Skip to content

feat: update aggregate tool schema description to support fusion pipline CLOUDP-367319#1294

Open
nima-taheri-mongodb wants to merge 7 commits into
mainfrom
cloudp-367319_guidance_for_search_fusion
Open

feat: update aggregate tool schema description to support fusion pipline CLOUDP-367319#1294
nima-taheri-mongodb wants to merge 7 commits into
mainfrom
cloudp-367319_guidance_for_search_fusion

Conversation

@nima-taheri-mongodb

Copy link
Copy Markdown
Collaborator

No description provided.

@nima-taheri-mongodb nima-taheri-mongodb added the braintrust-evals Runs search eval suite on Braintrust label Jun 30, 2026
@github-actions

This comment has been minimized.

@nima-taheri-mongodb nima-taheri-mongodb changed the title feat: update aggregate tool schema description to support fusion pipline feat: update aggregate tool schema description to support fusion pipline CLOUDP-367319 Jun 30, 2026
@github-actions

This comment has been minimized.

@JimmyChoiMDB JimmyChoiMDB added braintrust-evals Runs search eval suite on Braintrust and removed braintrust-evals Runs search eval suite on Braintrust labels Jul 8, 2026
@github-actions

This comment has been minimized.

@JimmyChoiMDB JimmyChoiMDB marked this pull request as ready for review July 8, 2026 21:27
@JimmyChoiMDB JimmyChoiMDB requested a review from a team as a code owner July 8, 2026 21:28
@JimmyChoiMDB JimmyChoiMDB requested review from ciprian-tibulca and Copilot and removed request for a team July 8, 2026 21:28

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Pull request overview

Updates the MongoDB aggregate tool’s pipeline schema description to better guide LLM-generated aggregation pipelines, especially for vector search and hybrid (lexical + vector) search patterns.

Changes:

  • Clarifies when $vectorSearch must be the first stage vs. when $unionWith is appropriate.
  • Adds detailed guidance for hybrid search using $rankFusion / $scoreFusion, including construction constraints and recommended patterns.

Comment thread src/tools/mongodb/read/aggregate.ts Outdated
Comment thread src/tools/mongodb/read/aggregate.ts
nima-taheri-mongodb and others added 2 commits July 8, 2026 14:39
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
@JimmyChoiMDB JimmyChoiMDB force-pushed the cloudp-367319_guidance_for_search_fusion branch from 30be32a to 8bf1e42 Compare July 8, 2026 21:39
…h_fusion' into cloudp-367319_guidance_for_search_fusion

# Conflicts:
#	src/tools/mongodb/read/aggregate.ts
@github-actions

github-actions Bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

Braintrust eval CI report

Current run

Field Value
Status passed
Eval exit code 0
llm_judge (accuracy %) 77.87%
Experiment HEAD-1783547799
Experiment ID 0063a197-ef52-47e3-a04f-085990e36070
Experiment URL link
Baseline main-1783462270

Accuracy timeline (historical + this run)

---
config:
   xyChart:
       showDataLabel: true
       showDataLabelOutsideBar: true
   themeVariables:
       xyChart:
           titleColor: 'orange'
---
xychart
    title "accuracy"
    x-axis ["2026-07-06 10:19", "2026-07-06 10:26", "2026-07-06 10:42", "2026-07-06 10:42", "2026-07-06 10:43", "2026-07-06 10:52", "2026-07-06 13:07", "2026-07-06 13:25", "2026-07-07 08:04", "2026-07-07 22:11", "This run"]
    y-axis "Accuracy (%)" 0 --> 100
    bar [41.6, 43.4, 39.7, 46.8, 38.2, 43.1, 40, 42.7, 44.2, 38.2, 77.9]
    line [41.6, 43.4, 39.7, 46.8, 38.2, 43.1, 40, 42.7, 44.2, 38.2, 77.9]
Loading
Date / id Commit Accuracy Experiment
2026-07-06 10:19 f684e6f 41.57% main-1783333148
2026-07-06 10:26 92dd83e 43.43% main-1783333602
2026-07-06 10:42 8ed41ef 39.72% main-1783334575
2026-07-06 10:42 5f9ae53 46.76% main-1783334540
2026-07-06 10:43 a013380 38.24% main-1783334600
2026-07-06 10:52 4c06177 43.06% main-1783335176
2026-07-06 13:07 815a33f 40.00% main-1783343245
2026-07-06 13:25 5fc7dfc 42.69% main-1783344346
2026-07-07 08:04 3f10451 44.17% main-1783411485
2026-07-07 22:11 e99ccd0 38.24% main-1783462270
This run 77.87% HEAD-1783547799

@JimmyChoiMDB JimmyChoiMDB requested a review from nirinchev July 8, 2026 22:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

braintrust-evals Runs search eval suite on Braintrust type: feature

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants