Apache Burr (incubating)

51 posts

Apache Burr (incubating)

Apache Burr (incubating)

@burr_framework

OS framework to build applications that make decisions: chatbots, agents, simulations, etc. Monitor, trace, persist, & execute in #python. Run by @TheASF

加入时间 Ağustos 2024
46 关注65 粉丝
Apache Burr (incubating) 已转推
Stefan Krawczyk
Stefan Krawczyk@stefkrawczyk·
Things I hear in private circles: "even the CEOs of @langchain and @llama_index say there is little value in abstracting over LLM API calls". If you haven't been following Apache @hamilton_os or Apache @burr_framework that's exactly what we've been saying for years -- you need to own the LLM call -- why? because customization here is what is going to deliver value, not the POC you threw together with those overly abstract VC backed frameworks. Plug (1): building on Apache Hamilton &/or Apache Burr is a better investment because you can drive the direction. Plug (2): @hugobowne and I cover this our @MavenHQ course -maven.com/s/course/67c6a…
English
0
3
5
594
Apache Burr (incubating) 已转推
Chip Huyen
Chip Huyen@chipro·
My 8000-word note on agents: huyenchip.com//2025/01/07/ag… Covering: 1. An overview of agents 2. How the capability of an AI-powered agent is determined by the set of tools it has access to and its capability for planning 3. How to select the best set of tools for your agent 4. Whether LLMs can plan and how to augment a model’s capability for planning 5. Agent’s failure modes AI-powered agents are an emerging field with no established theoretical frameworks for defining, developing, and evaluating them. This post is a best-effort attempt to build a framework from the existing literature, but it will evolve as the field does. As always, feedback is much appreciated!
English
51
449
2.8K
362.3K
Apache Burr (incubating)
Apache Burr (incubating)@burr_framework·
@braelyn_ai Once you get into CI build systems, it's very easy to rack up downloads. E.g. someone puts in a PR, it triggers a CI run that downloads the library fresh. Boom lots of downloads.
English
0
0
1
380
Braelyn ⛓️
Braelyn ⛓️@braelyn_ai·
whats the most used agent framework? i wanted to know so i made this graphic i was really surprised by how much github stars are lying can anyone explain to me how langgraph has SO many more downloads than stars? or why autogen is far in the lead on stars but nearly no downloads???
Braelyn ⛓️ tweet media
English
41
40
343
84.2K
Apache Burr (incubating) 已转推
Stefan Krawczyk
Stefan Krawczyk@stefkrawczyk·
Super excited for this post by @thierryjean that provides a well laid out golden path for folks iterating in the #GenAI space. This follows up from my tweet yesterday about framework coupling. If the framework allows loose coupling, then graduating out of it isn't a thing you'll run into. In this post Thierry lays out to use Burr and how it doesn't get in your way as you build more complex and sophisticated workflows and agents. blog.dagworks.io/p/the-graduati…
Stefan Krawczyk tweet media
Stefan Krawczyk@stefkrawczyk

A @burr_framework user shared this video youtube.com/watch?v=evmZTh… with me on the "problem with frameworks". Worth a watch. I 💯% agree with the take home. The "coupling problem" is the reason why people graduate out of frameworks like @langchain & @llama_index. You become overly coupled and then find yourself overtime asking why am I using this? It's not that the framework authors did this maliciously, it's just that they optimized for their needs, in this case for POCs, which is not the same as long lived maintainable code. That's why we see people either build their own frameworks, or they hopefully discover @hamilton_os & @burr_framework and realize that there are frameworks that allow "loose coupling" that don't get in your way (as a platform person and framework author we optimize for maintainable code). A good example of this is @FastAPI - very easy to not couple your business logic and iterate quickly no matter the age of the code. So how can you tell where a framework lies on the spectrum of tight coupling versus not? Some tests: (1) How many "objects" do I need to use from the framework to couple the logic I want to happen? The fewer the better. E.g. with @hamilton_os by default it's 0. With @burr_framework it's just 1 and that's due to state for edge transitions, but that's easy to decouple from. (2) How many framework imports do you need to get something to run? The less the better - consider @burr_framework vs @langchain using #langgraph (see images) If you're feeling framework pains, or are curious on how it can be done right, checkout: github.com/DAGWorks-Inc/b… (agents) github.com/DAGWorks-Inc/h… (pipelines/tools) or subscribe to our blog - blog.dagworks.io #python #opensource #genai #llmops

English
0
5
4
356
Apache Burr (incubating) 已转推
Stefan Krawczyk
Stefan Krawczyk@stefkrawczyk·
A @burr_framework user shared this video youtube.com/watch?v=evmZTh… with me on the "problem with frameworks". Worth a watch. I 💯% agree with the take home. The "coupling problem" is the reason why people graduate out of frameworks like @langchain & @llama_index. You become overly coupled and then find yourself overtime asking why am I using this? It's not that the framework authors did this maliciously, it's just that they optimized for their needs, in this case for POCs, which is not the same as long lived maintainable code. That's why we see people either build their own frameworks, or they hopefully discover @hamilton_os & @burr_framework and realize that there are frameworks that allow "loose coupling" that don't get in your way (as a platform person and framework author we optimize for maintainable code). A good example of this is @FastAPI - very easy to not couple your business logic and iterate quickly no matter the age of the code. So how can you tell where a framework lies on the spectrum of tight coupling versus not? Some tests: (1) How many "objects" do I need to use from the framework to couple the logic I want to happen? The fewer the better. E.g. with @hamilton_os by default it's 0. With @burr_framework it's just 1 and that's due to state for edge transitions, but that's easy to decouple from. (2) How many framework imports do you need to get something to run? The less the better - consider @burr_framework vs @langchain using #langgraph (see images) If you're feeling framework pains, or are curious on how it can be done right, checkout: github.com/DAGWorks-Inc/b… (agents) github.com/DAGWorks-Inc/h… (pipelines/tools) or subscribe to our blog - blog.dagworks.io #python #opensource #genai #llmops
YouTube video
YouTube
Stefan Krawczyk tweet media
English
1
3
7
600
Apache Burr (incubating) 已转推
Hugo Bowne-Anderson
Hugo Bowne-Anderson@hugobowne·
💫 Humbled to have nearly 250 registrants for my free LLM Software Dev Lifecycle 30 min primer with @stefkrawczyk on @MavenHQ (and great to feel there's interest in what I currently want to teach!) 🤖 You can still register below and this is the lifecycle we'll be going through 👇 maven.com/p/38a781/build…
Hugo Bowne-Anderson tweet media
English
0
2
11
512
Apache Burr (incubating) 已转推
Stefan Krawczyk
Stefan Krawczyk@stefkrawczyk·
@latentspacepod @_anshulr Yep that's why @hamilton_os and @burr_framework observability is built in & pluggable by design, so you can offer all the trappings for enterprise without having to engineer for it later; graph / flowchart mental models FTW!
Stefan Krawczyk tweet mediaStefan Krawczyk tweet media
English
0
2
3
169
Apache Burr (incubating) 已转推
Hamza
Hamza@TheHamzaFarhan·
System Prompt Improvement Using Dialog Engineering and @burr_framework @dreamai/prompt-improvement-using-dialog-engineering-and-burr-0e022a1872a1" target="_blank" rel="nofollow noopener">medium.com/@dreamai/promp…
English
0
1
1
40

发现

@langchain @llama_index @hamilton_os @hugobowne @MavenHQ @LinkedIn @pyodide @scrapegraphai