LogoLogo
👋 Get in touch⭐️ GitHub
  • Welcome
  • Getting Started
    • Why Superlinked?
    • Setup Superlinked
    • Basic Building Blocks
  • Run in Production
    • Overview
    • Setup Superlinked Server
      • Configuring your app
      • Interacting with app via API
    • Supported Vector Databases
      • Redis
      • Mongo DB
      • Qdrant
  • Concepts
    • Overview
    • Combining Multiple Embeddings for Better Retrieval Outcomes
    • Dynamic Parameters/Query Time weights
  • Reference
    • Overview
    • Changelog
    • Components
      • Dag
        • Period Time
      • Parser
        • Json Parser
        • Dataframe Parser
        • Data Parser
      • Schema
        • Id Schema Object
        • Schema Object
        • Schema
        • Event Schema Object
        • Event Schema
      • App
        • App
        • Interactive
          • Interactive App
        • Online
          • Online App
        • Rest
          • Rest App
        • In Memory
          • In Memory App
      • Space
        • Custom Space
        • Exception
        • Has Space Field Set
        • Number Space
        • Image Space Field Set
        • Text Similarity Space
        • Input Aggregation Mode
        • Image Space
        • Recency Space
        • Space Field Set
        • Categorical Similarity Space
        • Space
      • Executor
        • Exception
        • Executor
        • Interactive
          • Interactive Executor
        • Rest
          • Rest Descriptor
          • Rest Handler
          • Rest Executor
          • Rest Configuration
        • In Memory
          • In Memory Executor
        • Query
          • Query Executor
      • Registry
        • Superlinked Registry
        • Exception
      • Storage
        • Mongo Db Vector Database
        • Vector Database
        • Redis Vector Database
        • In Memory Vector Database
        • Qdrant Vector Database
      • Index
        • Effect
        • Index
        • Util
          • Aggregation Node Util
          • Event Aggregation Node Util
          • Event Aggregation Effect Group
          • Effect With Referenced Schema Object
          • Aggregation Effect Group
      • Source
        • Data Loader Source
        • Interactive Source
        • Types
        • In Memory Source
        • Source
        • Rest Source
      • Query
        • Param
        • Typed Param
        • Query
        • Query Weighting
        • Query Descriptor
        • Nlq Param Evaluator
        • Space Weight Param Info
        • Query Param Information
        • Query Filters
        • Nlq Pydantic Model Builder
        • Clause Params
        • Param Evaluator
        • Query Mixin
        • Query Param Value Setter
        • Query Filter Validator
        • Natural Language Query Param Handler
        • Query Filter Information
        • Query Vector Factory
        • Query Clause
        • Result
        • Query Result Converter
          • Default Query Result Converter
          • Query Result Converter
          • Serializable Query Result Converter
        • Predicate
          • Binary Op
          • Query Predicate
          • Binary Predicate
        • Query Clause
          • Similar Filter Clause
          • Overriden Now Clause
          • Looks Like Filter Clause
          • Space Weight Map
          • Nlq System Prompt Clause
          • Nlq Clause
          • Radius Clause
          • Weight By Space Clause
          • Base Looks Like Filter Clause
          • Limit Clause
          • Select Clause
          • Looks Like Filter Clause Weights By Space
          • Single Value Param Query Clause
          • Hard Filter Clause
          • Query Clause
        • Nlq
          • Nlq Compatible Clause Handler
          • Exception
          • Nlq Clause Collector
          • Nlq Handler
          • Suggestion
            • Query Suggestion Model
            • Query Suggestions Prompt Builder
          • Param Filler
            • Query Param Model Validator
            • Query Param Model Validator Info
            • Query Param Model Builder
            • Query Param Prompt Builder
            • Nlq Annotation
            • Templates
  • Recipes
    • Overview
    • Multi-Modal Semantic Search
      • Hotel Search
    • Recommendation System
      • E-Commerce RecSys
  • Tutorials
    • Overview
    • Semantic Search - News
    • Semantic Search - Movies
    • Semantic Search - Product Images & Descriptions
    • RecSys - Ecommerce
    • RAG - HR
    • Analytics - User Acquisition
    • Analytics - Keyword Expansion
  • Help & FAQ
    • Logging
    • Support
    • Discussion
  • Policies
    • Terms of Use
    • Privacy Policy
Powered by GitBook
On this page

Was this helpful?

Edit on GitHub
  1. Tutorials

RAG - HR

Learn about fundamental concepts of Superlinked.

Many companies aim to make HR documents more accessible to employees and contractors. A recent promising approach is building a RAG system on top of HR documents. This is because it

  • provides a unique response to any query,

  • reduces hallucinations as the answer has to be grounded in the retrieved context,

  • makes the process highly scalable due to automatic question-answering.

However, this solution possesses its unique challenges. For example

  • keeping the knowledgebase consistent and up-to-date,

  • running LLMs efficiently,

  • ensuring the generated results are correct and aligned with company communication guidelines,

In our case, we have three HR policy sources for our hypothetical company.

  1. An older HR policy, which contains our maternity leave policy and details on manager responsibilities.

  2. A more recent update, that contains inaccurate information on management responsibilities - but one that also contains unique information on paternity leave.

  3. A newer policy document that contains updated information about management responsibilities, correcting the mistakes of the previous modernising attempt - alongside some other HR policy information.

A good system will be able to:

  • provide relevant information on maternity leave (only covered in the old document),

  • synthesize contradicting information and only present to us the correct ones

Regarding synthesizing information, there are contradictions between the documents pertaining to management responsibilities. We are going to use the

  • creation_date of the policy,

  • and the usefulness score of each paragraph

as a proxy to know for similar documents with

  • similar information but different wording, and some important parts slightly altered, or

  • also talking about seemingly the same topic, but without conveying useful information

which one is more relevant to our query.

Follow along in this Colab

PreviousRecSys - EcommerceNextAnalytics - User Acquisition

Last updated 8 months ago

Was this helpful?

Google Colab
Logo