Minor changes

[azaddhirajkumar]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @azaddhirajkumar, 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 contains minor textual adjustments within the chat_with_pdf_query.py application. The changes aim to improve clarity and update terminology related to the vector search functionality, specifically by renaming the application's displayed title and refining the description of the RAG process to use more precise language.

Highlights

• UI Text Update: The application title displayed in the UI has been updated from "Chat with PDF (GSI Vector Search)" to "Chat with PDF (Query Vector Store)".
• RAG Description Clarification: The explanatory text for the Retrieval-Augmented Generation (RAG) mechanism has been revised to refer to "Query based Vector search" instead of "N1QL-based Vector search".

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 updates the terminology in the UI of the chat_with_pdf_query.py demo, replacing references to "GSI" and "N1QL" with "Query". The changes improve clarity and consistency. However, one reference to the old terminology was missed. My review includes a suggestion to fix this remaining inconsistency.

[gemini-code-assist]

There's a small inconsistency here. While you've updated N1QL-based Vector search to Query based Vector search in this line, and changed the page title from (GSI Vector Search) to (Query Vector Store) on line 226, the term Couchbase GSI Vector Search remains. For consistency with the other changes, you should update this as well.

Suggested change

	"For RAG, we are using [Langchain](https://langchain.com/), [Couchbase GSI Vector Search](https://couchbase.com/) & [OpenAI](https://openai.com/). We fetch parts of the PDF relevant to the question using Query based Vector search & add it as the context to the LLM. The LLM is instructed to answer based on the context from the Vector Store."
	"For RAG, we are using [Langchain](https://langchain.com/), [Couchbase Query Vector Search](https://couchbase.com/) & [OpenAI](https://openai.com/). We fetch parts of the PDF relevant to the question using Query based Vector search & add it as the context to the LLM. The LLM is instructed to answer based on the context from the Vector Store."