Nya is so, so dear to me. She is incredibly frail and keeps going because there are orphans she’s looking after that need food. Her parents have mobility impairments, making her rent for their room every month extremely pressing.

I think she doesn’t get much support because she refuses to violate her family’s privacy & dignity by sharing photos. But this is a real family, I promise.

Anything helps. Please help. https://chuffed.org/project/help-a-family-of-8

#MutualAid #MutualAidRequest #Gaza

I found a Scarlet Lichen Moth this morning. Such a gorgeous moth.

#nature #wildlife #moth #Lepidoptera

Gaza is burning and so is Raytheon, allegedly.

Activist in Canada this passed week took credit for starting a fire in a Raytheon warehouse and posted this video online.

What a tragic loss of windows and genocide weapons.

#Canada #FreeGaza #Raytheon #calgary

Look. Nya was just 38 kg in March—before the occupation resumed its aggression. She recently wrote to me:

“We are completely broken inside.”

This is my beloved friend. My dear sweet friend. And this starving woman is responsible for her whole family, including young kids & a baby. They haven’t eaten in days.

Anything helps. Click “weekly” or “monthly” to stand by her: https://chuffed.org/project/help-a-family-of-8

#MutualAid #MutualAidRequest #Gaza

Hello friends! It is my birthday soon, I would love nothing better than to
ensure Mohammed can feed himself & his family:
https://chuffed.org/project/118369-help-mohammeds-family-bear-the-heavy-burdens-of-life-in-gaza
[https://chuffed.org/project/118369-help-mohammeds-family-bear-the-heavy-burdens-of-life-in-gaza]

1kg of lentils cost $26 in Gaza, 1L cooking oil is $23. There is very little aid
coming in and whatever is coming in is being stolen and sold for inflated
prices. Only cash is accepted and the cost to convert donations into cash is
~38% of the money.

LLMs don’t know your PDF.
They don’t know your company wiki either. Or your research papers.

What they can do with RAG is look through your documents in the background and answer using what they find.

But how does that actually work? Here’s the basic idea behind RAG:
 Chunking: The document is split into small, overlapping parts so the LLM can handle them. This keeps structure and context.
 Embeddings & Search: Each part is turned into a vector (a numerical representation of meaning). Your question is also turned into a vector, and the system compares them to find the best matches.
 Retriever + LLM: The top matches are sent to the LLM, which uses them to generate an answer based on that context.

#llm #largelanguagemodel #ai #ki #rag #tech #technology #vector #datascience #vectorsearch #vector #machinelearning