[flagged]
another AI post...
Show HN: Omni – Open-source workplace search and chat, built on Postgres
41–50 of 54 posts
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#42(ParadeDB maintainer here). This is super cool. Congrats on the project, and I'm excited to see ParadeDB be used to power this kind of use case. If there's anything else you need to ship Omni, don't hesitate to reach out to me!
This is a good time to be offering hybrid search extensions. I just did that myself recently with pgvector for a documentation site.
Does ParadeDB work with Render? They seem to have a whitelist of extensions https://render.com/docs/postgresql-extensions
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#43(ParadeDB maintainer here). This is super cool. Congrats on the project, and I'm excited to see ParadeDB be used to power this kind of use case. If there's anything else you need to ship Omni, don't hesitate to reach out to me!
This is a good time to be offering hybrid search extensions. I just did that myself recently with pgvector for a documentation site. Does ParadeDB work with Render? They seem to have a whitelist of extensions https://render.com/docs/postgresql-extensions
We just made a blueprint for it! https://github.com/paradedb/render-blueprint
One-click deploy with Render, and we're directly in contact with the core team to get it added to their official docs. I hear the PR is up internally :)
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#44(ParadeDB maintainer here). This is super cool. Congrats on the project, and I'm excited to see ParadeDB be used to power this kind of use case. If there's anything else you need to ship Omni, don't hesitate to reach out to me!
Thanks Philippe! You guys have been super helpful on slack!
Anytime! We have some vector search work coming in the next few weeks/months that I expect you'll find interesting. Stay tuned :)
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#45[dead]
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#46[dead]
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#47Earlier quoted context omitted.
This is a good time to be offering hybrid search extensions. I just did that myself recently with pgvector for a documentation site. Does ParadeDB work with Render? They seem to have a whitelist of extensions https://render.com/docs/postgresql-extensions
We just made a blueprint for it! https://github.com/paradedb/render-blueprint One-click deploy with Render, and we're directly in contact with the core team to get it added to their official docs. I hear the PR is up internally :)
Sweet, nice work
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#48Earlier quoted context omitted.
Most organizations are going to be self hosting on aws, gcp or azure... So as long as you use their inference services as your LLM then you can keep it all within the private network
Even self-hosting on AWS, GCP, or Azure isn't local enough for certain application, such as people doing export-controlled work where any sysadmin or person with physical access to the server/data is required to be a US Person (or equivalent in other countries). This is the niche that the govcloud solutions are aimed at serving. But some people just want to build big actually-private, actually self-hosted systems and…
AWS Bedrock seems to say the inference code is only scanned for CASM and no one trains on your data.
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#49Earlier quoted context omitted.
Even self-hosting on AWS, GCP, or Azure isn't local enough for certain application, such as people doing export-controlled work where any sysadmin or person with physical access to the server/data is required to be a US Person (or equivalent in other countries). This is the niche that the govcloud solutions are aimed at serving. But some people just want to build big actually-private, actually self-hosted systems and…
AWS Bedrock seems to say the inference code is only scanned for CASM and no one trains on your data.
Are all people with physical access to the servers or network access to the hosts guaranteed to be US persons? Are all physical and network accesses logged for audits? That's the kind of thing govcloud promises that export control auditors want to see.
I felt like "Confidential Compute" tech could solve this issue once and for all but I'm not so sure after seeing some of the attacks people can do with physical access.
Another option of course is to not use cloud at all and have your own rack in a locked room with a good security system and/or armed US person guards.
Re: Show HN: Omni – Open-source workplace search and chat, built on Postgres
#50Nice! Could you elaborate on "not just a basic RAG"?
Thank you! Typical RAG implementations I’ve seen take the user query and directly run it against the full-text search and embedding indexes. This produces sub-par results because the query embedding doesn’t really capture fully what the user is really looking for. A better solution is to send the user query to the LLM, and let it construct and run queries against the index via tool calling. Nothing too ground-breakin…
I call this ralphgrep