AI Agent Hub
Back to plugins
🤖

dsh-vector-search

Model Inference Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install satan9394/dsh-vector-search

Paste the following prompt into your AI chat to install this plugin:

To install this plugin in DeepSeek Harness, run dsh plugin install satan9394/dsh-vector-search; the full source code is available at https://github.com/satan9394/dsh-vector-search .

About this plugin

dsh-vector-search is a vector-search plugin in the DeepSeek Harness ecosystem, aimed squarely at the model-inference category. It wraps vector retrieval into Harness workflows so that steps requiring semantic search or approximate matching can be plugged in directly rather than bolted on as a separate service at the application layer.

Its core role is to provide vector-search support inside a Harness inference pipeline. The plugin follows the standard Harness plugin interface, is released under the MIT license, and lets developers activate it on demand to match query vectors against a target collection—covering common scenarios such as semantic question answering and retrieval-augmented inference.

It is best suited for developers who are building model-inference workflows on DeepSeek Harness and need a vector-retrieval step in their pipeline. If your Harness orchestration already chains multiple inference stages and you are looking for a lightweight, plug-and-play vector-search component to fill that gap, dsh-vector-search is a natural fit.

Use Cases

  • Plug a vector-retrieval step into a Harness inference pipeline
  • Invoke the plugin for semantic or approximate matching on demand
  • Fill the vector-matching gap in a multi-step inference chain

Best For

  • Developers building model-inference workflows on DeepSeek Harness
  • Developers whose pipelines already include a vector-retrieval step
  • Developers looking for a lightweight, plug-and-play vector-search component