Fine-tuning can work wonders — but only within the bounds of a model's inherent intelligence. This guide explores when a model is too small to meet your task’s quality requirements and how to tell if you've hit that limit.
This document outlines practical applications where either Retrieval-Augmented Generation (RAG), fine-tuning, or both are best suited. It also includes a rough cost breakdown to help with planning.
- Why RAG: Fetch live policy, FAQ, or documentation.
Choosing between RAG (Retrieval-Augmented Generation) and fine-tuning depends on your use case, data type, infrastructure, and latency/accuracy needs. This guide helps you understand when to use each technique.
You change the model itself.
- Analyzed and documented the agent code and its flow
- Examined the utility profit API
- Developed hypothetical flow for data acquisition
- Executed various curl requests to test endpoints
- Created automation script for initial flow
- Combined actual data with mocked data to produce sample JSON in required format
This document illustrates the flow of data through the Utility Profit Consolidated Workflow API, from initial user input to final consolidated output. The diagrams and explanations provide a visual and textual representation of each step in the process.
graph TD
A[User/Client] --> B[API Endpoint]
B --> C{Validation}
Below are the schema diagrams for the Superyacht Technology Platform's database, visualized using Mermaid. Each diagram represents the structure of the main entities as described in the technical documentation.
classDiagram
class User {
+String email
- Step 1: Use MongoDB to store technology data as per the
Technology Schema
provided. - Step 2: Develop a React component
<TechnologyBrowser>
to display technologies with filters usingTechnologyFilters
component. - Step 3: Implement API endpoints like
GET /api/technologies
to fetch technology data with query parameters for filtering.