DBA Advice

🔥 THIS IS A BIG DEAL 🔥 I've been working on this for MONTHS & it's finally live! What could you create if you had 30 min to plan + 4 hrs to build? @lizziepika, @chancethedev, @jherr, & I decided to find out w/help from @crtr0 filmed IN PERSON in my PDX studio (link in thread)

Can your vector database index - All of Wikipedia? - On a laptop? - In under 6h? - Without compromising accuracy? JVector can. Article and live demo links in thread.

⭐️How Physics Wallah Uses LangChain, DataStax Astra DB, Vector Search and RAG to Revolutionize Education Physics Wallah built an AI Guru - a personalized AI tutor application, to assist students with their academic and support queries. datastax.com/blog/how-physi…

@AnasRzaa Give Astra DB a try. The free tier allows Up to 80GB storage and 20 million read/write operations (using free $25/mo credit). It's built on Cassandra so it has the latency, availability and scalability requirements you'd expect/need for a Gen AI app.

ChromaDB, pinecone, GCP Vector Search, pgvector. In this tutorial, I explain how you can set up `pgvector` with PostgreSQL and test it in Python. Do share your wonderful feedback. :-) anas-rz.medium.com/getting-starte…

Excited to share my tutorial: Getting Started with Vector Databases with pgvector and Python. Vector databases can be used for many important tasks including Retrieval Augmented Generation (RAG), and Image Similarity Search. Popular options for vector databases include ....

@Shavtge Give Astra DB a try. The free tier allows Up to 80GB storage and 20 million read/write operations (using free $25/mo credit). It's built on Cassandra so it has the latency, availability and scalability requirements you'd expect/need for a Gen AI app.

Redis might surprise some as a viable vector database option, given its key-value store reputation, but it's undoubtedly fast. #Redis redis.com/solutions/use-…

Vector databases are crucial for storing dense vectors and advanced similarity search. Each has unique features suited for different needs. Incredibly useful, but also numerous (we have >20 to choose from...) so let's compare some! #VectorDatabases #AI #DataStorage

@AstraDB Cassandra-based Vector DB 🌌 Explore the langchain-astradb integration package! Harness the serverless, vector-capable database built on Apache Cassandra for scalable NoSQL solutions enhanced with the power of vector similarity search. python.langchain.com/docs/integrati…

@nyike Interesting article! You forgot to mention Astra DB on your list of DBs with Vector capabilities. Check them out astra.datastax.com!

What are vector dbs? Vector databases and vector search are the two primary platforms developers use to convert unstructured information into vectors, now more commonly called embeddings. #AI #LLM #Data infoworld.com/article/370991…

@ClementDelangue It'll be mixed! Firms are struggling to figure out the right AI budget balance right now. Hard to prove a lot of ROI and efficiencies that are being promised with such a new technology. Once companies see some of those proof points, I expect budgets to change quickly.

Can AI cloud spend be bigger than software cloud spend in 5 years?

Great chat on vector databases and the future of #GenAI apps! Be sure to follow these fantastic handles/brands below @DataStaxDevs, @erickramirezau, @thenewstack, @llama_index, @langchain, @ChetKapoor, @edanuff, @mgrygles, @linuxfoundation, @PatrickMcFadin, @APloetz, @engineeringcom, @jeremya_real, @InnoNewsNetwork, @cassandra, @yi_ding, @RavitJain, @superagent_ai, @domlovesai, @osd_podcast, @spyced, @langstream_ai, @karinwolok, @ABridgwater, @ania_kubow, @twimlai, @cbornet_, @SiliconANGLE, @skypointcloud, @tjake, @crtr0, @BlocksandFiles, @VentureBeat, @FlowiseAI, @vercel, @hackernoon, @SanjMo, @samuelmatioli, @jscarp, @toVitaly, @DBAdvice123, @dhinchcliffe, @gigaom, @TonyBaer, @rwang0, @AndyThurai, @IrmaRaste, @DataRobot

