Home Console GitHub

Apolo concepts
CLI Reference
Examples/Use Cases
Flow CLI
Actions Reference
Apolo Extras CLI
Python SDK

Enterprise-Ready Generative AI Applications
- Apolo Documentation Chatbot
- Canada Budget RAG
Visual RAG on Complex PDFs: Enterprise-Ready Multimodal AI
- Architecture Overview
- Implementation
Generic
- ML Model Lifecycle on Apolo Platform
  - End-to-End ML Model Lifecycle using Apolo CLI
  - ML Model Lifecycle using Apolo Console
Large language models
Image and Video processing
- Synthetic Data Generation using Stable Diffusion
- HOWTO: Lora models with Stable Diffusion
Audio Processing
- Deploying Text-to-Speech and Speech-to-Text Models in Apolo

Powered by GitBook

On this page

Was this helpful?

Visual RAG on Complex PDFs: Enterprise-Ready Multimodal AI

Architecture Overview

PreviousVisual RAG on Complex PDFs: Enterprise-Ready Multimodal AI NextImplementation

Last updated 2 months ago

Was this helpful?

The Visual RAG pipeline consists of the following key components:

Data Ingestion: PDFs are uploaded to Apolo’s object storage and processed by a job that uses ColPali to generate embeddings for text and images.
Storage:

LanceDB serves as the vector database for storing embeddings.
Apolo’s storage backend is used to persist raw data and intermediate outputs.

Query Handling:

User queries are embedded using ColPali.
LanceDB retrieves the most relevant PDF pages (text and image embeddings).

Response Generation: A visual LLM takes retrieved pages and the user query as input, generating a comprehensive answer.
Visualization: Results are displayed via a Streamlit dashboard, showing the top-matched images and the LLM’s response.