Chandrayaan-3 Mission:
'India🇮🇳,
I reached my destination
and you too!'
: Chandrayaan-3
Chandrayaan-3 has successfully
soft-landed on the moon 🌖!.
Congratulations, India🇮🇳!
#Chandrayaan_3#Ch3
Create Your Own Custom LLM Chatbot
Impressive step-by-step tutorial explaining how to choose the best LLM and the components needed for building your own custom LLM-powered chatbot.
@abacusai offers one of the best solutions that I've used to quickly build custom LLM chatbots.
The foundational parts discussed in the tutorial are:
• Data sources - data warehouses, data lakes, and a range of databases are supported. You can also transform data within the platform as needed. There is even an AI agent that can assist with operating on data.
• Chunk size - the chunk size determines how to split the text; this affects performance and varies by use case. You should also think about the overlap between adjacent chunks so information is not abruptly cut off.
• Embedding technique and document retriever - the chunks of texts are embedded and stored in a vector database that helps you build a powerful retriever that the LLM interacts with to ensure it's using the relevant information to answer questions. This is particularly useful for a lot of knowledge-intensive use cases.
• LLM - the synthesizing capabilities of LLMs combined with the retrievers enables a robust solution to create your custom LLM chatbots and pick the best LLM for your dataset and task. With @abacusai you can choose between models offered by Google, OpenAI, Anthropic, the open-source community, and Abacus's proprietary LLMs. I like that you can also fine-tune your own models as well so the offering is pretty comprehensive.
• Automation and Evaluation - picking the right model and the right configurations is challenging. The AutoML capabilities of Abacus help in this regard. You can also upload an evaluation dataset that enables the platform to compare combinations and determine an optimal solution for your use case. Metrics include BLEU score, METEOR, and others.
• Deployment & Monitoring - this whole process is iterative in nature and new data will always be available. You can deploy your LLMs and set up pipelines to keep incorporating or fine-tuning on new data. Having your solution in production means you need to continuously evaluate and monitor performance on a regular basis to ensure the solution doesn't deteriorate.
Read more here: https://t.co/WcQEbqtAZa
If there is enough interest, I will also be posting a full demo with a use case in an upcoming post. Stay tuned!
📣 Update on the name of Kotlin Multiplatform
From now on, “Kotlin Multiplatform” (KMP) is the preferred term when referring to the Kotlin technology for sharing code, regardless of the combination of platforms being discussed.
We are deprecating the “Kotlin Multiplatform Mobile” (KMM) product name to resolve the long-standing issues of naming inconsistency and abbreviation confusion that have puzzled many Kotlin developers over the past two years.
Kotlin Multiplatform is excellent for sharing code across multiple platforms, not just iOS and Android. It enables you to share code with desktop and server-side as well. Moreover, we are actively developing Kotlin/Wasm to facilitate modern web development with Kotlin Multiplatform. When used alongside Compose Multiplatform, which supports Android, desktop, iOS (Alpha), and web (Experimental), you gain more freedom and can opt to share 100% of your codebase – all in Kotlin.
@jetbrains aims to deliver further improvements for Kotlin Multiplatform and Compose Multiplatform, making this combo the ultimate choice for sharing code between platforms.
Learn more: https://t.co/8CPPHwcw4A
What should you never do in a pitch? What would his nickname be if it wasn’t Mr. Wonderful? Find out in this rapid fire Q&A with #SharkTank's @kevinolearytv and HBS's @RezaSatchu.
@shreyas Another framework that we use at Amazon is 5Qs:
1. Who is the customer?
2. What is the problem/opportunity?
3. What is the main customer benefit?
4. How do you know customers want this?
5. What is the customer experience?
#FIFAWorldCup fever has hit Kerala 🇮🇳
Giant cutouts of Neymar, Cristiano Ronaldo and Lionel Messi popped up on a local river ahead of the tournament.
12 days to go until #Qatar2022 🏆
“Building a company is like having a child: you nurture it, take care of it even when it will ruin you.” Here you see the raw emotion of the toll @tesla@SpaceX took for @elonmusk to make it what it is today. Never give up.
Flutter leadership team wants to answer your questions!
1⃣ Post your questions with #AskFlutter, give them a chance to prepare for you 😋
2⃣Tune in on March 3 during #FlutterEngage and watch their answers
👋
Apparently, this stream shattered all expectations. I can't say enough about the fantastic viewers we had today!
And we're coming back this Wednesday, 9am Pacific / Noon Eastern / 6pm CET. Watch for the announcement, soon!
#Flutter@FlutterDev @gdg @timothyjordan#Android
⭐ Testing app compatibility with @AndroidStudio is now easier than ever before!
See how you can run tests across multiple API levels and form factors to make sure that your app looks its best on all devices. #11WeeksOfAndroid
Learn how → https://t.co/JjmMcHj3Np