grep agents find the right docs just fine
they just bring 24 friends
on our bench, only 1 in 25 chunks a grep agent returns is actually needed
full post from the research team below 👇
Emil retweeted
Announcing Dagger 1.0 beta.
Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens.
Featuring: test-native CI, dev shells, local and remote execution, official modules, and more.
dagger.io/blog/dagger-10-bet…
here you go :) xitter.cf/emilsnotes/status/2113…
the team took @cohere's new reranker v5 on a run on our company knowledge evals (real-world messy data)
it's cheap and fast! impressive jump from v4
the team took @cohere's new reranker v5 on a run on our company knowledge evals (real-world messy data)
it's cheap and fast! impressive jump from v4
wow jev 1.14 is stupidly good as a reranker
gg @typesafeai team
rerank-3 go brrrrrrr
“Voyage wins on score, cost, and latency.” Don’t believe us? Check out the latest benchmark from @kapa_ai.
Frontier models keep getting better, but they aren’t the whole stack. Agentic systems constantly make smaller decisions: what to retrieve, where to route a query, and which results matter. Specialized models are often better suited to that work.
Jev, @typesafeai’s general-purpose decision model, is a great example. Give it context, a question, and a set of labels, and it returns a probability for each label, allowing you to steer it with a rubric for routing, labeling, or ranking.
@kapa_ai tested Jev as a reranker on 1,000 real-world evaluation cases built from production queries over company knowledge bases, including product docs, Slack threads, support tickets, wikis, and code. Jev wasn’t built for reranking, yet it came within a hair of first place on retrieval quality, while also beating several dedicated rerankers.
Which model finished first? The rerank-3 model from Voyage AI by MongoDB topped the benchmark for retrieval quality while also being the cheapest and fastest model that Kapa measured.
Read the post for the full setup and results: mongodb.social/6016BHno7j
Kapa is now an official ChatGPT plugin
search your docs, tickets, wikis and code right from ChatGPT, with source links
or ask it to connect a new source, or show your coverage gaps
install: Plugins → Kapa
it's still mindblowing to be that jev isn't a reranker but it performs like one
wow jev 1.14 is stupidly good as a reranker
gg @typesafeai team
wow jev 1.14 is stupidly good as a reranker
gg @typesafeai team
Emil retweeted
love to see this integration
introducing @LangChain × kapa
your langchain agents can now search all your company knowledge more accurately, 3x faster and 8x cheaper than frontier models
we synch docs, github, notion, slack, zendesk and more into a single index (with vectors + file system)
your agent gets two tools: search everything, and read the full doc
it takes 2 min for your agent to set up (+ free to try)
just paste this into your agent:
"set up a knowledge base for my agent using docs.kapa.ai/getting-started… and pip install langchain-kapa-ai to use official plugin"
keep making agents go brr @hwchase17 + team!
introducing @LangChain × kapa
your langchain agents can now search all your company knowledge more accurately, 3x faster and 8x cheaper than frontier models
we synch docs, github, notion, slack, zendesk and more into a single index (with vectors + file system)
your agent gets two tools: search everything, and read the full doc
it takes 2 min for your agent to set up (+ free to try)
just paste this into your agent:
"set up a knowledge base for my agent using docs.kapa.ai/getting-started… and pip install langchain-kapa-ai to use official plugin"
keep making agents go brr @hwchase17 + team!