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

Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 134 posts

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#11

Post by yuhongsun »

trungdq88 wrote: post #9

Quick question: do you offer API? I'm hoping to integrate this with an existing chat UI that I have.

Yes, we have an API and a way of accessing it with a generated API key which you can find in the admin panel.

Two things to note though.

The APIs are intended for serving the Danswer frontend. The functionality is generally complete for similar use cases but it's not documented so you have to look at the code.

If you're overusing the API on the cloud without providing your own OpenAI key, we will likely have to shut down the instance to prevent losing too much on inference fees.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#12

Post by BillFranklin »

Good luck folks! I'm glad there are projects trying to solve enterprise search.

I guess the main problem is the "private" aspect, if I've understood your goals correctly. Since most SaaS products lock down the private data unless you pay enterprise fees for compliance tooling.

For instance, if you want to ingest data from private Slack channels or Notion groups, you have to get the users in those groups to add your bot to them, otherwise there's no way of your service getting access to the data. It's possible, just a bad UX for users.

That said, built-in search for most SaaS products built after 2015 is generally quite good (e.g. Slack has an internal Learning to Rank service for a while now, which makes their search excellent: https://slack.engineering/search-at-slack/), so you'd be solving for companies like Webex and Confluence where their internal search is not great. At companies like Google they have internal search across products, which is the ideal end state, but have the benefit that they own the source code for most of their internal products.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#13

Post by Oras »

The integration part (connectors) is the key here. I can see how beneficial this would be for companies as they can plug and play.

Adding the vectorisation locally is superb, I've played around with sbert models before and ability to run without GPU is going to simplify the process a lot.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#14

Post by yuhongsun »

BillFranklin wrote: post #12

Good luck folks! I'm glad there are projects trying to solve enterprise search. I guess the main problem is the "private" aspect, if I've understood your goals correctly. Since most SaaS products lock down the private data unless you pay enterprise fees for compliance tooling. For instance, if you want to ingest data from private Slack channels or Notion groups, you have to get the users in those groups to add your b…

I think I understand your concern but if I miss the point, please follow up!

So regarding getting access to read knowledge from the different tools, it depends tool by tool but a lot of them have API keys or options for app integrations available in the free tier (GitHub, Google Drive, Confluence come to mind). Other tools don't have a free tier and you just get access to the API keys as a part of paying for the service. I think there are probably tools that require a premium fee to get integration access but I'm not aware of any personally.

For the SlackBot, it can add itself to public channels but for private channels someone needs to add it. It is what it is sadly.

About search being available for most SaaS products: SaaS tools are definitely improving their own searches. But I still think a single place to search and aggregate data has significant value. For example, as an engineer by training, often getting the full picture for some customer escalation includes reading Slack threads, Confluence Design docs, old Pull Requests on GitHub. Would be nice to get it all in one place.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#15

Post by michaelmior »

I noticed the Google Drive connector includes sheets. It looks like for the time being, these just get indexed as CSV file. That seems like it would miss a lot of context since a good number of spreadsheets aren't structured as a simple table. I'm wondering if you have any plans to make spreadsheet indexing more useful going forward.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#16

Post by yuhongsun »

Oras wrote: post #13

The integration part (connectors) is the key here. I can see how beneficial this would be for companies as they can plug and play. Adding the vectorisation locally is superb, I've played around with sbert models before and ability to run without GPU is going to simplify the process a lot.

Ah yes, this reminds me! I forgot to mention it but for the local NLP models that we run, they're in the range of 100 million parameters so they're able to be run on CPU (no GPU required!) with pretty low latency.

Also a fun tidbit on the connectors, more than half of them now are built by open source contributors! We just have an interface that needs to be implemented and people have been able to figure it out generally.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#17

Post by yuhongsun »

michaelmior wrote: post #15

I noticed the Google Drive connector includes sheets. It looks like for the time being, these just get indexed as CSV file. That seems like it would miss a lot of context since a good number of spreadsheets aren't structured as a simple table. I'm wondering if you have any plans to make spreadsheet indexing more useful going forward.

Ya, handling spreadsheets is a beast of its own. We have this simple implementation to cover easy cases for folks but likely it will need its own more involved pipeline for indexing, retrieval, and interactions with the LLM.

Currently with large tables, it's not handled very well either. The more complete approach would be to pass the headers to the LLM and ask it to generate a formula to parse the data rather than feeding the whole table(s) to the LLM directly.

Some of the bigger items we want to target that require special flows are code search, SQL tables, and Excel/CSVs/TSVs

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#18

Post by cyanydeez »

yuhongsun wrote: post #17
michaelmior wrote: post #15

I noticed the Google Drive connector includes sheets. It looks like for the time being, these just get indexed as CSV file. That seems like it would miss a lot of context since a good number of spreadsheets aren't structured as a simple table. I'm wondering if you have any plans to make spreadsheet indexing more useful going forward.

Ya, handling spreadsheets is a beast of its own. We have this simple implementation to cover easy cases for folks but likely it will need its own more involved pipeline for indexing, retrieval, and interactions with the LLM. Currently with large tables, it's not handled very well either. The more complete approach would be to pass the headers to the LLM and ask it to generate a formula to parse the data rather than f…

most of the files I have, I'm most interested in finding graphs and then updating relevant data.

it looks like the best way to do that is understand the ooxml format in xlsx. it's all fairly easy to understand.

Re: Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

#20

Post by yuhongsun »

cyanydeez wrote: post #18
yuhongsun wrote: post #17

Earlier quoted context omitted.

Ya, handling spreadsheets is a beast of its own. We have this simple implementation to cover easy cases for folks but likely it will need its own more involved pipeline for indexing, retrieval, and interactions with the LLM. Currently with large tables, it's not handled very well either. The more complete approach would be to pass the headers to the LLM and ask it to generate a formula to parse the data rather than f…

most of the files I have, I'm most interested in finding graphs and then updating relevant data. it looks like the best way to do that is understand the ooxml format in xlsx. it's all fairly easy to understand.

Ya, parsing the file is generally not bad at all. The problem comes with the fact that LLMs are notoriously bad with numbers and formatted data. So the current approach of passing relevant information to the LLM and asking it to generate answers will produce misleading information when larger tables are passed in.

By asking the LLM to generate a formula though, it doesn't actually need to do any number crunching of its own which makes solving the challenge a bit more reliable when it comes to LLMs.

Post reply on HN