31–40 of 113 posts
Earlier quoted context omitted.
Why not use Temporal? An example use with AWS Bedrock: https://temporal.io/blog/amazon-bedrock-with-temporal-rock-s...
Because when you see someone try and reinvent Erlang in another language for the Nth time you know you can safely ignore them.
Earlier quoted context omitted.
There isn't one. The real challenge for at scale inference is that the compute for models is too long to keep normal API connections open and you need a message passing system in place. This system also needs to be able to deliver large files for multi-modal models if it's not going to be obsolete in a year or two. I build a proof of concept using email of all things but could never get anyone to fund the real deal w…
Thanks. Could something like Kafka be used?
People really don't understand how much better LLM swarms get with more agents. I never hit a point of diminishing returns on text quality over two days of running a swarm of llama2 70Bs on an 8x4090 cluster during the stress test.
You would need something similar to, but better than, whatsapp to handle the firehose of data that needs to cascade between agents when you start running this at scale.
In the example folder they used qdrant as a vector database, why not use openai’s assistants api? The idea for a vendor lock solution is to make things simpler. Is it because qdrant is faster?
qdrant is part of the openai tech stack for their RAG solutions
Looks kinda poorly written: not even a single async present, print debugging, deepcopy all over the place. Such a shame that there's nothing to replace Langchain with other than writing it all from the ground up yourself.
> Such a shame that there's nothing to replace Langchain with other than writing it all from the ground up yourself.
Supports .NET, Java, and Python. Lots of sample code[0] and support for agents[1] including a detailed guide[2].
We use it at our startup (the .NET version). It was initially quite unstable in the early days because of frequent breaking changes, but it has stabilized (for the most part). Note: the official docs may still be trailing, but the code samples in the repo and unit tests are up to date.
Highly recommended.
[0] https://github.com/microsoft/semantic-kernel/tree/main/pytho...
[1] https://github.com/microsoft/semantic-kernel/tree/main/pytho...
[2] https://github.com/microsoft/semantic-kernel/tree/main/pytho...
There used to be another open-source agentframework by the same name, but it was for multi-agent simulations. For a moment I thought there was a new wave of interest in a deeper understanding of complex systems by means of modelling. https://en.wikipedia.org/wiki/Swarm_(simulation) https://www.santafe.edu/research/results/working-papers/the-...
I believe there is a new wave of interest in deeper understanding of complex systems through modelling and connecting with machine learning. I organized this conference on exploring system dynamics with AI which you can see most of the lectures here: https://youtube.com/playlist?list=PL6zSfYNSRHalAsgIjHHsttpYf... The idea was to think about it from different directions including academia, industry, and education. Nob…
As-is, it's hard to skim the playlist, and likely terrible for organic search on Google or YouTube <3
There's absolutely nothing new in this framework that you won't find in a dozen other agent frameworks on github.
Looks kinda poorly written: not even a single async present, print debugging, deepcopy all over the place. Such a shame that there's nothing to replace Langchain with other than writing it all from the ground up yourself.
OpenAI's code quality leaves to be desired, which is surprising considering how well compensated their engineers are. Their recent realtime demo had so many race conditions, function calling didn't even work, and the patch suggested by the community hasn't been merged for a week. https://github.com/openai/openai-realtime-api-beta/issues/14
Do they use their own product?
Earlier quoted context omitted.
Thanks. Could something like Kafka be used?
You could use messenger pigeons if you felt like it. People really don't understand how much better LLM swarms get with more agents. I never hit a point of diminishing returns on text quality over two days of running a swarm of llama2 70Bs on an 8x4090 cluster during the stress test. You would need something similar to, but better than, whatsapp to handle the firehose of data that needs to cascade between agents when…
Could you elaborate please ?
One use for swarms is to use multiple agents/prompts in place of one single agent with one long prompt in order to increase performance by splitting one big task into many. It is very time consuming though, as it requires experimenting to determine how best to divide one task into subtasks, including writing code to parse and sanitize each task output and plug it back into the rest of the agent graph.
Dspy [1] seems to target this problem space but last time I checked it only focused on single prompt optimization (by selecting which few shots examples lead to the best prompt performance for instance), but even though I have seen papers on the subject, I have yet to find a framework that tackles the problem of agent graph optimization although research on this topic has been done [2][3][4]
[1]DSPy: The framework for programming—not prompting—foundation models: https://github.com/stanfordnlp/dspy
[2]TextGrad: Automatic 'Differentiation' via Text -- using large language models to backpropagate textual gradients: https://github.com/zou-group/textgrad
[3]What's the Magic Word? A Control Theory of LLM Prompting: https://arxiv.org/abs/2310.04444
[4]Language Agents as Optimizable Graphs: https://arxiv.org/abs/2402.16823