Word embedding
66
MENTIONS
9
EPISODES
8
PODCASTS
Search complete. 66 mentions across 9 episodes found for "Word embedding".
Nov 18, 2026
The Complete Guide to HIPAA/GDPR-Compliant AI Inference: Self-Hosting Open-Source Models
S
1:27speaker_0NARRATOR
Retrieved context, retrieval augmented generation, or RAG, chunks of records pulled from your index often more sensitive than the prompt itself.
S
1:35speaker_0NARRATOR
Embeddings in vector databases' numeric versions of your documents' VEC2 text demonstrated exact recovery of 92% of 32 token inputs, including names from clinical notes.
S
1:46speaker_0NARRATOR
Queues and payload stores requests waiting for a GPU data at rest is usually not considered.
S
1:52speaker_0NARRATOR
Logs and traces full request bodies when debug logging is on ends up in a third-party log tool.
S
4:45speaker_0NARRATOR
If you already have a BAA with your cloud provider, self-hosting in that account adds no new vendor.
S
4:51speaker_0NARRATOR
Your agent needs features outside the BAA scope, batch jobs, file uploads, code execution.
S
4:58speaker_0NARRATOR
your policy says no retention and the covered option keeps data for 30 days eu data must stay in the eu there are also state laws like texas sb 1188 that limit where records can live volume is steady and high which open source inference servers can you self-host the short skimmable list tool best for limitations vllm high throughput llm serving with broad model support one model per server You build routing and auth around ITS GLang multi-turned chat, structured output, RAG with shared prefixes smaller ecosystem than VLL Malama local development and single-user setups not designed for multi-tenant production TEI Text Embeddings Inference Embeddings and Rerankers 1 model per server No generation TGI Text Generation Inference Existing deployments only put in maintenance mode by hugging FaceSci.
S
5:51speaker_0NARRATOR
Superlinked inference engine.
Mētis, WordPress's flagship theme
A
8:53Alicia IrelandHOST
RAG was also discussed.
A
8:57Alicia IrelandHOST
Embeddings are part of the 7.2 work, but there is no decision yet on whether RAG belongs in core or in plugins.
A
9:05Alicia IrelandHOST
On what will ship with WordPress 7.2, the group asks for continued testing of the Secrets API, especially on Multisite, preparing developer notes for the Abilities API before RC1, and more feedback on a change to Abilities permissions that, if it doesn't receive support, could be reverted.
A
9:23Alicia IrelandHOST
It was approved to move the shared abilities into their own Composer package within the WordPress organization on GitHub, so projects such as WooCommerce can use them without installing the entire AI plugin.
The Comings and Goings of an Important CEO Edition
J
74:48Jim HedgerHOST
Profile relevance model.
J
74:50Jim HedgerHOST
It's profile relevance model using LLM-generated embeddings to show users more relevant posts from people.
K
74:56Kristine SchachingerHOST
Wait, what was that? Embeddings?
J
75:00Jim HedgerHOST
It's using LLM-generated embeddings.
K
75:03Kristine SchachingerHOST
Nice.
ZeroEntropy with Ghita Houir Alami - Weaviate Podcast #150!
G
37:32Ghita Houir AlamiGUEST
For various reasons, I think you do need a mechanism on top of your initial first pass search.
G
37:41Ghita Houir AlamiGUEST
Embeddings are not going to be enough for the whole dimensionality problem, where if you're trying to encode information into like an embedding with like a certain number of dimensions, you can like prove like there were some papers about this as well.
G
37:58Ghita Houir AlamiGUEST
You can prove that, you know, you're never going to be able even for like a small K to retrieve all of the documents in the right order.
G
38:09Ghita Houir AlamiGUEST
And so having like a step after this is definitely necessary.
Build Real AI E11: Make the LLM Answer From Your Own Data (RAG, Simply)
O
4:09OliverHOST
There's one piece of quiet magic that makes the search work, and the word is less cold than it looks.
O
4:16OliverHOST
Embeddings.
