Tech Ninja (@techninjahere) header
Tech Ninja (@techninjahere) profile picture

Life begins at the end of your comfort zone! OpenSource, Analytics & Cloud enthusiast | Voracious Reader

United States
Joined January 2012
Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)Photo by Tech Ninja (@techninjahere)
Nice initiative 🤩 Spring AI The Spring AI project provides a Spring-friendly API and abstractions for developing AI applications. Let's make your @Beans intelligent! github.com/spring-projects-e…
1
16
1
69
5,000
*Vector databases and why they matter in the LLM and Gen AI world* Large language models like GPT generally represent words and sentences as vectors or embeddings. Vector databases are nothing more than a database of these vectors and work hand-in-hand with Large Language Models (LLMs) specifically for enterprise AI use-cases. These embeddings capture the semantic meaning and allow models to understand "dog" and "puppy" are close to each other. Common AI use-cases for LLMs include enterprise search, chat on internal databases, summarization and key entity extraction. Operationalizing these use-cases involves a bunch of steps and includes Step 1 - Vectorizing the Knowledge - When you have a custom knowledebase (KB), the first order of business is translating every piece of information into a vector - a multi-dimensional mathematical representation of that information Step 2 - Storing and Searching the Vectors - Vector databases help you store and look up these vectors efficiently. Fundamentally, they enable you to find similar items based on a query vector. So you can easily perform searches for "like" or "close to" other words or phrases, at scale. Step 3 - Integration with LLMs - LLMs like GPT4, don't know have information from your custom knowledgebase, when a user sends a prompt/query, we first have to look-up the Vector database for the relevant piece of information For example, if you are looking for information to log-in to your internal HR system, and you ask your custom ChatBot, it needs to go to the vector database to first fetch the web page that has this information The custom ChatBot will then send this information to the LLM API (GPT-4) along with the user-query. The LLM API will then answer the user's question by reading the webpage about your internal HR system Step 4 - Orchestration and Operationalization - Now that we have responded to the first user query, the user may have follow-up questions or start a thread. Developers have to come up with the complex orchestration flow, where they keep state across chats, do multiple vector database look-ups and facilitate a smooth conversation The process of operationalizing all these steps and launching your custom ChatBot or LLM-based Enterprise AI use-case in production is often termed - LLM Operations or LLMOps You can use an end-to-end LLMOps platform to operationalize your use-case or build your own end-to-end system by using all the LEGO blocks such as vector databases, LLM APIs and kubernetes. Key resources: Open source vector databases chroma - trychroma.com/ milvus - github.com/milvus-io/milvus end to end - LLMops platform Abacus - abacus.ai pic credit and a good read - medium.com/thirdai-blog/unde…
9
147
6
668
121,971
Updated roadmap diagram!
1,503
5,530
1,192
21,754
Back by popular demand, we are holding our Biological Data Science Workshop virtually again, FOR FREE!! August 8-19. #datascience #biology #bioinformatics #AI #NSF #Drexel #RowanUniv #UChicago
84
1,272
58
3,361
Top revenue sources for tech firms: $AAPL, $AMZN, $BABA, $GOOGL, $META, $MSFT, and $TCEHY. 📊
6
63
3
259
btw these large scary math symbols are just for-loops
548
6,148
1,344
35,032
Tech Ninja retweeted
Data Engineering Technologies 2021 by @ninjaVijay link.medium.com/3yKT1Rysyib
1
1
When to use CPUs vs GPUs vs TPUs in a Kaggle Competition? towardsdatascience.com/when-…
1
4
5
Tech Ninja retweeted
This Sunday is my birthday! The best gift🎁 to me would be if you can watch this video and let me know what you think. youtube.com/watch?v=06-AZXmw… Lets you and I work to shift AI from Model-Centric toward Data-Centric AI development, which will help many teams.
89
149
26
1,323
"By using the learnings from the work between @Arm Mbed and @Arduino in the IoT space, we are investigating ways to get tinyML in the hands of more developers." https://xitter.cf/t.co/AFhCdTgrcd
26
85
The matrix A is invertible if and only if...
17
341
41
2,505
If you live in the US, Canada, Central/South America, or Western Europe and looking for a new opportunity, DM me. We have the need for developers and infra/ops engineers. Work remotely, choose how you want to be paid, and focus on having a quality of life. #golang
8
25
56
100 most influential people in #AI Honoured to be mentioned amongst @elonmusk @sama @an_open_mind @kaifulee @AndrewYNg @drfeifei @lexfridman @2morrowknight @karpathy @KirkDBorne @SpirosMargaris @SchmidhuberAI (...) Congrats to all inspiring minds 🧠🚀 > ow.ly/aLOb30rtBn9
3
21
1
49
Tech Ninja retweeted
Resist.
13
301
38
1,782
A Wholistic View of Continual Learning: arxiv.org/abs/2009.01797 If you're interested in Continual Learning and Active Learning, this paper comes with a neat taxonomy!
3
120
7
462
Tech Ninja retweeted
An empty calendar slot does not mean a person is free. Thank you.
2
8
3
70
Today at the airport a CISF officer asked me if “I am an Indian” when I asked her to speak to me in tamil or English as I did not know Hindi. I would like to know from when being indian is equal to knowing Hindi. #hindiimposition
7,579
7,982
2,307
33,051
Long ago I asked a Sr leader @ Google why Larry picked Sundar as CEO. Apparently it wasn't coz Sundar was smartest, most visionary etc. At one pt other leaders just couldn't agree w/ each other unless he was there to mediate. Low ego, high EQ is an under-rated leadership quality.
96
2,993
192
17,523
hash functions are amazing
26
449
11
2,121