@lionbloggertech You missed Astra DB! Astra.datastax.com

The Power of Vector Databases for AI & Machine Learning lionbloggertech.com/the-power-of-v… #ArtificialIntelligence #MachineLearning #Milvus #Pinecone #VectorDatabase #Weaviate

@lewiswalkerai Awesome. Thank you! I found this article to be helpful as well hackernoon.com/need-more-rele…

This paper explores 32 techniques to mitigate hallucinations in LLMs 🧠💭 It considers techniques such as Retrieval Augmented Generation (RAG) and Knowledge Retrieval, with a specific emphasis on dataset utilisation, tasks, and feedback mechanisms. #ai #rag

@knajjars Astra DB - astra.datastax.com It's powered by Cassandra, so you'll gain scalability, reliability, and ultra-low latencies that come with C*. They've also got a solid free tier for you to test.

what is a good vector database? Trying pinecone right now, but running into some basic limitations with the free version and there is no self hosting

@bindureddy I used this short article to help me determine if RAG or Fine Tuning is the answer. thenewstack.io/fine-tuning-is…

RAG Or Fine-Tuning? There is a lot of confusion about when to apply which method. RAG makes sense when you have a custom knowledge base and want a standard ChatGPT-like interface on top of it. RAG has multiple components to it and can be tricky to get right. However, it's definitely easier to implement than fine-tuning. Fine-tuning makes sense when you have several supervised examples of request responses and are looking for a particular format for your responses. That is if you want the model to adapt to a particular type of response. For example, you can fine-tune a model to be good at a specific type of SQL code generation. Sometimes, but not often, it makes sense to do both. Using something like Abacus AI makes applying either method on open-source and closed-source LLMs super simple. Of course, we are particularly partial to open-source, especially if it can do the job!

@kaarthikcodes @MistralAI @togethercompute @CloudflareDev @langchain @nextjs Give Astra DB a try! It could cover both your DB and Vector Search layers. Astra.datastax.com

The LLM stack that I am currently testing - Model - @MistralAI MoE Inference - @togethercompute Vector DB - @CloudflareDev Vectorize Caching - @CloudflareDev KV Database - @CloudflareDev D1 Document Loaders - @langchain Hosting - @CloudflareDev Framework - @nextjs

@Irshit_dev_exp Hi There! Super interesting space. I use Astra DB to run my Gen AI applications. You should check it out! The free tier is nice and the UI is super easy to use. astra.datastax.com

Recently, I've been learning about vector embeddings and how to execute queries within a vector database—it has been quite an enjoyable experience. I specifically delved into PineconeDB and gained valuable insights. #vectordatabase #pineconedb

Looking at Pinecone? You should read this first. DataStax Astra DB outperforms Pinecone in 4 areas: throughput, response time, F1 relevancy, and total cost of ownership. GigaOm study: gigaom.com/reprint/vector…

@ThawabHAlsubaie @skalskip92 @ClementDelangue DataStax created a service in Astra that has the same API endpoints and does the same things, except it doesn’t have to use OpenAI, and, most importantly, it stores all of the data for these API calls in Astra. Announcement Blog: datastax.com/blog/introduci…

@skalskip92 @ClementDelangue My bet is on the vector database companies. Can’t see how they can survive after openai supported uploading custom data.

Six predictions for AI in 2024: - A hyped AI company will go bankrupt or get acquired for a ridiculously low price - Open-source LLMs will reach the level of the best closed-source LLMs - Big breakthroughs in AI for video, time-series, biology and chemistry - We will talk much more about the cost (monetary and environmental) of AI - A popular media will be mostly AI-generated - 10 millions AI builders on Hugging Face leading to no increase of unemployment

@Theater_Dev Here you go. Won't take all day and you can learn from a different angle: youtube.com/watch?v=PR7xz5…

@ChrisDzoba I've been using Astra. The quickstart here is helpful and the developer experience preview in Astra makes everything much easier to use. docs.datastax.com/en/astra-serve…

Are there any really good vector search -> RAG learning resources?

@VikramSubrama11 @OpenAI @pinecone @milvusio @trychroma Check out Astra DB! It works in conjunction with Open AI - datastax.com/blog/getting-s…