Skip to content

Enhance AI Search with Filters, Ranking & Contextual Results (#76)#89

Merged
imuniqueshiv merged 1 commit into
imuniqueshiv:mainfrom
mrunmayeekokitkar:Enhance-AI-Search
Jul 7, 2026
Merged

Enhance AI Search with Filters, Ranking & Contextual Results (#76)#89
imuniqueshiv merged 1 commit into
imuniqueshiv:mainfrom
mrunmayeekokitkar:Enhance-AI-Search

Conversation

@mrunmayeekokitkar

@mrunmayeekokitkar mrunmayeekokitkar commented Jul 7, 2026

Copy link
Copy Markdown
Contributor

Pull Request

Description

Enhances the AI Search experience by adding advanced filtering, semantic result ranking, modular UI components, contextual search results, and improved loading and empty states. The existing AI Search endpoint remains fully compatible while providing a more powerful and user-friendly search experience across desktop and mobile devices.

Type of Change

  • New Feature
  • Bug Fix
  • Documentation Update
  • Refactor
  • Performance Improvement
  • Security Improvement
  • Other

Related Issue

Closes #76

Changes

Backend

  • Enhanced AI search to support advanced filtering.
  • Added support for filtering by:
    • Result type
    • Date range
    • Organization
    • Tags
  • Added configurable topK limit for search results.
  • Implemented semantic ranking based on similarity score.
  • Preserved compatibility with the existing AI Search endpoint.

Frontend Components

Created reusable search components:

  • SearchBar
  • SearchFilters
  • SearchResultCard
  • SearchSkeleton
  • SearchEmptyState

SearchBar

  • Search input with Enter key support.
  • Added clear search button.

SearchFilters

Added filtering controls for:

  • Result type
    • Meetings
    • Policies
    • AI Summaries
  • Date range
  • Sort order:
    • Relevance
    • Newest
    • Oldest

SearchResultCard

Displays rich contextual search results including:

  • Title
  • Result type badge
  • Similarity score
  • Summary preview
  • Tags
  • Date
  • Quick actions

Added color-coded badges for different result types.

Displays semantic similarity as a percentage.

Quick Actions

Added actions for each search result:

  • View Details
  • Open Meeting
  • Copy Summary

Loading & Empty States

  • Added skeleton loading UI.
  • Added contextual empty states for:
    • Initial search state
    • No matching results
  • Improved overall search experience during loading and empty results.

AI Search Page

Updated AiSearch.jsx to:

  • Integrate all new reusable components.
  • Manage filter state.
  • Support advanced filtering.
  • Handle quick actions.
  • Improve error handling.
  • Maintain compatibility with the existing backend API.

Design

  • Responsive across desktop, tablet, and mobile.
  • Consistent with the existing MeetOnMemory design language.

Implementation Summary

Backend Enhancements

embeddingUtils.js

  • Enhanced searchVectorStore to support:
    • Result type filters
    • Date range filters
    • Organization filters
    • Tag filters
  • Added configurable topK result limit.
  • Implemented semantic ranking using similarity scores.

aiRoutes.js

  • Updated AI search route to forward filter parameters to the search service.

Frontend Components

Created:

  • SearchBar.jsx
  • SearchFilters.jsx
  • SearchResultCard.jsx
  • SearchSkeleton.jsx
  • SearchEmptyState.jsx

Frontend Page

Updated AiSearch.jsx with:

  • Component integration
  • Filter state management
  • Quick actions
  • Improved loading and error handling

Features Implemented

  • Semantic search ranking
  • Similarity score sorting
  • Configurable search result limit
  • Result type filtering
  • Date range filtering
  • Organization filtering
  • Tag filtering
  • Sort by relevance
  • Sort by newest
  • Sort by oldest
  • Color-coded result type badges
  • Similarity score percentage display
  • Search result previews
  • Summary preview
  • Tag display
  • Date display
  • View Details action
  • Open Meeting action
  • Copy Summary action
  • Clear search button
  • Enter key search
  • Skeleton loading UI
  • Contextual empty states
  • Responsive layout
  • Existing AI Search endpoint compatibility

Testing

  • Tested locally
  • Existing functionality verified
  • No new warnings or errors

Verification

  • ESLint completed successfully (only pre-existing warnings remain).
  • Production build completed successfully.
  • Code formatted successfully.
  • Backend filtering and semantic ranking verified.
  • Frontend search, filters, ranking, and quick actions verified.
  • Responsive layouts tested.
  • Changes committed and pushed to the Enhance-AI-Search branch.

