dsh-vector-search
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
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.