DA-1253: Update Haystack Rag Demo to use Couchbase 8.0+ Vector Indexes

[VirajAgarwal1]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @VirajAgarwal1, 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 significantly enhances the Haystack RAG demo by providing specialized tutorials for different Couchbase vector indexing capabilities. It introduces a new guide for integrating with Couchbase 8.0+'s Hyperscale Vector Index, optimized for large-scale, pure vector search, and refines the existing tutorial to focus on Couchbase 7.6+'s Search Vector Index for hybrid search scenarios. Both approaches now benefit from automated index creation, streamlining the setup process for users and offering clearer guidance based on their Couchbase version and specific vector search needs.

Highlights

• Tutorial Split for Vector Index Types: The existing Haystack PDF chat tutorial has been refactored into two distinct guides: one specifically for Couchbase Hyperscale Vector Index (targeting Couchbase 8.0+) and another for Couchbase Search Vector Index (targeting Couchbase 7.6+).
• Automated Index Management: Both new and updated tutorials now feature automatic creation of their respective Couchbase vector indexes (Hyperscale or Search Vector Index) directly from the application, significantly simplifying the setup process for users.
• Couchbase 8.0+ Hyperscale Integration: A new tutorial introduces the use of CouchbaseQueryDocumentStore and CouchbaseQueryEmbeddingRetriever for leveraging Couchbase 8.0+'s Hyperscale Vector Index, optimized for high-performance, pure vector search with SQL++ queries.
• Couchbase 7.6+ Search Vector Index Updates: The original tutorial has been updated and renamed to explicitly use CouchbaseSearchDocumentStore and CouchbaseSearchEmbeddingRetriever for seamless integration with Couchbase 7.6+'s Search Vector Index, ideal for hybrid search scenarios.
• Improved Document Chunking: The document splitting strategy in the Search Vector Index tutorial was updated from sentence-based to word-based splitting with increased overlap, potentially leading to better context preservation during retrieval.

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 does a great job of updating the Haystack RAG demo to support Couchbase 8.0+ vector indexes by splitting the tutorial into two distinct guides: one for Hyperscale Vector Index (query-based) and another for Search Vector Index (search-based). This separation significantly improves clarity for users. The new Hyperscale tutorial is comprehensive, and the existing tutorial has been effectively updated for SVI. I've identified several areas for improvement, primarily within the new tutorial, including typos, grammatical errors, incorrect code snippets with missing imports, and some conceptual inaccuracies such as a reference to LangChain and flawed logic for a pure LLM call. Addressing these points will greatly enhance the quality and correctness of these valuable tutorials.

[shyam-cb]

Just have search

[VirajAgarwal1]

But that makes the tutorial tag less verbose... Also, search could also mean plain FTS... I believe we should stick with vector search similar to other Vector search tutorials...