Danswer
AI
enterprise search
SHOW HN2023
189points
66comments
#298of 3,109 in 2023
Top 10%of 2023 by points
How HN took it
CuriousMostly questions and neutral comments
4 positive, 14 neutral or asking, 2 mixed, 7 critical, out of 27 comments about the project. Thread score -0.08.
Privacy: 0 for, 6 againstIdea: 2 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Accurate answers with source links in testing
From 1 comment
I maintain an open source documentation platform, for which I had received a few queries about AI tooling. I'm not into the AI world of development, and my tech stack &…
ssddanbrown on HN
Objections
Only works with OpenAI, so sending company data externally is a blocker
From 3 comments
Sadly completely unusuable for our usecase - if you are targeting Enterprise, you should know better than to use OpenAI models as the only LLM available. For now I will stick to…
danpetrov on HNAnother great tool solving the exact problem we're willing to solve using an external service we can't use. No company at a decent size (those who actually reach some complexity…
Intox on HNFrom FAQ: > Danswer provides Docker containers that you can run anywhere, so data never has to leave your PVC. The one exception is using GPT for inference but we are working on…
TeMPOraL on HN
Access control is basic; private docs leak to all users
From 2 comments
How are you thinking about the "document level access control" to make this viable for business environments? Ex: If a connected gdrive document gets indexed, but then someone…
lmeyerov on HNGreat question! Right now, our access control is very basic. When admins setup connectors to other apps, all documents indexed are accessible by all (meant to be public documents…
Weves on HN
Heavy to run, long docker build
From 1 comment
I maintain an open source documentation platform, for which I had received a few queries about AI tooling. I'm not into the AI world of development, and my tech stack &…
ssddanbrown on HN
Requests
Support for local open source models
From 3 comments
Sadly completely unusuable for our usecase - if you are targeting Enterprise, you should know better than to use OpenAI models as the only LLM available. For now I will stick to…
danpetrov on HNWait, this is not local? Why use OpenAI third-party requests instead of a local model?
XCSme on HNNoooooooo, not openAI! It looks perfect, just allow to run models like Vicuna or Llama locally - well, since it’s open source anyone can contribute to make this happen. Thank you…
lastdong on HN
Azure OpenAI support
From 2 comments
From FAQ: > Danswer provides Docker containers that you can run anywhere, so data never has to leave your PVC. The one exception is using GPT for inference but we are working on…
TeMPOraL on HNAt the very least, I'd start with adding support for the Azure flavor of OpenAI API. It's literally the same models, but the difference is that it's your company deploying those…
TeMPOraL on HN
Microsoft 365, SharePoint and OneDrive connectors
From 1 comment
Looks great and will test it out, but for enterprises definitely needs support for Azure/Office 365 integration to index Word, Excel, etc. Lots of docs are stored in Onedrive,…
TommyCat on HN
Notion connector
From 1 comment
This looks interesting. Thank you for making public. I made something similar that uses data from only Notion. Do you happen to have / be developing a Notion connector?
tibanne on HN
Questions
How does it compare to llama-index
From 1 comment
how does this compare to llama-index
nbulka on HN
Why not build on LangChain or similar frameworks
From 1 comment
The video looks impressive, well done. Why didn't you build it on top of langchain or other similar frameworks?
kaismh on HN
Business model
From 1 comment
I've seen a few of these, and this one looks like it is more feature complete than many (e.g. including web scraping I think is an important component). Looks nice! Curious about…
sixhobbits on HN
Alternatives named
PrivateGPT and LocalGPT
From 1 comment
Sadly completely unusuable for our usecase - if you are targeting Enterprise, you should know better than to use OpenAI models as the only LLM available. For now I will stick to…
danpetrov on HN
llama-index
From 1 comment
how does this compare to llama-index
nbulka on HN
osschat.io
From 1 comment
Check this out. Built on a vector database (https://github.com/milvus-io/milvus) and a semantic cache (https://github.com/zilliztech/GPTCache) https://osschat.io/
ChrisPzilla on HN