Louis 489e8aab24
Sync release 0.4.9 to dev (#2407)
* fix: move tensorrt executable to engine (#2400)

* fix: move tensorrt executable to engine

Signed-off-by: James <james@jan.ai>

* some update

Signed-off-by: hiro <hiro@jan.ai>

* chore: bump tensorrt version

* fix: wrong destroy path

* fix: install extensions in parallel

* chore: update path for tensorrt engine (#2404)

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>

---------

Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: Louis <louis@jan.ai>

* Release/v0.4.9 (#2421)

* fix: turn off experimental settings should also turn off quick ask (#2411)

* fix: app glitches 1s generating response before starting model (#2412)

* fix: disable experimental feature should also disable vulkan (#2414)

* fix: model load stuck on windows when can't get CPU core count (#2413)

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>

* feat: TensorRT-LLM engine update support (#2415)

* fix: engine update

* chore: add remove prepopulated models

Signed-off-by: James <james@jan.ai>

* update tinyjensen url

Signed-off-by: James <james@jan.ai>

* update llamacorn

Signed-off-by: James <james@jan.ai>

* update Mistral 7B Instruct v0.1 int4

Signed-off-by: James <james@jan.ai>

* update tensorrt

Signed-off-by: James <james@jan.ai>

* update

Signed-off-by: hiro <hiro@jan.ai>

* update

Signed-off-by: James <james@jan.ai>

* prettier

Signed-off-by: James <james@jan.ai>

* update mistral config

Signed-off-by: James <james@jan.ai>

* fix some lint

Signed-off-by: James <james@jan.ai>

---------

Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>

* Tensorrt LLM disable turing support (#2418)

Co-authored-by: Hien To <tominhhien97@gmail.com>

* chore: add prompt template tensorrtllm (#2375)

* chore: add prompt template tensorrtllm

* Add Prompt template for mistral and correct model metadata

---------

Co-authored-by: Hien To <tominhhien97@gmail.com>

* fix: correct tensorrt mistral model.json (#2419)

---------

Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>

---------

Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: NamH <NamNh0122@gmail.com>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-03-19 12:20:09 +07:00
..
2024-03-19 12:20:09 +07:00
2024-02-15 08:38:05 +07:00
2024-03-19 12:20:09 +07:00
2024-02-15 08:38:05 +07:00

@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";

// Node runtime
import * as node from "@janhq/core/node";

Build an Extension

  1. Download an extension template, for example, https://github.com/janhq/extension-template.

  2. Update the source code:

    1. Open index.ts in your code editor.
    2. Rename the extension class from SampleExtension to your preferred extension name.
    3. Import modules from the core package.
      import * as core from "@janhq/core";
      
    4. 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
          };
        }
      }
      
  3. Build the extension:

    1. Navigate to the extension directory.
    2. Install dependencies.
      yarn install
      
    3. Compile the source code. The following command keeps running in the terminal and rebuilds the extension when you modify the source code.
      yarn build
      
    4. Select the generated .tgz from Jan > Settings > Extension > Manual Installation.