Reptar

I was wondering if anyone has deployed Quivr (https://github.com/StanGirard/quivr) on their unraid instance? Currently using text-generation-webui but quivr seems way better. Only downside for me would probably be that it might not work with my home assistant instance like text-generation-webui does.

I also have a HX1500i and I also volunteer as tribute Think you can also throw the test version my way as well? Thanks!

Yeah, it's not there yet but it sure is cool to look at! I saw one guy who was mainly using to research and summarize things automatically. He basically asked it to look at what his company offered, look up a potential client and come up with marketing material that would look good to that specific potential client. I think stuff like that probably works well... if you ask it to build something though, it just goes full herrdurr

I actually have no idea what I'm doing, I basically looked at multiple random dockerfiles and tried to pull bits and pieces together until things worked. If errors popped up, I would research them and attempt fixes based on the research. Unfortunately, I didn't use just one guide... I pulled information from various sources... I watched this a while ago and I found her videos helpful in general: For compiling the autogpt_gotty image, I used some of these sites to pull bits of information: https://docs.docker.com/build/building/base-images/ https://devopscube.com/build-docker-image/ https://www.stereolabs.com/docs/docker/creating-your-image/ I also found someone else's project which did the same thing. At the time, it wasn't working at all though so I pulled snippets from their dockerfile and the main auto-gpt github repo and cobbled something together: https://github.com/claytondukes/autogpt-docker https://github.com/Significant-Gravitas/Auto-GPT

Do you mean it just locked up and stopped showing text on the screen? or did you see errors pop up?

Glad it all worked out!

Forgot to mention, use this redis docker: redis/redis-stack-server

I was able to make a docker image that uses gotty for a web based terminal (so you dont have to open auto-gpt in the console window every time) docker image: autogpt_gotty Docker Images needed: autogpt_gotty (reptard one -- You'll need to click "Click here to get more results from dockerhub" for it to show up) Note: you can allow unraid to detect config (that's what I did) redis (jj9987's repository) API Keys Required: OpenAI key, see: https://docs.agpt.co/setup/ (Getting an API Key section) Note: The instructions below also assumed you have set up a google api/custom search engine. you can omit those if you dont want to use google search. Otherwise, see here for instructions on how to acquire: https://docs.agpt.co/configuration/search/#google-api-keys-configuration Install redis (default port is 6379) -- leave everything other than port as is. Port can be changed to whatever Install autogpt_gotty A. Set container port 1 value. This can be any unused port. B. Add the following variables along with their values: - OPENAI_API_KEY - GOOGLE_API_KEY - CUSTOM_SEARCH_ENGINE_ID - MEMORY_BACKEND (value: redis) - REDIS_HOST (Value: your unraid IP) - REDIS_PORT (value: port set for redis container in step 1) - SMART_LLM_MODEL (value: gpt-3.5-turbo -- this assumes you do not have access to the gpt-4 API) Note: you can use add any of the other variables from the Auto-GPT repo C. Optional: If you want to save data written by Auto-GPT, add the following Path: - Name: Workspace Path - Container Path: /app/autogpt/auto_gpt_workspace - Host Path: Your desired unraid share/directory - Access Mode: Read/Write

That depends on the docker image you're using. Here's the .env from the auto-gpt github though: https://github.com/Significant-Gravitas/Auto-GPT/blob/master/.env.template

yes, search what youre looking for in apps, then click "Click here to get more results from dockerhub" Once you find what you're looking for you can click Install. It'll ask you if you want unraid to attempt to determine applicable paths and ports etc. You'll probably need to manually enter variable names/values.

I was able to make a docker image with gotty for web based terminal access but don't really have any idea how to make a nice UI for auto-gpt using something like streamlit for example.... Has anyone else been able to make something? I've been trying to get auto-gpt to do it (lol) but it's not working out too well.

Did anyone else have issues with the most recent update (v23.04.1)? seems to have broken things for me. all of my sites return 502 and I had to revert to v23.03.2

So I noticed fix common problems was displaying an error stating "Invalid folder addons contained within /mnt" shortly after I received an update for unassigned devices. I was able to find this post on the forum that mentions that specific path. Is this a fix common problems plugin issue or should I post on the unassigned devices thread? I don't have anything special going on with my instance (no ZFS etc) so I'm not sure why this would have suddenly popped up...

Looks like I initially failed to set the appropriate RAM frequencies listed in the link. Set from Auto to DDR4-2133 and I haven't had a crash in 3 days. Thanks for the help, @JorgeB!

I did also install new RAM a few weeks ago so I'll do a memtest now to be safe. Will definitely boot in safemode as suggested tonight as well. Thanks for the help @JorgeB! EDIT: Did one pass on memtest and there were no errors