LlamaIndex and Gemini Quickstart

[lucifertrj]

trafficstars

This PR contains a notebook: where anyone can get started with LlamaIndex with Gemini as the LLM.

• Approach-1: Using Image URL as input
• Approach-2: Using local image

[MarkDaoust]

Manually confirmed CLA. All good there.

[lucifertrj]

Manually confirmed CLA. All good there.

Hi @MarkDaoust

Thank you for the confirmation. The review hasn't been reviewed to merge

[review-notebook-app[bot]]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[TYMichaelChen]

Am I doing something wrong here? I get an error: ModuleNotFoundError: No module named 'llama_index.multi_modal_llms.generic_utils'

[lucifertrj]

We need images that are clearly open-licensed. We can't merge it with these images.

Sure, understood, will modify it

[lucifertrj]

Am I doing something wrong here? I get an error: ModuleNotFoundError: No module named 'llama_index.multi_modal_llms.generic_utils'

LlamaIndex version is changed, we need to install this:

!pip install llama-index-multi-modal-llms-gemini
!pip install llama-index-llms-gemini

I will update the notebook, with free open licensed images and updated modules to run the Quickstart guide

[lucifertrj]

@TYMichaelChen

Few changes to note:

• SimpleDirectoryReader is now imported via llama_index.core
• from llama_index.multi_modal_llms.generic_utils import load_image_urls is now called via llama_index.core i.e., from llama_index.core.multi_modal_llms.generic_utils import load_image_urls

@MarkDaoust

Used Open Licenses images from Unsplash

[lucifertrj]

Please delete the ".DS_Store" file.

For external integrations we're going to start an /examples/integrations directory. Can you create the directory and move this from /quickstarts/ to examples/integrations?

Thanks.

Done

[markmcd]

Hey @lucifertrj - sorry it's taken a while to get to this. Thanks for the contribution.

Can you give us a bit of context as to what this guide is trying to achieve? Right now it's missing some key introductory text to explain to the user what they are going to learn & do. For my context, and for the guide, can you give it a high level description, like "How to use Llama Index with the Gemini API for multi-turn chat conversations" or whatever task you want cover.

Before we review the content in detail it'd be great to make sure that this doesn't duplicate any existing content, and has some value on its own, so this info will help.

[lucifertrj]

Hey @markmcd sure. Will document the notebook

[github-actions[bot]]

Marking this pull request as stale since it has been open for 14 days with no activity. This PR will be closed if no further activity occurs.