Capella model services llamaindex example

[shyam-cb]

No description provided.

[github-actions]

Caution

Notebooks or Frontmatter Files Have Been Modified

• Please ensure that a frontmatter.md file is accompanying the notebook file, and that the frontmatter is up to date.
• These changes will be published to the developer portal tutorials only if frontmatter.md is included.
• Proofread all changes before merging, as changes to notebook and frontmatter content will update the developer tutorial.

2 Notebook Files Modified:

Notebook File	Frontmatter Included?
capella-model-services/llamaindex/query_based/RAG_with_Capella_Model_Services_and_LlamaIndex.ipynb	✅
capella-model-services/llamaindex/search_based/RAG_with_Capella_Model_Services_and_LlamaIndex.ipynb	✅

2 Frontmatter Files Modified:

Frontmatter File
capella-model-services/llamaindex/query_based/frontmatter.md
capella-model-services/llamaindex/search_based/frontmatter.md
Note: frontmatter will be checked and tested in the Test Frontmatter workflow.

[gemini-code-assist]

Summary of Changes

Hello @shyam-cb, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refactors and expands the LlamaIndex Retrieval-Augmented Generation (RAG) examples for Couchbase Capella Model Services. It introduces a new, comprehensive example demonstrating the use of Couchbase's Hyperscale and Composite Vector Indexes for optimized vector search, alongside an updated existing example that now leverages Capella Model Services more effectively. The changes aim to provide clearer, more up-to-date, and feature-rich tutorials for building RAG applications with Couchbase and LlamaIndex.

Highlights

• Example Restructuring: The LlamaIndex RAG examples have been reorganized into query_based and search_based subdirectories for better clarity and separation of concerns.
• New Query-Based RAG Tutorial: A new Jupyter notebook tutorial has been added, showcasing Retrieval-Augmented Generation (RAG) using LlamaIndex, Capella Model Services, and Couchbase's advanced Hyperscale and Composite Vector Indexes.
• Updated Search-Based RAG Tutorial: The existing RAG tutorial has been moved and significantly updated to align with the latest Capella Model Services, including changes to API key handling, model configuration, and package versions.
• Vector Index Configuration Updates: The search index definition for the search-based example was updated, specifically reducing the dims parameter from 4096 to 1024.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new Jupyter notebook for building a Retrieval-Augmented Generation (RAG) application using LlamaIndex, Capella Model Services, and Couchbase's Hyperscale and Composite Vector Indexes. It also updates an existing search-based RAG notebook to align with the new 'Capella Model Services' terminology, update package versions, and improve user input handling. Key changes include making model endpoints and API keys configurable, removing hardcoded model names, and correcting documentation links. Review comments highlight the need to dynamically configure the embedding dimension in the search index to prevent mismatches, update the dataset version used in the example, and improve output clarity by printing response.response instead of the full response object. Additionally, a redundant import was noted, and prompts for user input were refined for better clarity and consistency.