#RAG is no longer just about retrieval- it's about smart, self-improving intelligence!
We were all so excited when RAG was first introduced. We still are, this is never ending. I mean, RAG will still remain relevant for atleast a year from now (just my opinion).
So, RAG was first introduced by Meta AI researchers in 2020 through their paper — Retrieval-Augmented Generation for Knowledge-Intensive NLP Task— to address those kinds of knowledge-intensive tasks.
We saw a surge of simple to advanced RAG chatbots which is now taken over by AI agents:)
Coming to over RAG evolution over time. It all started with simple naive approach to retrieve contextually relevant responses/info and then moved on to what we call today corrective RAG.
While Standard RAG enhances response accuracy by retrieving and incorporating relevant documents into the generative process, Self-reflective RAG improves upon this by having the model assess its own outputs, tagging retrieved documents as relevant or irrelevant, and adjusting its responses accordingly.
Corrective RAG takes this a step further by using an external model to classify retrieved documents as correct, ambiguous, or incorrect, allowing the generative model to correct its answers based on this classification.
Together, these approaches represent increasing levels of refinement and accuracy in generating reliable responses.
Long live RAG!
Here is my hands-on video on RAG: https://lnkd.in/gsz_cXfv
Hey, here is my article on RAG you might like: https://lnkd.in/g7XUj-DD
Gen AI apps developer
3moApps-Script in a Google Sheet: function Do_Get_Emotions(nlpText) { doEmotionNlp = Get('doEmotionNlp') if (!doEmotionNlp) { return; } emotionsModel = Get('EmotionsModel') if (emotionsModel) { SelectGPTApi(), model = 'gpt-4o' } else { SelectTogetherApi(), model = 'meta-llama/Llama-3-70b-chat-hf' } //START PROMPT ENG emotions = 'Emotions are complex psychological and physiological states involving personal feelings, physical reactions, and behavioral expressions, triggered by specific stimuli or situations. They play a crucial role in decision-making and social interactions, influenced by how we perceive and interpret events.' prompt = 'Perform a Sentiment Analysis and extract any emotions found in this text: ' + nlpText + '. Ensure that each extracted emotion conforms to this definition of an emotion: ' + emotions + '\nAnalise the PROMPT and RESPONSE seperately. Categorise these sentiments and emotions as Positive, Neutral or Negative. Present the results without additional information by PROMPT and RESPONSE as a list with each item on a new line seperated by a comma and space showing Category, the Emotion name and Sentiment and assign a value to the Sentiment with 2 decimal places. //END PROMPT ENG