Feature: Added a reader using the multimodal capability of Gemini

[sumitaryal]

Description

Add GeminiReader: AI-powered PDF extraction using Google's Gemini models

This PR introduces a new LlamaIndex reader integration that leverages Google's Gemini AI models for high-quality PDF extraction and intelligent chunking.

Motivation

Traditional PDF parsers often struggle with complex layouts, scanned documents, tables, and forms. By utilizing Gemini's vision capabilities, this reader provides significantly better extraction quality and semantic chunking for improved RAG performance.

Key Features

• AI-powered OCR that handles complex layouts and scanned documents
• Intelligent semantic chunking that preserves document structure
• Special handling for tables, forms, and mathematical formulas
• Parallel processing with configurable parallelism
• Continuous mode for content spanning multiple pages
• Built-in caching system to avoid redundant processing

Implementation

The reader is built as a BasePydanticReader extension with comprehensive configuration options. It creates semantically meaningful document chunks while preserving metadata about their source and position in the original document.

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

• Yes
• No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No

Type of Change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[logan-markewich]

imo, it is 100000x times safer to be using async concurrency vs. threading. I would prefer something like asyncio.gather() behind a semaphore -- we actually have utility for this as well

from llama_index.core.async_utils import run_jobs

jobs = [some_async_fn() for x in thing]
results = await run_jobs(jobs, workers=self.max_workers)