Comments (8)
http://localhost:1234/v1/chat/completions works for me. I would suggest using that endpoint with Wingman. It mimics the OpenAI /chat/completions API, which is what the OpenAI provider in Wingman is expecting to use.
I'm running LM Studio 0.2.8.
http://localhost:1234/v1 does not work for me. Instead, I see this error in their console: [2023-12-10 21:14:57.283] [ERROR] Unexpected endpoint or method. (POST /v1). Returning 200 anyway.
from wingman.
You probably figured it out by now, but I think by default the Wingman panel is down below, next to the "Debug console", "Problems", "Output", etc.:
I think the default key to reveal this panel is CMD/CTRL-J, or you can go to View -> Debug console:
from wingman.
You can of course drag/drop the panel to the left sidebar if you want, which is where I like to keep it.
from wingman.
I'm assuming this was just a case of "where is it?", instead of something actually not working, so I'm closing this. Please feel free to open this back up if I'm wrong.
from wingman.
Thanks for the hint about View > Debug Console, but I found that from (Command-Shift-P) and searching Wingman. However when I look for it in Settings -> Extensions it's not there. So there are no settings, just the tab for "Presets" is that right? Also, I didn't know about the drag and drop to the sidebar trick. Thanks. My other extensions don't seem to behave this way.
from wingman.
So there are no settings, just the tab for "Presets" is that right?
Yep. The majority of configuration happens in the "Presets" tab, but the other tabs are used for some light configuration as well - prompts, placeholders, modes.
However when I look for it in Settings -> Extensions it's not there.
There are no settings in Settings -> Extensions. Everything that is configurable is configurable from the UI.
from wingman.
Thanks, for your reply. Now to connect to LM Studio which is running in server mode: the default URL for the endpoint says http://localhost:1234/v1/chat/completions but my other project using Open Interpreter uses "http://localhost:1234/v1", so should I change the URL by deleting the /chat/completions part? Because at the moment my prompt messages aren't received by LM Studio.
from wingman.
Thanks for your help.
from wingman.
Related Issues (20)
- Support configurable inference params per prompt HOT 8
- Context window and max_tokens management
- Disable the copy icon when generating HOT 1
- Write function comment prompt: ask before injecting the response into the file HOT 1
- New Goinfer provider HOT 3
- New Koboldcpp provider HOT 10
- Great Job! HOT 1
- A new theme sharing HOT 1
- Please include the julia language (.jl) extension also. HOT 1
- Wingman v2.0.8 , Local model is not supporting HOT 4
- Using the new version with local open source backends HOT 5
- Discussion: modelfusion HOT 2
- Missing Implementation of 'file' Placeholder as Mentioned in README HOT 1
- Feature Request: Enhance Contextual Understanding by Allowing Code File Integration
- Feature Request: Integration of Azure OpenAI Credentials Support HOT 1
- The selected code is forcibly replaced. HOT 4
- `Error: Failed to open completion stream: 429 Too Many Requests` HOT 2
- Feature Request: Support Anthropic messages API
- Remove restriction on Ollama models
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from wingman.