Infotrend Inc. Posted November 9, 2023 Share Posted November 9, 2023 (edited) Unraid-ready WebUI (streamlit-based) to ChatGPT and Dall-E's API (requires an OpenAI API key). Latest version: v0.9.7 (20240718): Added support for gpt-4o-mini The tool's purpose is to enable a company to install a self-hosted version of a WebUI to access the capabilities of OpenAI's ChatGPT and DallE, share access to the tool's capabilities, and consolidate billing through an OpenAI API key. Please review https://github.com/Infotrend-Inc/OpenAI_WebUI/README.md for two sections in particular: - the .env supported environment variables that are defined in this template - the Unraid specific setup section that introduces features not enabled by default: a default username for single user mode, and the ability to password protect the WebUI. Short list of supported GPT (including vision when supported by the model): - gpt-4o-mini - gpt-4o - gpt-4-turbo - gpt-4 - gpt-3.5-turbo Short list of supported DallE: - dall-e-3 - dall-e-2 Full list of authorized models at https://github.com/Infotrend-Inc/OpenAI_WebUI/tree/main?tab=readme-ov-file#11-supported-models This container is built from the source available at https://github.com/Infotrend-Inc/OpenAI_WebUI The container requires a set of environment variables to work, but will inform the end user if an expected value is missing. Changelog: - v0.9.7 (20240718): Added `gpt-4o-mini` and `deprecated` older `32k` models - v0.9.6 (20240701): Added method to disable `vision` for capable models + added whole WebUI password protection using streamlit's `secrets.toml` method - v0.9.5 (20240611): Added support for vision in capable models + Added gpt-4-turbo models + Deprecated some models in advance of 20240613 + Updated openai python package to 1.33.0 + Decoupled UI code to allow support for different frontends. - v0.9.4 (20240513): Added support for gpt-4o, updated openai python package to 1.29.0 - v0.9.3 (20240306): Simplifying integration of new models and handling/presentation of their status (active, legacy, retired) + Cleaner handling of max_tokens vs context window tokens + updated openai python package to 1.13.3 - v0.9.2 (20241218): Keep prompt history for a given session + allow user to review/delete past prompts + updated openai python package: 1.8.0 - v0.9.1 (20231120): Print streamlit errors in case of errors with environment variables + Addition of gpt-3.5-turbo-1106 in the list of supported models (added in openai python package 1.3.0) + added optional `OAIWUI_USERNAME` environment variable - v0.9.0 (20231108): Initial release -- incorporating modifications brought by the latest OpenAI Python package (tested against 1.2.0) Edited July 18 by Infotrend Inc. updated to v0.9.7 Quote Link to comment
Infotrend Inc. Posted November 9, 2023 Author Share Posted November 9, 2023 [Reserved post] Quote Link to comment
kharntiitar Posted November 12, 2023 Share Posted November 12, 2023 (edited) Hey there, I've spent a while trying to get this working, but I'm not having much success. Maybe you can advise, @Infotrend Inc.?? The container boots fine, but when I go to the web interface, I get a blank dark blue screen. there's a ... menu on the top right, and I can go to settings there. there is "made with streamlit" down on the bottom left and there's a gradient from red to yellow across the top. I've tried a couple of different browsers and computers, and I get the same result.. Also, when I refresh, for just a microsecond there's a box that pops up, which says "please wait". I've got no errors in the logs. Also, as a minor side note.. any chance you can allow reverse proxies, or a variable for the url? Edited November 12, 2023 by kharntiitar add additional question Quote Link to comment
Infotrend Inc. Posted November 13, 2023 Author Share Posted November 13, 2023 (edited) 19 hours ago, kharntiitar said: The container boots fine, but when I go to the web interface, I get a blank dark blue screen. there's a ... menu on the top right, and I can go to settings there. there is "made with streamlit" down on the bottom left and there's a gradient from red to yellow across the top. I've tried a couple of different browsers and computers, and I get the same result.. Also, when I refresh, for just a microsecond there's a box that pops up, which says "please wait". I've got no errors in the logs. That usually means the script encountered an error before the streamlit UI is able to boot. Usually this is related to the provided environment variables. All of them need to have a value. I would suggest from the Docker tab to click on the icon and checking the logs for error after you start it. Environment check variable errors were not being passed to the UI. I will see about adding UI errors when possible. I have deployed the UI on two different Unraid for testing without encountering this issue. 19 hours ago, kharntiitar said: Also, as a minor side note.. any chance you can allow reverse proxies, or a variable for the url? The tool works directly with reverse proxies that communicate with the IP:PORT of the Unraid installation. This has been tested using Nginx Proxy Manager as well as Cloudflare tunnels. Edited November 13, 2023 by Infotrend Inc. Quote Link to comment
