Mani Sarkar

Included in this article is the mention of vector databases. Unsurprisingly, Michael Stonebraker and Andy Pavlo feel there is not a need for vector-specific databases. They believe relational databases will adopt their features, which is already happening. Check out the details here: https://lnkd.in/gyq_4WjP

33

1 Comment

"...embeddings enable machine learning models to find similar objects." Read more of Gregory Hodum's article on embeddings https://lnkd.in/eFs6hhAP #ai #softwaredevelopment #embeddings #machinelearning

9

Multi-agent systems (MAS) are increasingly seen as a potential evolution beyond traditional #RPA. Check out what Waylay is doing - is this another signal of a rapid shift? Click here to learn more: https://lnkd.in/e5hst9SV #multiagents #smartagents #genai #ai #bot #customersupport #CCaaS #callcenter #contactcenter #services #fieldservice #fintech #insuretech #carrental Rajesh Iyer Werner Vogels Shankar Ramanathan Michael Dell Bill Coughran Johan Müllern-Aspegren Peter Zaffino McKeel Hagerty Evan Greenberg Alan Schnitzer Christopher Swift Thomas M. Siebel

9

5 Comments

Very insightful work by Anthropic’s interpretability team. And an amazing paper, with outstanding writing and figures. The idea is very simple: interpret LLMs by leveraging sparse autoencoders as surrogate models of the MLP of transformer blocks, which allow one to disambiguate the superposition of features captured by a single neuron. A simple idea, but a very careful and complex execution, as it is often the case in our line of work. The paper goes into many details and provide a large array of insights, although the gist of the implementation remains obfuscated due to the closed source nature of Claude. Too bad, because this is the kind of work that we need to better understand and eventually trust LLMs. This is demonstrated by the authors in the section ‘Influence on Behavior’, where they show that clamping some features to either high or low value during inference is “remarkably effective at modifying model outputs in specific, interpretable ways”. Hopefully this kind of work is going to be replicated and generalized to open-weights models, such that we have new ways to steer their behavior. https://lnkd.in/eVym7f_f #interpretability #xai #explainableai #steerableai #anthropic #claude #anthropic

3

Amazon Bedrock now supports compressed embeddings from Cohere Embed! 💡 Cohere Embed, a top text embedding model, is widely known for enhancing RAG & semantic search systems. The int8 and binary compressed embeddings now available empower developers and businesses to create more efficient #generativeAI applications without sacrificing performance. Explore more at: https://go.aws/4eBniXm #AWS ☁️

2

Heading into October🍂 - it's been quite a year for txtai. Just this year alone, txtai added: - llama.cpp support - LLM API support (i.e. OpenAI, Claude, Bedrock etc) - Graph RAG - Binary quantization and support for Matryoshka Embeddings - Postgres integration for all vector database components - Streaming LLM, Streaming RAG and chat message support - Significant text extraction improvements There's much more but these are the most crucial changes. It's hard to remember a time when txtai didn't have these features but it wasn't long ago! https://lnkd.in/dxWDeey

8

3 Comments

The final deep dive on change query support in the table formats is ready. This one covers Apache Paimon, focusing on understanding the change query support through the lens of its internals. https://lnkd.in/dFfM_8nA

28

AI data infrastructures are increasingly reliant on advanced storage solutions to manage the sheer volume and velocity of data processing demands, as highlighted in Stephen Foskett's article on Gestalt IT. Solidigm's contributions to the field, with their state-of-the-art storage technologies, underscore the necessity for innovation and scalability in supporting AI workloads. As AI applications continue to evolve, the selection of sophisticated, capable storage systems becomes a linchpin for the success and efficiency of AI-driven enterprises. This article brings together this entire series, sponsored by Solidigm.

3

🔢 Exciting new blog from Olly Britton, a #QuansightLabs summer intern! He's added support for multidimensional numerical integration of array-valued functions to SciPy. This fills an important gap in SciPy's integration toolkit! Read his about it here: 👉 https://lnkd.in/dNmHTX3G #OpenSource #Python #SciPy

13

Breadth vs depth? Support the maximum number of integrations or build a few deep and meaningful integrations? txtai has taken the depth approach to ensure that integrations it adds are performant and support a large number of the underlying libraries features. We're not into box checking. https://lnkd.in/dxWDeey

4

Interesting new open source Event processing platform from Microsoft. https://lnkd.in/gPr4Cifu The features that I am interested in are 1. It’s input schema is modelled on Debezium, another open source CDC product. 2. Enables action on an event 3. Write continuous queries using Cypher query lanaguage Combining such a powerful platform with a LLM would be sone pe suhaga (best of both worlds).

5

1 Comment

#RAG has fundamental limitations that prevent it from generating accurate answers for diverse queries on complex documents or on datasets at scale. Mehul Shah writes about the need for a new approach: LLM-Powered Unstructured Analytics. We call it LUnA, and this architecture is at the core of #Sycamore. Read about LUnA here: https://lnkd.in/gThndXVf #Sycamore #Aryn #Analytics #UnstructuredData #Search #GenAI

2

This article by Pere Martra explores a structured pruning technique for state-of-the-art models, that uses a GLU architecture, enabling the creation of smaller and more efficient large language models. #Llama #LLM

5

Here’s how you can use Gretel to create secure, synthetic versions of your sensitive data for training bespoke small language models tailored to specific business tasks. Design tabular datasets containing numeric, categorical, free text, JSON, and time-series data. https://lnkd.in/eAwcVWXv #SLM #Privacy #SyntheticData

5

Working with large language models has become a critical part of any data scientist’s or ML engineer’s job, and fine-tuning the large language models can lead to powerful improvements in the language models’ capabilities. Eivind Kjosbakken's article shows you how you can fine-tune Llama3.2 to improve its performance within a targeted domain. #LLM #Llama

13