Retrieval-Augmented Generation (RAG)

-

Retrieval-Augmented Generation (RAG)





Introduction

Retrieval-Augmented Generation (RAG) is a method/approach that basically enhances LLMs (Large Language Models). It extracts relevant information from external sources such as databases, APIs, Documents etc. before providing any response.






Uses of RAG





LLMs are limited to training data only and there are high chances that it may provide outdated or incorrect information. Well, worry not, RAG is there for rescue. 
RAG solves this by extracting the most recent and relevant data at query time, leading to more accurate, fact-based responses to the user. RAG improves LLMs by integrating external knowledge retrieval.

Let us see how RAG works

  • Retrieve: When a user asks a question, the system fetches relevant documents or data.

  • Augment: The retrieved data is added as context for the LLM.

  • Generate: The LLM then generates a response using both its pre-trained knowledge and the retrieved context.


    • Example:

    Without RAG: 🤖 The president of Nepal is Bidya Devi Bhandari.
    With RAG: 🤖The president of Nepal is Ram Chandra Poudel.

    Note: Stay tune for example with codes

    Comments

    Post a Comment

    Popular posts from this blog

    ML concepts (Regression, Classification, Clustering)

    -
    Image
     ML concepts (Regression, Classification, Clustering) Part1 Regression Regression is a supervised Learning. It is a statistical technique used in machine learning to predict continuous values . It helps understand relationships between dependent and independent variables. Example: Imagine you are a real estate agent and want to predict the price of a house based on its size. You collect data on previous sales, including house sizes (independent variable) and their prices (dependent variable). By applying regression, you can find a mathematical relationship between these two and use it to predict the price of a new house based on its size. Types of Regression Linear Regression Multiple Linear Regression Polynomial Regression Ridge & Lasso Regression Logistic Regression (used for classification, not traditional regression)  Linear Regression This is the simplest form of regression where we fit a straight line to the data. The mathematical equation is:      ...
    Read more

    Pyspark Transformation and Actions

    -
     Pyspark Transformation and Actions RDD Transformation Examples Some of the examples of RDD transformations are: flatmap() map() reduceByKey() filter() sortByKey() RDD Actions Example some of the examples of RDD actions are: count() first() max() reduce() take() collect() lets us understand by code how RDD is fault tolerant, immutable, how lazy evaluation works and also understand its distributed nature. lets define a RDD , while converting a data to RDD, it is not directly loaded in memory, first of all  a lineage graph is made for the data, such that even if any node crashes in future, data can be recreated. This lineage graph helps in fault tolerance by allowing Spark to recreate lost data partitions in case of any reason causing node failure. RDDs are distributed across multiple nodes in a cluster, allowing parallel processing of data records. rdd = sc.parallelize([ 1 , 2 , 3 , 4 , 5 ]) the immutability nature of RDD can be understand such that, notice now we didnt changed...
    Read more