(feat): add scoreThreshold + metadata for milvus

[GregoireDaure]

Summary by CodeRabbit

• New Features
  • Enhanced search functionality now filters and ranks results by relevance.
  • Search results display additional metadata and clear relevance scores, offering more informative results.

[coderabbitai]

Walkthrough

The pull request updates the SearchAsync method in the SemanticKernelMemoryStoreCollection class. It introduces an additional parameter, minRelevanceScore, for calling GetNearestMatchesAsync (derived from settings with a default value of 0). The method now processes search results more comprehensively by parsing the AdditionalMetadata into a dictionary and explicitly casting the relevance score to a float.

Changes

File	Changes Summary
src/SemanticKernel/.../SemanticKernelMemoryStoreCollection.cs	Updated SearchAsync: adds minRelevanceScore parameter in GetNearestMatchesAsync call; enhances VectorSearchResponse by extracting both Metadata (via string splitting) and RelevanceScore (cast to float) from the results.

Sequence Diagram(s)

sequenceDiagram
    participant C as Client
    participant SK as SemanticKernelMemoryStoreCollection
    participant NS as GetNearestMatchesAsync

    C->>SK: Call SearchAsync(request, settings)
    SK->>NS: GetNearestMatchesAsync(request, minRelevanceScore)
    NS-->>SK: Return result tuples
    SK->>SK: Process each tuple 
    Note over SK: Split AdditionalMetadata\nand cast RelevanceScore to float
    SK-->>C: Return enriched VectorSearchResponse

Loading

Poem

I'm a bouncy rabbit, full of glee,
Hopping through code changes with great esprit.
I split the metadata with a joyful twist,
And cast relevance as a float in a neat little list.
Bound to celebrate each refined feature in pure🐰✨ bliss.

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 7c17620 and 7c99441.

📒 Files selected for processing (1)

• src/SemanticKernel/src/SemanticKernelMemoryStoreCollection.cs (1 hunks)

🚧 Files skipped from review as they are similar to previous changes (1)

• src/SemanticKernel/src/SemanticKernelMemoryStoreCollection.cs

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai plan to trigger planning for file edits and PR creation.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 5279ead and 7c17620.

📒 Files selected for processing (1)

• src/SemanticKernel/src/SemanticKernelMemoryStoreCollection.cs (1 hunks)

🔇 Additional comments (1)

src/SemanticKernel/src/SemanticKernelMemoryStoreCollection.cs (1)

74-74: Good addition of minimum relevance score filtering.

Adding the minRelevanceScore parameter using settings.ScoreThreshold ?? 0 allows filtering out low-relevance search results. This is a valuable improvement that enhances the search functionality.