Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update ragknowledge.ts #2528

Closed
wants to merge 2 commits into from
Closed

Conversation

adventuresinai
Copy link

@adventuresinai adventuresinai commented Jan 19, 2025

Relates to

Rag improvements

Risks

Low

Background

synchronise chunking & overlap with increased sizing in [generation.ts]

(https://github.com/elizaOS/eliza/pull/2525/files#diff-b68254579d690900478f82405c1f5e9eab387a8637ffddaacbfadb2ca31369da)

What does this PR do?

What kind of change is this?

Improvements (misc. changes to existing features)

synchronise chunking & overlap with increased sizing in [generation.ts]

Documentation changes needed?

My changes do not require a change to the project documentation

Testing

Where should a reviewer start?

Detailed testing steps

Summary by CodeRabbit

  • Performance Improvements
    • Enhanced chunk processing capabilities by increasing maximum chunk size and count
    • Optimized batch processing of chunk embeddings for more efficient knowledge management

Copy link
Contributor

coderabbitai bot commented Jan 19, 2025

Warning

There were issues while running some tools. Please review the errors and either fix the tool’s configuration or disable the tool if it’s a critical failure.

🔧 eslint

If the error stems from missing dependencies, add them to the package.json file. For unrecoverable errors (e.g., due to private dependencies), disable the tool in the CodeRabbit configuration.

packages/core/src/ragknowledge.ts

Oops! Something went wrong! :(

ESLint: 9.18.0

ESLint couldn't find an eslint.config.(js|mjs|cjs) file.

From ESLint v9.0.0, the default configuration file is now eslint.config.js.
If you are using a .eslintrc.* file, please follow the migration guide
to update your configuration file to the new format:

https://eslint.org/docs/latest/use/configure/migration-guide

If you still have problems after following the migration guide, please stop by
https://eslint.org/chat/help to chat with the team.

📝 Walkthrough

Walkthrough

The pull request modifies the processFile method in the RAGKnowledgeManager class, focusing on chunk processing parameters. The changes increase the maximum chunk size from 512 to 1500 and expand the maximum chunk count from 20 to 100. Additionally, a batch processing approach is introduced with a BATCH_SIZE of 10, enabling more efficient parallel processing of chunk embeddings.

Changes

File Change Summary
packages/core/src/ragknowledge.ts - Modified splitChunks function parameters to support larger chunks (1500 vs 512)
- Increased maximum chunk count from 20 to 100
- Introduced batch processing with BATCH_SIZE of 10

Finishing Touches

  • 📝 Generate Docstrings (Beta)

🪧 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. (Beta)
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @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.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (2)
packages/core/src/ragknowledge.ts (2)

Line range hint 550-591: Enhance error handling for batch processing.

The batch processing implementation looks good, but could benefit from more robust error handling for individual batch failures.

Consider this enhancement:

 for (let i = 0; i < chunks.length; i += BATCH_SIZE) {
     const batchStart = Date.now();
     const batch = chunks.slice(
         i,
         Math.min(i + BATCH_SIZE, chunks.length)
     );

-    // Process embeddings in parallel
-    const embeddings = await Promise.all(
-        batch.map((chunk) => embed(this.runtime, chunk))
-    );
+    // Process embeddings in parallel with error handling
+    const embeddings = await Promise.allSettled(
+        batch.map((chunk) => embed(this.runtime, chunk))
+    );
+
+    // Filter out failed embeddings
+    const successfulEmbeddings = embeddings
+        .filter((result): result is PromiseFulfilledResult<number[]> => 
+            result.status === 'fulfilled')
+        .map(result => result.value);
+
+    if (successfulEmbeddings.length < batch.length) {
+        elizaLogger.warn(
+            `Failed to process ${batch.length - successfulEmbeddings.length} chunks in batch`
+        );
+    }

Line range hint 550-591: Consider adding progress metrics.

The batch processing implementation would benefit from performance metrics to help tune the batch size.

Add metrics collection:

+    let totalBatchTime = 0;
+    let totalEmbeddingTime = 0;
+    let totalStorageTime = 0;
+
     for (let i = 0; i < chunks.length; i += BATCH_SIZE) {
         const batchStart = Date.now();
+        const embeddingStart = Date.now();
         
         const embeddings = await Promise.all(
             batch.map((chunk) => embed(this.runtime, chunk))
         );
+        totalEmbeddingTime += Date.now() - embeddingStart;
+        const storageStart = Date.now();
         
         await Promise.all(/* ... */);
         
+        totalStorageTime += Date.now() - storageStart;
+        totalBatchTime += Date.now() - batchStart;
     }
+    
+    elizaLogger.info(
+        `Performance metrics - ` +
+        `Avg embedding time: ${(totalEmbeddingTime/totalChunks).toFixed(2)}ms per chunk, ` +
+        `Avg storage time: ${(totalStorageTime/totalChunks).toFixed(2)}ms per chunk`
+    );
📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between cfd1f48 and b88230f.

📒 Files selected for processing (1)
  • packages/core/src/ragknowledge.ts (1 hunks)
🔇 Additional comments (1)
packages/core/src/ragknowledge.ts (1)

550-550: Consider memory implications of increased chunk parameters.

The changes to chunk parameters (size: 512→1500, count: 20→100) significantly increase memory usage. While this preserves more context, it might impact performance on resource-constrained environments.

Let's analyze the potential impact:

@wtfsayo
Copy link
Member

wtfsayo commented Jan 20, 2025

can you specify why you need this change and benefits? reopen if you still think its valuable

@wtfsayo wtfsayo closed this Jan 20, 2025
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.

2 participants