[PR #137] [MERGED] enh: Add Valves support to MLX Pipeline #322

New Issue

2026-02-15T20:15:06-05:00

yindo commented

2026-02-15 20:15:06 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/pipelines/pull/137
Author: @justinh-rahb
Created: 6/30/2024
Status: ✅ Merged
Merged: 6/30/2024
Merged by: @tjbck

Base: main ← Head: mlx-pipeline-valves

📝 Commits (1)

7add7f5 Add Valves support

📊 Changes

1 file changed (+31 additions, -25 deletions)

View changed files

📝 examples/pipelines/providers/mlx_pipeline.py (+31 -25)

📄 Description

Update MLX Pipeline (v1.2)

This PR updates the MLX Pipeline to version 1.2, adding support for the following Valves:

MLX_MODEL: Allows specifying the MLX model to be used in the pipeline.
- If not found locally, it will be downloaded (similar to Ollama's pull feature).
- Reloads the MLX pipeline when changed.
MLX_STOP: Define stop words that will trigger the inference to end.
HUGGINGFACE_TOKEN: Enables authentication with the Hugging Face Hub for downloading private models.

These new Valves enhance the pipeline's flexibility and functionality, allowing for:

Dynamic model selection and execution.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/pipelines/pull/137 **Author:** [@justinh-rahb](https://github.com/justinh-rahb) **Created:** 6/30/2024 **Status:** ✅ Merged **Merged:** 6/30/2024 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `main` ← **Head:** `mlx-pipeline-valves` --- ### 📝 Commits (1) - [`7add7f5`](https://github.com/open-webui/pipelines/commit/7add7f52952602f5ea43f94ae4076f63fd168a3c) Add Valves support ### 📊 Changes **1 file changed** (+31 additions, -25 deletions) <details> <summary>View changed files</summary> 📝 `examples/pipelines/providers/mlx_pipeline.py` (+31 -25) </details> ### 📄 Description ## Update MLX Pipeline (v1.2) This PR updates the MLX Pipeline to version 1.2, adding support for the following Valves: - **`MLX_MODEL`**: Allows specifying the MLX model to be used in the pipeline. - If not found locally, it will be downloaded (similar to Ollama's pull feature). - Reloads the MLX pipeline when changed. - **`MLX_STOP`**: Define stop words that will trigger the inference to end. - **`HUGGINGFACE_TOKEN`**: Enables authentication with the Hugging Face Hub for downloading private models. These new Valves enhance the pipeline's flexibility and functionality, allowing for: - Dynamic model selection and execution. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

yindo added the pull-request label 2026-02-15 20:15:06 -05:00

yindo closed this issue

2026-02-15 20:15:06 -05:00

yindo referenced this issue

2026-02-15 20:15:19 -05:00

[PR #322] [CLOSED] Fork #377

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: open-webui/pipelines#322