From f64ae3b900df63018a385bb0b0f51453f7a555b6 Mon Sep 17 00:00:00 2001
From: Desmond Sow <desmondsow@hotmail.com>
Date: Wed, 18 Mar 2026 15:02:47 +0800
Subject: [PATCH] feat(provider): add OpenVINO Model Server provider (#2193)

add OpenVINO Model Server provider
---
 README.md                     | 76 +++++++++++++++++++++++++++++++++++
 nanobot/cli/commands.py       |  8 ++++
 nanobot/config/schema.py      |  1 +
 nanobot/providers/registry.py | 11 +++++
 4 files changed, 96 insertions(+)

diff --git a/README.md b/README.md
index 64ae157..52d4504 100644
--- a/README.md
+++ b/README.md
@@ -803,6 +803,7 @@ Config file: `~/.nanobot/config.json`
 | `moonshot` | LLM (Moonshot/Kimi) | [platform.moonshot.cn](https://platform.moonshot.cn) |
 | `zhipu` | LLM (Zhipu GLM) | [open.bigmodel.cn](https://open.bigmodel.cn) |
 | `ollama` | LLM (local, Ollama) | — |
+| `ovms` | LLM (local, OpenVINO Model Server) | [docs.openvino.ai](https://docs.openvino.ai/2026/model-server/ovms_docs_llm_quickstart.html) |
 | `vllm` | LLM (local, any OpenAI-compatible server) | — |
 | `openai_codex` | LLM (Codex, OAuth) | `nanobot provider login openai-codex` |
 | `github_copilot` | LLM (GitHub Copilot, OAuth) | `nanobot provider login github-copilot` |
@@ -938,6 +939,81 @@ ollama run llama3.2
 
 </details>
 
+<details>
+<summary><b>OpenVINO Model Server (local / OpenAI-compatible)</b></summary>
+
+Run LLMs locally on Intel GPUs using [OpenVINO Model Server](https://docs.openvino.ai/2026/model-server/ovms_docs_llm_quickstart.html). OVMS exposes an OpenAI-compatible API at `/v3`.
+
+> Requires Docker and an Intel GPU with driver access (`/dev/dri`).
+
+**1. Pull the model** (example):
+
+```bash
+mkdir -p ov/models && cd ov
+
+docker run -d \
+  --rm \
+  --user $(id -u):$(id -g) \
+  -v $(pwd)/models:/models \
+  openvino/model_server:latest-gpu \
+  --pull \
+  --model_name openai/gpt-oss-20b \
+  --model_repository_path /models \
+  --source_model OpenVINO/gpt-oss-20b-int4-ov \
+  --task text_generation \
+  --tool_parser gptoss \
+  --reasoning_parser gptoss \
+  --enable_prefix_caching true \
+  --target_device GPU
+```
+
+> This downloads the model weights. Wait for the container to finish before proceeding.
+
+**2. Start the server** (example):
+
+```bash
+docker run -d \
+  --rm \
+  --name ovms \
+  --user $(id -u):$(id -g) \
+  -p 8000:8000 \
+  -v $(pwd)/models:/models \
+  --device /dev/dri \
+  --group-add=$(stat -c "%g" /dev/dri/render* | head -n 1) \
+  openvino/model_server:latest-gpu \
+  --rest_port 8000 \
+  --model_name openai/gpt-oss-20b \
+  --model_repository_path /models \
+  --source_model OpenVINO/gpt-oss-20b-int4-ov \
+  --task text_generation \
+  --tool_parser gptoss \
+  --reasoning_parser gptoss \
+  --enable_prefix_caching true \
+  --target_device GPU
+```
+
+**3. Add to config** (partial — merge into `~/.nanobot/config.json`):
+
+```json
+{
+  "providers": {
+    "ovms": {
+      "apiBase": "http://localhost:8000/v3"
+    }
+  },
+  "agents": {
+    "defaults": {
+      "provider": "ovms",
+      "model": "openai/gpt-oss-20b"
+    }
+  }
+}
+```
+
+> OVMS is a local server — no API key required. Supports tool calling (`--tool_parser gptoss`), reasoning (`--reasoning_parser gptoss`), and streaming.
+> See the [official OVMS docs](https://docs.openvino.ai/2026/model-server/ovms_docs_llm_quickstart.html) for more details.
+</details>
+
 <details>
 <summary><b>vLLM (local / OpenAI-compatible)</b></summary>
 
diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py
index b915ce9..db348ed 100644
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -409,6 +409,14 @@ def _make_provider(config: Config):
             api_base=p.api_base,
             default_model=model,
         )
+    # OpenVINO Model Server: direct OpenAI-compatible endpoint at /v3
+    elif provider_name == "ovms":
+        from nanobot.providers.custom_provider import CustomProvider
+        provider = CustomProvider(
+            api_key=p.api_key if p else "no-key",
+            api_base=config.get_api_base(model) or "http://localhost:8000/v3",
+            default_model=model,
+        )
     else:
         from nanobot.providers.litellm_provider import LiteLLMProvider
         from nanobot.providers.registry import find_by_name
diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py
index 9c841ca..58ead15 100644
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -70,6 +70,7 @@ class ProvidersConfig(Base):
     dashscope: ProviderConfig = Field(default_factory=ProviderConfig)
     vllm: ProviderConfig = Field(default_factory=ProviderConfig)
     ollama: ProviderConfig = Field(default_factory=ProviderConfig)  # Ollama local models
+    ovms: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenVINO Model Server (OVMS)
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     minimax: ProviderConfig = Field(default_factory=ProviderConfig)
diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.py
index 825653f..9cc430b 100644
--- a/nanobot/providers/registry.py
+++ b/nanobot/providers/registry.py
@@ -452,6 +452,17 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
+    # === OpenVINO Model Server (direct, local, OpenAI-compatible at /v3) ===
+    ProviderSpec(
+        name="ovms",
+        keywords=("openvino", "ovms"),
+        env_key="",
+        display_name="OpenVINO Model Server",
+        litellm_prefix="",
+        is_direct=True,
+        is_local=True,
+        default_api_base="http://localhost:8000/v3",
+    ),
     # === Auxiliary (not a primary LLM provider) ============================
     # Groq: mainly used for Whisper voice transcription, also usable for LLM.
     # Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback.