Weves
Weves on Hacker News
You can plugin any model of your choice! Self-hosted, open source models are a great choice if you're very concerned about keeping your data safe and secure
You can also use any other LLM provider / any open source model of your choice!
Posted by
Weves on Tuesday November 28, 2023 @12:20PM
from the medium.com dept.
Posted by
Weves on Wednesday September 27, 2023 @12:50PM
from the show-hn dept.
https://docs.danswer.dev/introduction
Slack questions have always been a huge time sink for me. They’re a distraction that pulls me away from what I’m doing, and often requires digging up old knowledge. If I’m in the middle of something complex, I may take a while to context switch and get around to answering, which leaves the asker blocked for hours.Addressing this seems simple: give an LLM your organizational context and plop it...
Posted by
Weves on Wednesday August 09, 2023 @10:54AM
from the medium.com dept.
We'd love for you to contribute. Let us know in Discord / Slack (if you haven't already), and we'd be happy to find something interesting for you to hack on.
Right now, Danswer does send data to OpenAI. Once we support locally hosted, open source generative models that will change. If you go with that option, your data won't be sent anywhere.
That's a good suggestion! Will look into it, should be fairly easy to support
Agree with the point about intelligent chunking being very important! Each individual app connector can choose how it wants to split each `document` into `section`s (important point: this is customized at an app-level). The default chunker then keeps each section as part of a single chunk as much as possible. The goal here is, as you mentioned, to give each chunk the relevant surrounding context.
Additionally, the indexing process is setup as a composable pipeline under the hood. It would be fairly trivial to plug in different chunkers for different sources as needed in the future.
Great 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 only). Individual users can index private documents by providing their own access tokens for connectors, and those docs will be only available to the user who owns that access token. Improving this is a high priority item for us, as we understand this is a deal-breaker for enterprises.
The immediate plan is to extend our current poll / push based connectors to also grab access information (+ add IdP integrations for cross-app identity). There will be some delay to grab access updates, which will be combatted by the dynamic check with the app / IdP itself at query time that you mentioned (still investigating exactly how this will work).
We are also considering adding support for group based access defined within Danswer itself for sources that don't provide APIs to get access information (default being all-public if not specified). Of course, for these, we will not be able to sync permissions.
Amazing foundational tools like Qdrant make building in this space so much easier <3
Native support for the Microsoft suite of tools is something we plan to add fairly soon! We're a small team, and currently swamped with connector/feature requests so no promises on the timeline.
Ticketing platforms like ServiceNow fall under a similar category, although a bit lower priority in my mind.
Adding local/open source model support is at the top of our TODO list! When we started building, open source models were quite a bit more behind of GPT-4 then they are now. At that time the performance gap was at a point where locally hosted models would provide a significantly hampered experience, but we think that gap has (and will continue) to close rapidly.
LlamaIndex is a
very generic framework to ingest data (from anywhere, with no specific context in mind). Developers then build on top of this framework in order to simplify the process of creating LLM-powered on apps. Developers need to handle automatically syncing, building a UI to manage connections, build out the actual features/functionality they desire, etc.
Danswer is:
(1) itself an end-to-end application which allows you to connect to all your workplace tools via a UI, and then ask questions and get answers based on these documents. The goal is to be a permissively licensed, open source solution to the enterprise knowledge retrieval problem.
(2) an ingestion framework specifically targeted for enterprise applications. We provide a UI for admins to manage connections to other common workplace apps, automatically sync them into a vector DB + a keyword search engine, and expose APIs that allow access to these underlying data stores (more to come in this direction). We take care of access control (more in the pipeline here as well), only grabbing updates so we don't have to pull thousands (or millions) of documents every X minutes, etc. TL;DR: we're focused on a specific ingestion use case.
We're actually planning on migrating to LangChain very soon (primarily to allow for memory / tool usage + automatic integrations with llamacpp / other open source model serving frameworks). We didn't start with it initially since we didn't want to restrict our usage patterns too much while we were (even more) unsure of what exactly we were going to build.
As far as using other data connector frameworks, we found that we either (1) didn't think they were very good or/and (2) they didn't support automatic syncing effectively. For larger enterprises, it's not feasible to do a complete sync every X minutes. We need to be able to get a time-bounded subset (or have them push updates to us), which is something LangChain, LlamaIndex, etc. don't support natively.
We are actively building a Notion connector! Will be out very soon :)
Thanks! For now, we're just focused on making sure this solves a problem effectively for people. In the long term, if we're able to build up trust, we'll probably offer a managed version.
Yea, that's good feedback - we've gotten requests for open source model support from a lot from people we've talked about. It's one of our highest priorities, and should be available soon!
Posted by
Weves on Monday July 10, 2023 @10:55AM
from the show-hn dept.
https://github.com/danswer-ai/danswer
My friend and I have been feeling frustrated at how inefficient it is to find information at work. There are so many tools (Slack, Confluence, GitHub, Jira, Google Drive, etc.) and they provide different (often not great) ways to find information. We thought maybe LLMs could help, so over the last couple months we've been spending a bit of time on the side to build Danswer.It is an open source,...