Cosine Similarity
cosine similarity is used in computer science to group data, or to find data as a response to a query.
it is the cosine of the angle between two vectors.
if the angle is 90, cos(90) = 0 - not similar
if the angle is 0, cos(0) = 1 - same
if the angle is 180, cos(180) = -1 - opposite
To compare two sentences, you need to find the cosine similarity between the numerical representation of the two sentences. Embeddings are numerical representations of words or sentences. Embedding models are offered by OpenAI, Cohere, etc. Their apis take a sentence and return the embeddings.
59 views
Comments
Participate in the conversation.
Never miss a post from
Satyajeet Jadhav
Get notified when Satyajeet Jadhav publishes a new post.
Read More
Embeddings eli5 version
Computers don’t understand text like humans do. Computers understand numbers.To get computers to understand text, you need to convert the text to numbers.
Retrieval Augmented Generation (RAG) on Postgres
So I recently learnt that Postgres works quite well for RAG Applications. Here is the flow I followed.
Semantic Search, aka Magic
The related notes feature searches all your notes to find the ones that are closest in meaning to your current note.Searching notes to find text similar in meaning to your query is called semantic search. We are trying to build a semantic search engine.
Repetition
A wise friend once pointed out that a repetitive pattern is one of the fundamental blocks of art.
The laws of psychology in marketing
A short story from the book, Alchemy:
On satisficing — a bet on human irrationality
When consumers can’t determine the optimal solution, they give a brand the power of their decisions. It’s why many choose Apple, because they’ve abrogated the rationality of choice. This has to be viewed with care though. The corollary of it is valid too. Think about the below st...