Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Parallel Search API

parallel.ai

Post reply on HN
Print view View original

41–50 of 55 posts

Re: The Parallel Search API

#41

Post by nextworddev »

davidsainez wrote: post #38

Saw this post. clicked on pricing. "Run up to 20,000 requests for free", ok lets try it. sign up for an account. click on playground. try a query -> balance is insufficient. then I clicked on "pricing" tab inside of the dashboard ( https://platform.parallel.ai/pricing ), no mention of any free requests. I pay for a lot of tools, but patterns like this leave me with a really bad impression.

+ apps that make it hard to cancel on a self serve basis

I tried cancelling Exa (search) and they had me email the support, which they ignored and required a follow up. Then they had the nerves to ask for feedback.

Re: The Parallel Search API

#42

Post by barapa »

tcdent wrote: post #12

Search accuracy, when used in the context of an agent, is so important because when you are delivered search results which are incorrect, the agent tends to interpret them as fact because they come from a "credible" source. So, this is very much an industry that still has plenty of room for improvement, and I'm excited to see how this product performs.

I don't really understand this. You can and should tell the llm the source of the search results.

Re: The Parallel Search API

#43

Post by keeganpoppen »

hamasho wrote: post #37

> Traditional search engines were built for humans. They rank URLs, assuming someone will click through and navigate to a page. The search engine's job ends at the link. The system optimizes for keywords searches, click-through rates, and page layouts designed for browsing - done in milliseconds and as cheaply as possible. > ... AI search has to solve a different problem: what tokens should go in an agent's context w…

it’s funny because this is literally how Google USED to work. sigh.

Re: The Parallel Search API

#45

Post by dragonwriter »

pegasus wrote: post #20
srameshc wrote: post #19

I like Parallel and been using it for tests but I am not sure about the terms. > The materials displayed or performed or available on or through our website, including, but not limited to, text, graphics, data, articles, photos, images, illustrations and so forth (all of the foregoing, the “Content”) are protected by copyright and/or other intellectual property laws. You promise to abide by all copyright notices, tra…

IANAL but think this is to remind you that fragments of text it returns to you after pulling them from various sites in response to your query are protected by whatever copyright notices might be found on those websites. Seems reasonable to me.

As it written it makes part of your agreement with Parallels not to use anything provided via the service without the prior consent of the content owner even if it doesn't violate any legal rights to do so. It may merely be poorly written, but I wouldn't rely on that.

Re: The Parallel Search API

#47

Post by petralithic »

paragagrawal wrote: post #32
pegasus wrote: post #24

Earlier quoted context omitted.

This is a search agent available in the cloud. The site mentions that they doesn't optimize for being "done in milliseconds and as cheaply as possible", and that they do a lot more work like extracting relevant paragraphs and "Single-call resolution for complex queries that normally require multiple search hops" and more. Geared to be consumed by other agents, hence the latency may be tolerable. They have the advanta…

In agentic use cases, we save on end-to-end latency by spending more time and compute on individual searches. This happens because agents do fewer searches, use fewer tokens, and end up using fewer thinking tokens when using the Parallel Search API.

How would the product work if for example I just wanted to get basic information from various websites, such as "how many calories are in a McDonald's hamburger?" I'm creating a product that tracks calories via natural language and I'd want a structured JSON back of calories, grams of fat, protein, carbs etc. What API would I use for that, the Chat API one?

Re: The Parallel Search API

#49

Post by kshelat »

davidsainez wrote: post #38

Saw this post. clicked on pricing. "Run up to 20,000 requests for free", ok lets try it. sign up for an account. click on playground. try a query -> balance is insufficient. then I clicked on "pricing" tab inside of the dashboard ( https://platform.parallel.ai/pricing ), no mention of any free requests. I pay for a lot of tools, but patterns like this leave me with a really bad impression.

hi-this is unexpected. new users should receive free credits. we're looking into the bug. happy to help if you can email support@parallel.ai
Post reply on HN