opencode-eyes-nvidia: Integrating NVIDIA NIM Vision Capabilities into Text Models
This plugin provides visual reasoning capabilities for DeepSeek Harness, enabling text models to process images. Built on NVIDIA NIM, it integrates seven visual models, including MiniMax-M3, and supports automatic key rotation, MCP server packaging, and tools for image description and model queries. Installation requires Python ≥3.8, the Pillow library, and an NVIDIA API Key. Configuration is flexible, supporting multi-key rotation and ThinkingMode tuning, and it is loaded via cordis.patch.yml, making it suitable for scenarios that require cost-effective integration of multimodal capabilities.
Read MoreDeepSeek Harness Plugin: Integrating with Ant Digital MaaS and NVIDIA NIM
`dsh-cloud-model-providers` is a plugin for DeepSeek Harness (DSH) designed to simplify integration with Ant Digital MaaS and NVIDIA NIM. It reuses DSH built-in adapters and provides streaming model routing support through declarative configuration. Users need to provide API keys via environment variables or DSH settings, then select the corresponding route (for example, `ant-maas-responses` or `nvidia`). The plugin is compatible with DSH’s `llm-pi-ai` adapter and supports features such as streaming and tool calling. Note that it does not deploy containers, and protocol changes should be monitored.
Read More