Launch HN: Exa (YC S21) – The web as a database 1 year ago
I’ll add better support for tablet breakpoints in an hour, thanks for flagging!
HN user
liam-hinzman
21 karma
Posts0
Comments14
No posts found.
The API response you were looking at is the preview search, the full search linked below found 25 matches in a minute.
github repos that are implementations of ReBAC authorization servers
That was an unmaintained landing page with old iframes, thanks for catching that! Removed all links to it, and set it to redirect to the correct page at websets.exa.ai
We were down for a bit, sorry about that. Ran your search for you, and found 25 results in ~2 minutes.
“List of food festivals on the east coast specializing in small dishes or encourages sampling from multiple vendors. features more than 20 vendors”
https://websets.exa.ai/cmad3sonh001zhx0i1h7t692f
btw I like how you host screenshots on your personal website
We charge $5 per 1000 requests with our search and answer endpoints.
Perplexity charges the same on their lowest tier model, and three times as much for their more expensive models.
Gemini charges $35 per 1000 requests.
We were down for a bit, back up now! Lmk how the search quality turns out for you
We were down for a bit! Ran your search, got 8 matches after analyzing 100 results. Took 40 seconds for the first match, and another 80 seconds for the other matches.
We use an agentic search planner that adapts its search strategy as matches are found, but it could be smarter with substrings.
Deduplication is mainly driven by LLMs with search results as context. Our entity resolution works well because Exa’s main business is crawling and indexing the web at scale, and we can control how we search across that within Websets.
As far as I know ChatGPT’s search is primarily a wrapper around another company’s search engine, which is why it often feels like it’s just summarizing a page of search results and sometimes hallucinates badly.
I think I found it! Unfortunately we do not include tweets in our search index
TLDR LLM training runs are significant stress-tests of an overall fault tolerance of a large computing system acting as a biological entity.
We find supporting references when evaluating the search criteria / enrichments of each result, and you can view these citations
Without signing in you’re only able to view the preview table, which is just Exa’s regular search.
If you sign in each result will be graded by an LLM, supporting references will be found, you can get agents to add arbitrary data to each result, and the table UI is much better.
Understand if you don’t want to sign up, I’d just look at the examples linked in the OP in that case
We hid it because the UI wasn’t maintained.
I joined recently, and live-streamed myself designing and shipping the new search frontend in 5h32m
https://x.com/LiamHinzman/status/1911244983291514941
Added a link to it on our homepage, thanks for pointing that out!
Amazing! I didn't notice the control panel earlier
Is there anything like this where it's only coloring the text and not the background of the font? Hoping to find something like ascii-gen [0,1] but for video
[0] https://github.com/seatedro/asciigen [1] https://x.com/seatedro/status/1828414268707946506