[Feat] Add vllm support

pyproject.toml

@@ -64,9 +64,13 @@ gemini = [
 openai = [
     "openai==1.59.8",
 ]
+vllm = [
+    "vllm>=0.9.2",
+]
 all = [
     "google-genai>=0.2.0",
     "openai==1.59.8",
+    "vllm>=0.9.2",
 ]
 
 [tool.hatch.build.targets.wheel]
@@ -83,4 +87,9 @@ include = [
 "src/vision_parse/image_analysis.j2" = "vision_parse/image_analysis.j2"
 
 [tool.hatch.version]
-source = "vcs"
+source = "vcs"
+
+[tool.pytest.ini_options]
+markers = [
+    "integration: marks tests that exercise external services",
+]

src/vision_parse/constants.py

@@ -1,24 +1,25 @@
-from typing import Dict
-
-SUPPORTED_MODELS: Dict[str, str] = {
-    "llama3.2-vision:11b": "ollama",
-    "gpt-4o": "openai",
-    "gpt-4o-mini": "openai",
-    "gemini-2.5-pro": "gemini",
-    "gemini-2.5-flash": "gemini",
-    "gemini-2.0-flash": "gemini",
-}
-
-
-def discover_ollama_vision_models() -> Dict[str, str]:
-    try:
-        import ollama
-        from .model_detector import ModelDetector
-
-        client = ollama.Client()
-        detector = ModelDetector(client)
-        vision_models = detector.get_vision_models()
-
-        return {model: "ollama" for model in vision_models}
-    except Exception:
-        return {}
+from typing import Dict
+
+SUPPORTED_MODELS: Dict[str, str] = {
+    "llama3.2-vision:11b": "ollama",
+    "gpt-4o": "openai",
+    "gpt-4o-mini": "openai",
+    "gemini-2.5-pro": "gemini",
+    "gemini-2.5-flash": "gemini",
+    "gemini-2.0-flash": "gemini",
+    "unsloth/Mistral-Small-3.1-24B-Instruct-2503-bnb-4bit": "vllm",
+}
+
+
+def discover_ollama_vision_models() -> Dict[str, str]:
+    try:
+        import ollama
+        from .model_detector import ModelDetector
+
+        client = ollama.Client()
+        detector = ModelDetector(client)
+        vision_models = detector.get_vision_models()
+
+        return {model: "ollama" for model in vision_models}
+    except Exception:
+        return {}