📋
Philanthrolab
  • Philanthrolab Technical Docs
  • SSN Component Library
  • Datalabs
    • Introduction
    • Architecture
    • Schema Dictionary
    • Project Status/Timeline
  • Social Safety Network
    • Introduction
    • Architecture
    • Schema Dictionary
    • Project Status/Timeline
      • V1
      • V2
  • SSN for Organisations
    • Introduction
    • Features and user stories
    • Architecture
    • Schema Dictionary
    • Project Status/Timeline
  • Developer Resources
    • Frontend Project Guide
    • Coding Guide
    • Creating a Neo4j instance on GCP vm
    • Set up local deploy for staging and production envs
    • Install ElasticSearch on GCP
    • ElasticSearch Query
    • ETL Strategy for Neo4j Database: Scraping, Transformation, and Enrichment
    • ETL Checklist
  • SSN Authentication
    • Introduction
    • Architecture
    • Schema
  • SSN Admin Dashboard
    • Introduction
    • Architecture
  • SSN Job Board
    • Introduction
    • Architecture
    • User Stories
    • Schema Dictionary
  • SSN Eligibility criteria AI feature
    • Introduction
    • Working Principles
    • Architecture
    • Schema Dictionary
  • DataBase Repopulation
    • Introduction
    • Proposed Solution
    • DB Details
    • Batch 1
  • LLM INTEGRATION
    • LLM Strategy and Implementation
Powered by GitBook
On this page
  • Background
  • Purpose of the document
  • Flow
  • Expected Outcome
  • Guide

Was this helpful?

  1. LLM INTEGRATION

LLM Strategy and Implementation

PreviousBatch 1

Last updated 11 months ago

Was this helpful?

Background

We aim to provide the best experience for those seeking public health information on services and organizations offering them. Utilizing a , we hope to achieve chat and speech functionality to provide better contextual results and feedback to our users.

Purpose of the document

This document serves as a comprehensive guide, outlining our strategic approach to implementing LLM.

Flow

We are optimizing our search functionality by adding an LLM layer between the client and the data on our knowledge graph. This layer would handle embedding and parsing the response retrieved. The ideal flow is:

  • The client sends the request with the query value.

  • The LLM layer embeds the query: turning it into a vector.

  • Our algorithm compares the data in our knowledge graph, ordering based on relevance - distance between the vectors.

  • The LLM layer converts the data back into natural language.

  • The client displays the result to the user.

Expected Outcome

Guide

Have Voice search and feedback implemented: using

We will be using the course for the implementation.

https://elevenlabs.io/
Neo4j & LLM Fundamentals
Large Language Model
Ideal flow of search request and response