RAG with Google Vertex AI and BigQuery

Development of a rapid Proof of Concept (POC) for a Retrieval-Augmented Generation (RAG) system, integrating Google Vertex AI, BigQuery, and advanced LLM capabilities to enhance data query and document processing.

Contact Us

Project Overview

Developed a robust RAG system using multiple LLMs, integrated with Google Vertex AI and BigQuery to handle complex queries, enhance LLM responses, and improve document ingestion and retrieval for seamless workspace management.

Project Details

Team Composition

1 Member

Duration

472 Hours

Country

Romania

Industry

Technology

Client Name

Confidential Client

Expertise Used

Large Language Models (LLM), Streamlit, Flask, FastAPI, GCP Vertex AI, BigQuery, LangChain, RAG Architecture

Client Information

Confidential Client

Confidential Role

Restricted Details

Confidential Client

Technology

Streamlit
Flask
FastAPI
Google Vertex
Google Big Query
LangChain
chroma
No items found.
Streamlit
Flask
FastAPI
Google Vertex
Google Big Query
LangChain
chroma
No items found.
Streamlit
Flask
FastAPI
Google Vertex
Google Big Query
LangChain
chroma
No items found.

Solution Delivered

Developed a POC for a RAG-based system that allows for LLM integration with Google Vertex AI and BigQuery, enabling flexible query handling, document processing, and workspace management. The solution also included features for API switching between different LLMs, error handling to reduce API calls, and data ingestion for enhanced query accuracy.

Project Details

RAG with Google Vertex AI and BigQuery - delivered solution
No items found.

Key Features

  1. Generative AI Chat App: Created a chat app using Streamlit and integrated LLM functionalities.
  2. Multi-Column Layout: Implemented a multi-column layout within the chat app for better organization.
  3. Database Reset: Added functionality to reset the database using Chroma DB's reset function.
  4. LLM Switching: Developed an API to toggle between OpenAI and Vertex AI models.
  5. Streaming Response in FastAPI: Integrated streaming response capabilities for better user interaction.
  6. Workspace Management: Added workspace creation, selection, and file upload functionality.
  7. PDF Ingestion: Provided support for PDF uploads and ingestion using GCP BigQuery.
  8. Error Handling: Developed error-handling mechanisms to reduce unnecessary API calls and improve system efficiency.
  9. Chunking Support: Added chunking capabilities to show relevant content during queries.
  10. Delete Dataset and File Functionality: Implemented features to delete datasets and files from GCP storage.

Business Challenge

The primary business challenge was to develop a scalable, high-performance RAG system that could efficiently handle large datasets and provide accurate LLM responses. This involved creating a seamless integration between Google Vertex AI and BigQuery while maintaining real-time processing capabilities and minimizing operational costs associated with API calls.

Technical Challenges

The technical challenges included ensuring smooth integration between multiple platforms (Google Vertex AI, OpenAI, and BigQuery) and managing large volumes of data while maintaining performance. Further challenges arose with the implementation of streaming response mechanisms, database reset functionalities, and adapting the LangChain framework for indexing in BigQuery, which did not have native support for LangChain indices.