This commit introduces a new field, `is_embedding`, to the `SessionInfo` structure to clearly mark sessions running dedicated embedding models. Key changes: - Adds `is_embedding` to the `SessionInfo` interface in `AIEngine.ts` and the Rust backend. - Updates the `loadLlamaModel` command signatures to pass this new flag. - Modifies the llama.cpp extension's **auto-unload logic** to explicitly **filter out** and **not unload** any currently loaded embedding models when a new text generation model is loaded. This is a critical performance fix to prevent the embedding model (e.g., used for RAG) from being repeatedly reloaded. Also includes minor code style cleanup/reformatting in `jan-provider-web/provider.ts` for improved readability.
@janhq/core
This module includes functions for communicating with core APIs, registering app extensions, and exporting type definitions.
Usage
Import the package
// Web / extension runtime
import * as core from '@janhq/core'
Build an Extension
-
Download an extension template, for example, https://github.com/menloresearch/extension-template.
-
Update the source code:
-
Open
index.tsin your code editor. -
Rename the extension class from
SampleExtensionto your preferred extension name. -
Import modules from the core package.
import * as core from '@janhq/core' -
In the
onLoad()method, add your code:// Example of listening to app events and providing customized inference logic: import * as core from '@janhq/core' export default class MyExtension extends BaseExtension { // On extension load onLoad() { core.events.on(MessageEvent.OnMessageSent, (data) => MyExtension.inference(data, this)) } // Customized inference logic private static inference(incomingMessage: MessageRequestData) { // Prepare customized message content const content: ThreadContent = { type: ContentType.Text, text: { value: "I'm Jan Assistant!", annotations: [], }, } // Modify message and send out const outGoingMessage: ThreadMessage = { ...incomingMessage, content, } } }
-
-
Build the extension:
- Navigate to the extension directory.
- Install dependencies.
yarn install - Compile the source code. The following command keeps running in the terminal and rebuilds the extension when you modify the source code.
yarn build - Select the generated .tgz from Jan > Settings > Extension > Manual Installation.