Skip to content

chore(wren-ai-service): fix config examples#1267

Merged
paopa merged 1 commit into
mainfrom
chore/ai-service/fix-config-examples
Feb 5, 2025
Merged

chore(wren-ai-service): fix config examples#1267
paopa merged 1 commit into
mainfrom
chore/ai-service/fix-config-examples

Conversation

@cyyeh
Copy link
Copy Markdown
Member

@cyyeh cyyeh commented Feb 5, 2025

Summary by CodeRabbit

  • Documentation

    • Updated configuration examples to provide clearer and more consistent guidelines for AI embedder integration.
  • Refactor

    • Reformatted embedder model settings and revised model references across samples for streamlined consistency and ease of use.

@cyyeh cyyeh requested a review from paopa February 5, 2025 08:42
@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai Bot commented Feb 5, 2025

Walkthrough

This pull request updates configuration files for the AI service. In two files, the embedder model configuration formatting is modified by removing the list item marker, while preserving the model name, API base, and timeout settings. In the Google AI Studio configuration, the embedder reference is consistently updated from the previous model to a new gemini-based model across various pipeline entries. The overall configuration structure and comments remain intact.

Changes

File(s) Change Summary
wren-ai-service/docs/config_examples/config.deepseek.yaml
wren-ai-service/docs/config_examples/config.groq.yaml
Reformatted embedder model configuration by removing the list marker and using a single entry while retaining the same properties (model name, API base, timeout) and comments.
wren-ai-service/docs/config_examples/config.google_ai_studio.yaml Updated embedder reference in the pipeline: changed from litellm_embedder.text-embedding-004 to litellm_embedder.gemini/text-embedding-004; adjusted comments accordingly.

Suggested labels

module/ai-service, ci/ai-service

Poem

Oh, I’m a rabbit, swift and light,
Hopping through YAML fields with delight.
New embedder formats make my ears stand tall,
Updated configs answer the call.
I nibble on changes, joyful and keen—
A bunny’s cheer for code so clean!

Tip

🌐 Web search-backed reviews and chat
  • We have enabled web search-based reviews and chat for all users. This feature allows CodeRabbit to access the latest documentation and information on the web.
  • You can disable this feature by setting web_search: false in the knowledge_base settings.
  • Please share any feedback in the Discord discussion.

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 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
Copy Markdown
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 (1)
wren-ai-service/docs/config_examples/config.google_ai_studio.yaml (1)

110-113: Remove Trailing Whitespace
Line 112 contains trailing whitespace after the embedder value (litellm_embedder.gemini/text-embedding-004 ). Removing the extra space will help avoid potential YAML parsing issues.

Suggested diff:

-    embedder: litellm_embedder.gemini/text-embedding-004 
+    embedder: litellm_embedder.gemini/text-embedding-004
🧰 Tools
🪛 YAMLlint (1.35.1)

[error] 112-112: trailing spaces

(trailing-spaces)

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between c00d46d and f96af76.

📒 Files selected for processing (3)
  • wren-ai-service/docs/config_examples/config.deepseek.yaml (1 hunks)
  • wren-ai-service/docs/config_examples/config.google_ai_studio.yaml (4 hunks)
  • wren-ai-service/docs/config_examples/config.groq.yaml (1 hunks)
🧰 Additional context used
🪛 YAMLlint (1.35.1)
wren-ai-service/docs/config_examples/config.google_ai_studio.yaml

[error] 112-112: trailing spaces

(trailing-spaces)

⏰ Context from checks skipped due to timeout of 90000ms (1)
  • GitHub Check: Analyze (go)
🔇 Additional comments (7)
wren-ai-service/docs/config_examples/config.google_ai_studio.yaml (3)

18-22: Embedder Configuration Updated for Gemini Model
The embedder section now specifies the gemini/text-embedding-004 model with its dedicated API base and timeout. This update helps standardize the configuration according to the new gemini-based approach.


92-93: Pipeline Embedder Reference Consistency
The pipeline entry for question_recommendation_db_schema_retrieval now correctly references litellm_embedder.gemini/text-embedding-004. This aligns with the updated embedder naming convention and ensures consistency across pipeline tasks.


102-105: Updated Pipeline for Intent Classification
The updated pipeline entry for intent_classification now includes the correct embedder reference (litellm_embedder.gemini/text-embedding-004) alongside the LLM. This change is consistent with the overall configuration update.

wren-ai-service/docs/config_examples/config.groq.yaml (1)

18-22: Simplified Embedder Model Entry Formatting
The embedder configuration now omits the list item dash (i.e. “-”) for the sole model entry. This cleaner format is appropriate when only one embedder model is being configured and improves readability.

wren-ai-service/docs/config_examples/config.deepseek.yaml (3)

9-30: LLM Models Configuration Verification
The LLM section correctly lists multiple Deepseek models (reasoner, chat, coder) with consistent API base settings and kwargs. No issues were detected here.


35-40: Embedder Model Entry Formatting Updated
The embedder model entry has been reformatted by removing the dash (list marker) from the beginning. This results in a tidier YAML structure when a single embedder configuration is expected, while keeping the api_base and timeout settings intact.


55-142: Pipeline Section Consistency Check
The pipeline entries remain unchanged and continue referencing the appropriate LLM and embedder configurations. They align with the intended configuration structure and should integrate smoothly with the overall system settings.

🧰 Tools
🪛 YAMLlint (1.35.1)

[warning] 60-60: wrong indentation: expected 0 but found 2

(indentation)


[error] 130-130: trailing spaces

(trailing-spaces)

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