Nicholai/jan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: fix configuration

Browse Source
This commit is contained in:
Ho Duc Hieu 2024-01-02 19:17:52 +07:00
parent 39be5bf9c3
commit d96d5d30c9
1 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docs/docs/guides/04-using-models/02-import-manually.mdx
View File

@ -172,11 +172,13 @@ Your model is now ready to use in Jan.
In this guide, we will show you how to configure a client connection to a remote/local server, using LM Studio as an example. In this guide, we will show you how to configure a client connection to a remote/local server, using LM Studio as an example.
At the moment, you can only connect to one compatible server at a time (e.g OpenAI Platform, Azure OpenAI, LM Studio, etc) At the moment, you can only connect to one compatible server at a time (e.g OpenAI Platform, Azure OpenAI, LM Studio, etc).
### 1. Configure Local Server in Engine ### 1. Configure Local Server in Engine
Create `lmstudio.json` in the `~/jan/engines` folder. Configure `full_url` properties with the endpoint server that you want to connect. For example, if you want to connect to LM Studio, you can configure as follows: Navigate to the `~/jan/engines` folder and find the `openai.json` file. Currently, the code support any openai compatible endpoint only read `engine/openai.json` file, thus, it will not search any other files in this directory.
Configure `full_url` properties with the endpoint server that you want to connect. For example, if you want to connect to LM Studio, you can configure as follows:
```js ```js
{ {
@ -194,17 +196,12 @@ Navigate to the `~/jan/models` folder. Create a folder named `remote-lmstudio` a
- Ensure the filename must be `model.json`. - Ensure the filename must be `model.json`.
- Ensure the `id` property matches the folder name you created. - Ensure the `id` property matches the folder name you created.
- Ensure the `format` property is set to `api`. - Ensure the `format` property is set to `api`.
- Ensure the `engine` property is set to as the filename that you recently created in `~/jan/models`. In this example, it is `lmstudio`. - Ensure the `engine` property is set to `openai`.
- Ensure the `state` property is set to `ready`. - Ensure the `state` property is set to `ready`.
```js ```js
{ {
"source": [ "source_url": "https://lmstudio.ai",
{
"filename": "lmstudio",
"url": "https://lmstudio.ai"
}
],
// highlight-next-line // highlight-next-line
"id": "remote-lmstudio", "id": "remote-lmstudio",
"object": "model", "object": "model",
@ -220,7 +217,7 @@ Navigate to the `~/jan/models` folder. Create a folder named `remote-lmstudio` a
"tags": ["remote", "awesome"] "tags": ["remote", "awesome"]
}, },
// highlight-start // highlight-start
"engine": "lmstudio", "engine": "openai",
"state": "ready" "state": "ready"
// highlight-end // highlight-end
} }
@ -230,8 +227,6 @@ Navigate to the `~/jan/models` folder. Create a folder named `remote-lmstudio` a
Restart Jan and navigate to the Hub. Locate your model and click the Use button. Restart Jan and navigate to the Hub. Locate your model and click the Use button.
![start-model](assets/configure-local-server.png)
## Assistance and Support ## Assistance and Support
If you have questions or are looking for more preconfigured GGUF models, please feel free to join our [Discord community](https://discord.gg/Dt7MxDyNNZ) for support, updates, and discussions. If you have questions or are looking for more preconfigured GGUF models, please feel free to join our [Discord community](https://discord.gg/Dt7MxDyNNZ) for support, updates, and discussions.