Dmitriyus Posted November 15, 2023 Share Posted November 15, 2023 (edited) Is there a limit to the "OAIWUI_GPT_MODELS:"? I have the models below but adding them in the field doesn't allow me to get past the "Enter User" screen. Checked logs but nothing. Thanks! gpt-3.5-turbo,gpt-3.5-turbo-0301,gpt-3.5-turbo-0613,gpt-3.5-turbo-1106,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-4 Side Note: It does NOT like when there are spaces after the commas. Edited November 15, 2023 by Dmitriyus Quote Link to comment
Infotrend Inc. Posted November 20, 2023 Author Share Posted November 20, 2023 (edited) On 11/15/2023 at 6:10 PM, Dmitriyus said: Is there a limit to the "OAIWUI_GPT_MODELS:"? I have the models below but adding them in the field doesn't allow me to get past the "Enter User" screen. Checked logs but nothing. Thanks! gpt-3.5-turbo,gpt-3.5-turbo-0301,gpt-3.5-turbo-0613,gpt-3.5-turbo-1106,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-4 Side Note: It does NOT like when there are spaces after the commas. First, thank you for the note on the spaces, I should have fixed this in the latest branch (soon to be released as v0.9.1) To answer your question: Yes, the tool has a limited list of models supported (it displays a small help for each model based on that knowledge). I am adding a UI error (in the latest branch) that will let you know the list of models not supported from the list. In particular, for gpt-3.5, older models ("0301", "0613") are "Legacy" models per https://platform.openai.com/docs/models/gpt-3-5 so we did not include them in the release. The current list of supported models is in the ".env.example" file (see first post), which currently contains: gpt-3.5-turbo gpt-3.5-turbo-16k gpt-3.5-turbo-1106 gpt-4 gpt-4-32k gpt-4-1106-preview As for the "instruct" models, per their model page "Similar capabilities as text-davinci-003 but compatible with legacy Completions endpoint and not Chat Completions" knowing that "text-davinci-003" is a legacy API at this point, it also was not added. We have also removed that piece of code (legacy completion) in favor of the chat one. I hope this helps answer your questions. Edited November 20, 2023 by Infotrend Inc. 1 Quote Link to comment
kharntiitar Posted December 5, 2023 Share Posted December 5, 2023 (edited) Hey @Infotrend Inc., thanks for getting back to me so fast, sorry I failed to achieve the same. Quote That usually means the script encountered an error before the streamlit UI is able to boot. Usually this is related to the provided environment variables. All of them need to have a value. You were 100% correct on it being an environmental variable. I had, in my haste to get it setup, set the value of "OAIWUI_SAVEDIR" to the path of a host folder, rather than correctly to "/iti". I have no idea how I missed this, but stepping away for a couple of weeks has helped me work it out Quote The tool works directly with reverse proxies that communicate with the IP:PORT of the Unraid installation. This has been tested using Nginx Proxy Manager as well as Cloudflare tunnels. I think this is what is causing my ongoing issue, I use a MACVLAN network for my unraid containers, so my IP isn't the same as my unraid install. Either that or I've misconfigured something. Edited December 5, 2023 by kharntiitar Edited for clarity and succinctness. Quote Link to comment
Infotrend Inc. Posted December 10, 2023 Author Share Posted December 10, 2023 (edited) On 12/5/2023 at 5:57 PM, kharntiitar said: You were 100% correct on it being an environmental variable. I had, in my haste to get it setup, set the value of "OAIWUI_SAVEDIR" to the path of a host folder, rather than correctly to "/iti". I have no idea how I missed this, but stepping away for a couple of weeks has helped me work it out Glad the environment variable issue got resolved. As for the networking issue, I am uncertain on how to help, unfortunately. Edited December 10, 2023 by Infotrend Inc. Quote Link to comment
Maitresinh Posted July 2 Share Posted July 2 Could it be used to install GPT trans on unraid ( ie: bazarr ?) https://github.com/machinewrapped/gpt-subtrans Quote Link to comment
martial Posted July 2 Share Posted July 2 19 minutes ago, Maitresinh said: Could it be used to install GPT trans on unraid ( ie: bazarr ?) Unfortunately, this is not the purpose of the tool. If subtrans can be run as a Docker container, I would investigate a tool like Dokge or Dockemon (which are in the App Catalog) to start the service. Quote Link to comment
Maitresinh Posted September 14 Share Posted September 14 Far beyond my skills and time i'm afraid, but thanks for the tips. Seems quite an interesting way to do it Quote Link to comment
Maitresinh Posted September 14 Share Posted September 14 Could not found these two on Unraid app tab (if i understand correctly) Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.