O
4:18OliverHOST
Stay with me.
O
4:19OliverHOST
They're friendlier than the syllable.
How SaaS Wins in World of Agents with BOX CTO Ben Kus
B
22:18Ben KusGUEST
And that's always been a problem.
B
22:19Ben KusGUEST
And so then the really cool thing and the exciting thing is that the next generation of context retrieval, powered by some of the same technologies like vector embeddings and the ability to not just understand the lexical search capabilities but the semantic capabilities, like the meaning-based searches, this is now significantly improving.
B
22:39Ben KusGUEST
And so then the idea of can a person, or an agent in this case, find the data it needs It may be the key to unlocking the benefits that any company would have to be able to use agents effectively.
B
22:53Ben KusGUEST
And this is definitely an area that we're focused on.
B
23:14Ben KusGUEST
Now, the problem was, I mean, it was amazing.
B
23:15Ben KusGUEST
Here's 300 documents.
B
23:18Ben KusGUEST
chunk them up, find the most related paragraph using vector embeddings, and then give it to an agent, which is awesome.
B
23:25Ben KusGUEST
And when it works, it's great.
Stanford CS224N: NLP with Deep Learning | Winter 2021 | Lecture 1 - Intro and Word Vectors
C
1:40Christopher ManningHOST
I'll then introduce the ideas of the Word2Vec algorithm for learning word meaning, and then Going from there, we'll concretely work through how you can work out objective function gradients with respect to the word2vec algorithm and say a teeny bit about how optimization works.
C
1:58Christopher ManningHOST
And then right at the end of the class, I then want to spend a little bit of time giving you a sense of how these word vectors work and what you can do with them.
C
2:08Christopher ManningHOST
So really, the key learning for today is I want to give you a sense of how amazing deep learning word vectors are.
C
2:18Christopher ManningHOST
So we have this really surprising result that word meaning can be represented, not perfectly, but really rather well by a large vector of real numbers.
C
2:28Christopher ManningHOST
And that's sort of in a way a commonplace of the last decade of deep learning, but it flies in the face of thousands of years of tradition.
33 MINS LATER
C
35:50Christopher ManningHOST
And so they're actually then grouped close together to the verb to be.
C
35:54Christopher ManningHOST
So there's a lot of interesting structure in this space that then represents the meaning of words.
C
36:02Christopher ManningHOST
So the algorithm I'm going to introduce now is one that's called Word2Vec, which was introduced by Tamás Mikulov and colleagues in 2013 as a framework for learning word vectors.
Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 10 - Transformers and Pretraining
J
2:09John HewittHOST
But when we discuss pre-training, it's important to know that subwords are a part of it.
J
2:15John HewittHOST
Then we'll sort of motivate, we'll go on another journey of motivation of motivating model pre-training from word embedding.
J
2:21John HewittHOST
So we've already seen pre-training in some sense in the very first lecture of this course because we pre-trained individual word embeddings that don't take into account their contexts on very large text corpora and saw that they were able to encode a lot of useful things about language.
J
2:38John HewittHOST
So after we do the motivation, we'll go through model pre-training three ways.
J
2:42John HewittHOST
And we're going to reference, actually, the lecture on Tuesday.
11 MINS LATER
J
14:02John HewittHOST
So we never saw Tasty enough with however many As in order to add it into our subword vocabulary.
J
14:09John HewittHOST
But we're still able to split it into things.
J
14:11John HewittHOST
And then the neural network that runs on top of these subword embeddings could be able to sort of induce that, oh, yeah, this is one of those things where people chain letters together, chain vowels together in English for emphasis.
AI Coworkers How Intelligent Agents Are Changing Office Work
S
23:56speaker_6HOST
No.
S
23:57speaker_6HOST
It relies on vector embeddings.
S
23:59speaker_4HOST
So when we upload our internal company documents into a RAG system, a specialized embedding model reads all the text and converts every sentence into a coordinate in a massive multi-dimensional space.
S
24:10speaker_6HOST
Exactly.