CTO, Co-Founder, @tryArcade | @redisinc @HPE_Cray | AI, LLM, Python, HPC, ⚾️ fan, roll tide | Blog: partee.io | Opinions are my own.
San Francisco, CA
Based in United States
- Tweets 1,395
- Following 464
- Followers 1,650
- Likes 3,986
Agents people!!
Parallelism and concurrency are not the same!
“Parallel” tool calls are actually executed *concurrently* 99.9% of the time.
if you’re waiting on a batch of web requests to complete, it’s concurrency.
157
In honor of @LangChain Interrupt today, here's my favorite Agent I made with Fleet + @TryArcade
Don Forgettabouit - a very sarcastic reminder agent
Started as a simple email triage agent I setup in 5 minutes and now it's the first email I open everyday.
Today's gem - "Did you miss the 'Action Required Today' part of that email from 3 days ago?"
1
4
20
3,906
@openclaw ... but give it everything!
Wrote a plugin to give OpenClaw / Moltbot / Clawdbot access to all of @TryArcade tools.
Now you can use 100s of services from any of your msg apps i.e. Discord, Telegram, etc. Auth included
👇Me using GCal and Slack from Telegram
2
2
5
373
Big day! We're releasing arcade-mcp - "the secure MCP framework"
All of arcade's supported Auth and 1000s of tools available in a first-class MCP framework.
We're committed to being the place for production MCP. With this launch, Arcade provides devs with secure MCP end-to-end
1
7
12
550
Agents that impersonate you
That’s what @aydin , @alexandras_dev and I chatted about here.
Might sound scary but it’s what unlocks agents to be useful.
Bunch of practical tips/tricks in here too from cursor vibing to how I use agents.
piped.video/QKkCpbPNCqg
1
4
517
Open Agents Platform 👥
Make and share agents that can do anything. Awesome use case of Arcade MCP support. Blog below.
@langchain 🤝 @TryArcade
2
5
33
9,867
Wow..
Just woke up to @TryArcade in @WSJ
Early on, I got feedback like: "LLMs can't even output JSON correctly, tool use is a hobby project". Now every major AI lab is deeply investing in it.
Things went from 0-100 real quick.
Picture sums up how I'm feeling right now
7
6
46
3,744
😳 this is crazy.
Imagine all the shit you can do with just AirPods now.
It’s like turning your life into an interactive podcast.
Simple app too, just @OpenAI when given @TryArcade tools. Plug and play. Ad hoc uncut demo so no bs.
1
2
10
1,455
What happens when your cofounder surprises everyone mid photo with a confetti canon.
The @TryArcade team is cracked. Best in the biz. Big releases coming soon :)
2
13
695
If you’re interested in agents and tool calling, I’ll be talking about everything I’ve learned building a platform for tool calling, @TryArcade, this Wednesday. My first public talk about it
Good, bad, ugly, everything.
Lots of other great speakers as well! Link in next tweet
1
1
12
1,087
1 slide.
Also, Modal is awesome. Would love to pick your brain on GRPC in python at some point.
1
111
Example of building a GPT with natural language.
Support for
- retrieval
- custom knowledge
- iterative creation
- image generation
- custom capabilities like code interpreter
177
Ok @langchain peeps, I bring you 🥁
ArXiv ChatGuru!
Put in a topic, number of papers, and chat with a guru who knows all about them.
Features:
▶️ Langchain-based QnA
▶️ ArXiv API loader
▶️ Semantic caching
▶️ @Redisinc vector db stats
▶️ LLM and retrieval controls
8
50
338
95,723
@hwchase17 DEMOOOO
It's still highly prone to over utilize context, but it's not that bad. You need to help me with my prompts next time I come over.
@lizziepika should we put this behind a @twilio API so people can text it?
3
1
15
19,955
Not using copilot tonight, I want to press every key haha. About to annoy everyone on a phone call with me.
See if you can spot me mess up the exit vim command 😅
1
1
91
Had an awesome time at @QCon talking about LLMs, RAG, and @Redisinc!
Thanks to Hein Liu (@DoorDash) for the invite!
Special shoutout to the @sourcegraph team whose raffle I won for this wicked WASD keyboard 😍
2
12
916
3. Don't use cloud!
Obviously not an option for many, but we've seen a large uptick in custom LLMs and people wanting to run them onsite.
I love @nvidia Triton, and just put in inference caching support.
1
1
1
202
2. AWS!
Put everything in AWS including the LLM. Same VPC, data never leaves the network besides input/output.
@cohere (check me if I'm wrong here) can support this kind of deployment.
AWS is also definitely coming out with more here too.
1
1
1
138
My new way of looking for Arxiv papers in my field?
@langchain + @Redisinc
Here's the full, simplified, example:
4
13
61
10,034
You can also create arbitrarily long sequences of filters that creates a SQL like experience.
This one combines the previous filter with a fuzzy text search on papers published first in 2023.
This means the vector search in Redis is only looking at that subset of papers.
1
1
832
**New Redis Filter Expression Language**
Why index metadata? To filter on it!
We've also implemented the RedisVL filter expression language into Langchain. This means, all that auto-indexed metadata can filter vector search results
This example filters on Arxiv categories
1
2
513
**Automatic Metadata Indexing**
Every time you use a document loader in Langchain with Redis, the metadata will now be automatically indexed into Tag, Text, or Numeric fields.
For example, the Arxiv loader now creates an index with the following fields in Redis.
1
3
598
Awesome to see @svonava and @superlinked get featured as a public use case for @Redisinc vector database.
redis.com/customers/superlin…
Also, look at this adorable picture of us with @chipro and @JackyGKoh at the LLM Stack hackathon!
1
11
1,066
Love to see all these awesome people hacking away on LLM apps with
@Redisinc
@RelevanceAI_
Great job @mlopscommunity
1
22
1,443
Memoiz is a personal assistant for your brain. You can log emotions, journal, and even chat with yourself.
Some ethical questions here, but nonetheless, awesome.
1
2
64
