49 comments

[ 4.1 ms ] story [ 62.4 ms ] thread
My biggest gripe with small models has been the inability to keep it informed with new data. Seems like this at least eases the process.
I had no idea they had their own cloud offering, I thought the whole point of Ollama was local models? Why would I pay $20/month to use small inferior models instead of using one of the usual AI companies like OpenAI or even Mistral? I'm not going to make an account to use models on my own computer.
Do they pull their own index like brave or are they using Bing/Google in the background?
I'd love to know what search engine provider they're using under the hood for this. I asked them on Twitter and didn't get a reply (yet) https://twitter.com/simonw/status/1971210260015919488

Crucially, I want to understand the license that applies to the search results. Can I store them, can I re-publish them? Different providers have different rules about this.

You should ask if search results are even copyrightable, if they are just a list of links.
I was hoping for more details about their implementation, I saw ollama as the open source // platform agnostic tool but I worry their recent posturing is going against that
> Create an API key from your Ollama account.

Dead on arrival. Thanks for playing, Ollama, but you've already done the leg work in obsoleting yourself.

Any tips on local/enterprise search?

I like using ollama locally and I also index and query locally.

I would love to know how to hook ollama up to a traditional full-text-search system rather than learning how to 'fine tune' or convert my documents into embeddings or whatnot.

Does this work with (tool use capable) models hosted locally?
I wish they would instead focus on local tool use. I could just use my own web search via brave api.
On a slightly related note-

I've been thinking about building a home-local "mini-Google" that indexes maybe 1,000 websites. In practice, I rarely need more than a handful of sites for my searches, so it seems like overkill to rely on full-scale search engines for my use case.

My rough idea for architecture:

- Crawler: A lightweight scraper that visits each site periodically.

- Indexer: Convert pages into text and create an inverted index for fast keyword search. Could use something like Whoosh.

- Storage: Store raw HTML and text locally, maybe compress older snapshots.

- Search Layer: Simple query parser to score results by relevance, maybe using TF-IDF or embeddings.

I would do periodic updates and build a small web UI to browse.

Anyone tried it or are there similar projects?

Kind of. I made ainews247.org that crawls certain sites and filters content so it's AI specific and valuable. I think it's a really good idea.
Reminds me of building a Obsidian vault with all the content in markdown form. There's also plugins to show vault results when doing a Google search, making notes within your vault show up before external websites.
Yep. Built a crawler, an indexer/queryprocessor, and an engine responsible for merging/compacting indexes.

Crawling was tricky. Something like stackoverflow will stop returning pages when it detects that you're crawling, much sooner than you'd expect.

I think a lot of time an exhaustive searchable index just of what I've browsed would be useful, though I suppose refresh feature would be useful.
This is a nice first step - web search makes sense, and it’s easy to imagine other tools being added next: filesystem, browser, maybe even full desktop control. Could turn Ollama into more than just a model runner. Curious if they’ll open up a broader tool API for third-party stuff too
What "Ollama account?" I am confused, I thought the point of Ollama was to self-host models.
What is the data retention policy for the free account versus the cloud account?
Can someone tell me how much this costs and how this compares to Tavily etc
I know it might be a security nightmare, but I still want to see an implementation of client-side web search.

Like a full search engine that can visit pages on your behalf. Is anyone building this?

WTF is going to happen to Google's ad revenue if every PC has an AI that can perform searches on the user's behalf?
That’s easy - they’re just going to ram the ads down your throat inline via Gemini
I think because Google knows traditional search is gonna die, they will be aggressively pushing ads on traditional search to extract as much money as possible till they figure out newer ways of making money.
I have a MCP tool that uses SERP API and it works quite well.
Ollama is a business? They raised money? I thought it was just a useful open source product.

I wonder how they plan to monetize their users. Doesn't sound promising.

There are very few recently launched pure open source projects these days (most are at least running donation-ware models or funded by corporate backers), none in the AI space that I'm aware of.
Until I saw your reply I had thought this post is about OpenAI lol.
The launched a hosted platform a while back
I am just working on a tool using websearch and iterating over different providers.

openAI, xAI, gemini all suffer from not being allowed on respective competitor sites.

this searched works for me with some quick tests well on YT videos, which OpenAI web search can't access. It kind of failed on X but sometimes returned ok relevant results. Definitely hit and miss but on average good

Are the rate limits documented somewhere?
Was looking to and could see them
it seems not, not even for the pro plan. just 'generous'
I added search to my LLMs years ago with the python DuckDuckGo package.

However I found that Google gives better results, so I switched to that. (I forget exactly but I had to set up something in a Google dev console for that.)

I think the DDG one is unofficial, and the Google one has limits (so it probably wouldn't work well for deep research type stuff).

I mostly just pipe it into LLM apis. I found that "shove the first few Google results into GPT, followed by my question" gave me very good results most of the time.

It of course also works with Ollama, but I don't have a very good GPU, so it gets really slow for me on long contexts.

How do you meaningfully use it without using scraping APIs? Aren't the official apis severely limited?
Your regular reminder that you don't need ollama to get a quick chat engine on the command line, you can just do this with pretty much any major model on huggingface:

pip install transformers

transformers chat Qwen/Qwen2.5-0.5B-Instruct

So, use ollama to avoid cloud models and services, but ollama sells cloud models and services. The dissonance makes my teeth hurt.
Exa, Tavily or Firecrawl. Which one is it?