Screenshots

N/A

Checklist

  • Code follows project conventions
  • Documentation updated where required
  • No unnecessary files included
  • Changes have been tested
  • Ready for review

@mrunmayeekokitkar
Enhance AI Search with Filters, Ranking & Contextual Results (imuniqu…
b04918a 
…eshiv#76)

- Enhanced backend search with filter support (resultType, date range, organization, tags)
- Added configurable topK limit for search results
- Implemented semantic ranking with similarity score sorting
- Created modular AI search components: SearchBar, SearchFilters, SearchResultCard, SearchSkeleton, SearchEmptyState
- Updated AiSearch page with new components and features
- Added result type badges with color coding
- Implemented similarity score display with percentage
- Added quick actions: View Details, Open Meeting, Copy Summary
- Improved loading states with skeleton UI
- Enhanced empty states for better UX
- Added clear search button functionality
- Implemented date range and sort filters
- Maintained existing AI Search endpoint compatibility
- Responsive design across desktop, tablet, and mobile
- All linting and build checks passed
@vercel

vercel Bot commented Jul 7, 2026

Copy link
Copy Markdown

@mrunmayeekokitkar is attempting to deploy a commit to the Shiv Raj Singh's projects Team on Vercel.

A member of the Team first needs to authorize it.

@coderabbitai

coderabbitai Bot commented Jul 7, 2026

Copy link
Copy Markdown

Warning

Review limit reached

@mrunmayeekokitkar, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 42 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 3ce62123-bc8b-4bb9-a27c-f2f455abe719

📥 Commits

Reviewing files that changed from the base of the PR and between d007009 and b04918a.

📒 Files selected for processing (8)
  • client/src/components/ai-search/SearchBar.jsx
  • client/src/components/ai-search/SearchEmptyState.jsx
  • client/src/components/ai-search/SearchFilters.jsx
  • client/src/components/ai-search/SearchResultCard.jsx
  • client/src/components/ai-search/SearchSkeleton.jsx
  • client/src/pages/AiSearch.jsx
  • server/routes/aiRoutes.js
  • server/utils/embeddingUtils.js
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@vercel

vercel Bot commented Jul 7, 2026 •
edited
Loading

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
meetonmemory Ready Ready Preview, Comment Jul 7, 2026 9:46am

@imuniqueshiv imuniqueshiv added enhancement New feature or request ECSoC26 Eligible for Elite Coders Summer of Code 2026 automated scoring. good-backend +50 XP optimization performance UI/UX automation frontend backend labels Jul 7, 2026
@imuniqueshiv

imuniqueshiv commented Jul 7, 2026

Copy link
Copy Markdown
Owner

@mrunmayeekokitkar Thank you for another high-quality contribution to MeetOnMemory! 🚀

I really appreciate the effort you put into enhancing the AI Search experience. The addition of advanced filters, semantic ranking, reusable components, and improved loading/empty states makes the feature much more powerful while keeping the implementation well organized and compatible with the existing API.

I'm happy to have merged your PR! 🎉 If you found MeetOnMemory helpful, please consider ⭐ starring the repository. Looking forward to your future contributions—happy coding! 💙

@imuniqueshiv imuniqueshiv merged commit b9a9d9f into imuniqueshiv:main Jul 7, 2026
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@imuniqueshiv imuniqueshiv imuniqueshiv approved these changes

Assignees

No one assigned

Labels

automation backend ECSoC26-L3 ECSoC26 Eligible for Elite Coders Summer of Code 2026 automated scoring. enhancement New feature or request frontend good-backend +50 XP optimization performance UI/UX

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

🔍 Enhance AI Search with Filters, Ranking & Contextual Results

2 participants

@mrunmayeekokitkar @imuniqueshiv