🧠 Problem: Too much data for embedding? 🤯🧩 Solution: Chunk your data! ✂️
7 102
3.4
Google Cloud Platform1.34 млн
Следующее
27.02.25 – 1 2587:52Популярные
89 дней – 13 02339:27
118 дней – 8416:36Опубликовано 27 февраля 2025, 14:00
A core principal of RAG is to search through your data to use as an input for LLMs. You can embed the data into a vector so it is searchable, but if you have a large video or entire book that will be too much data in one embedding.
Let's talk about some strategies for chunking your data for using with embedding models.
#AI #RAG #embedding #LLMs #VectorSearch #NLP #Firestore #VertexAI #Google #GoogleCloud #Tech #ComputerScience #Engineering
Let's talk about some strategies for chunking your data for using with embedding models.
#AI #RAG #embedding #LLMs #VectorSearch #NLP #Firestore #VertexAI #Google #GoogleCloud #Tech #ComputerScience #Engineering
Свежие видео
1 день – 2 8840:15
1 день – 19 9930:55
2 дня – 38 6079:33
5 дней – 60:15
5 дней – 20 2972:55
9 дней – 505 2080:31Случайные видео
183 дня – 5 7940:20
329 дней – 734 7241:02
14.01.25 – 4 6050:13
21.06.24 – 4471:00
14.10.23 – 9 4900:32
18.05.16 – 450 0426:25
5 дней – 20 5920:48
10 дней – 10 0830:16
11 дней – 025:34
11 дней – 1 9060:19
14 дней – 1652:21
22 дня – 10 9411:03