cool features and promises improved result stability 🥳!
Curious about what's new? Visit our releases page to delve into all the awesome details about this new version.

Summary

✅ 13 untouched benchmarks

Copy link

codecov bot commented Aug 18, 2025

Codecov Report

❌ Patch coverage is 44.71154% with 805 lines in your changes missing coverage. Please review.
✅ Project coverage is 80.22%. Comparing base (98706ec) to head (816ead4).

Files with missing lines Patch % Lines
orchestrator/search/indexing/indexer.py 23.78% 125 Missing ⚠️
orchestrator/search/indexing/traverse.py 32.52% 83 Missing ⚠️
orchestrator/search/agent/tools.py 7.81% 59 Missing ⚠️
orchestrator/search/retrieval/ranker.py 37.17% 49 Missing ⚠️
orchestrator/search/core/types.py 62.50% 45 Missing ⚠️
orchestrator/search/retrieval/validation.py 25.00% 45 Missing ⚠️
orchestrator/api/api_v1/endpoints/search.py 40.54% 44 Missing ⚠️
orchestrator/search/filters/base.py 47.61% 44 Missing ⚠️
orchestrator/search/retrieval/utils.py 25.00% 42 Missing ⚠️
orchestrator/cli/search_explore.py 42.18% 36 Missing and 1 partial ⚠️
... and 15 more
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1028      +/-   ##
==========================================
- Coverage   84.93%   80.22%   -4.72%     
==========================================
  Files         214      245      +31     
  Lines       10408    11821    +1413     
  Branches     1020     1161     +141     
==========================================
+ Hits         8840     9483     +643     
- Misses       1295     2082     +787     
+ Partials      273      256      -17     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Comment on lines +46 to +51
dotenv run python main.py search semantic "Shop for an alligator store"
...
{
"path": "subscription.shop.shop_description",
"value": "Kingswood reptiles shop"
},

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should make the examples more generic (also the ones below), since this is specific for the WFO instance where we built the initial POC.

### Step back to the revision right before the dynamic-dimension migration

```bash
dotenv run python main.py db downgrade 850dccac3b02

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I commented before that we needed a script for this, but does this mean you can run this migration independent from all other migrations?

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes you can downgrade a specific migration and upgrade it again, essentially achieving the same as a cli script.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SURF doesn't have a downgrade policy: often they are written: but not always. (also no tests).

If stuff breaks in production -> we try to move forwards.

FilterCondition = (
DateFilter # DATETIME
| NumericFilter # INT/FLOAT
| StringFilter # STRING TODO: convert to hybrid search

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we need to make a ticket for this TODO?

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Im thinking that maybe this stringfilter should be removed altogether, its already possible to do a hybrid search by passing a user query, passing something like the top 5 results back to the agent will probably yield better results.

For things like booleans/product blocks , we already have the equality filter. Matching on exact text by letting the agent fill in a string will probably not work well.

timfdev and others added 6 commits August 23, 2025 19:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants