Merge pull request trypear#140 from Madhav160804/ollama-model-selection

Added Ollama Model Check for installed models

extensions/void/src/common/sendLLMMessage.ts

@@ -237,39 +237,56 @@ export const sendOllamaMsg: SendLLMMessageFnTypeInternal = ({ messages, onText,
 	let didAbort = false
 	let fullText = ""
 
-	// if abort is called, onFinalMessage is NOT called, and no later onTexts are called either
 	abortRef.current = () => {
 		didAbort = true;
 	};
 
 	const ollama = new Ollama({ host: voidConfig.ollama.endpoint })
 
-	ollama.chat({
-		model: voidConfig.ollama.model,
-		messages: messages,
-		stream: true,
-		options: { num_predict: parseMaxTokensStr(voidConfig.default.maxTokens) } // this is max_tokens
-	})
+	// First check if model exists
+	ollama.list()
+		.then(async models => {
+			const installedModels = models.models.map(m => m.name.replace(/:latest$/, ''))
+			const modelExists = installedModels.some(m => m.startsWith(voidConfig.ollama.model));
+			if (!modelExists) {
+				const errorMessage = `The model "${voidConfig.ollama.model}" is not available locally. Please run 'ollama pull ${voidConfig.ollama.model}' to download it first or
+				try selecting one from the Installed models: ${installedModels.join(', ')}`;
+				onText(errorMessage, errorMessage);
+				onFinalMessage(errorMessage);
+				return Promise.reject();
+			}
+
+			return ollama.chat({
+				model: voidConfig.ollama.model,
+				messages: messages,
+				stream: true,
+				options: { num_predict: parseMaxTokensStr(voidConfig.default.maxTokens) }
+			});
+		})
 		.then(async stream => {
+			if (!stream) return;
+
 			abortRef.current = () => {
-				// stream.abort()
 				didAbort = true
 			}
-			// iterate through the stream
 			for await (const chunk of stream) {
 				if (didAbort) return;
 				const newText = chunk.message.content;
 				fullText += newText;
 				onText(newText, fullText);
 			}
 			onFinalMessage(fullText);
-
 		})
-		// when error/fail
 		.catch(error => {
-			onError(error)
-		})
-
+			// Check if the error is a connection error
+			if (error instanceof Error && error.message.includes('Failed to fetch')) {
+				const errorMessage = 'Ollama service is not running. Please start the Ollama service and try again.';
+				onText(errorMessage, errorMessage);
+				onFinalMessage(errorMessage);
+			} else if (error) {
+				onError(error);
+			}
+		});
 };
 
 // Greptile

extensions/void/src/webviews/common/contextForConfig.tsx

@@ -119,11 +119,11 @@ const voidConfigInfo: Record<
 			'http://127.0.0.1:11434'
 		),
 		// TODO we should allow user to select model inside Void, but for now we'll just let them handle the Ollama setup on their own
-		// model: configEnum(
-		// 	'Ollama model to use.',
-		// 	'llama3.1',
-		// 	["codegemma", "codegemma:2b", "codegemma:7b", "codellama", "codellama:7b", "codellama:13b", "codellama:34b", "codellama:70b", "codellama:code", "codellama:python", "command-r", "command-r:35b", "command-r-plus", "command-r-plus:104b", "deepseek-coder-v2", "deepseek-coder-v2:16b", "deepseek-coder-v2:236b", "falcon2", "falcon2:11b", "firefunction-v2", "firefunction-v2:70b", "gemma", "gemma:2b", "gemma:7b", "gemma2", "gemma2:2b", "gemma2:9b", "gemma2:27b", "llama2", "llama2:7b", "llama2:13b", "llama2:70b", "llama3", "llama3:8b", "llama3:70b", "llama3-chatqa", "llama3-chatqa:8b", "llama3-chatqa:70b", "llama3-gradient", "llama3-gradient:8b", "llama3-gradient:70b", "llama3.1", "llama3.1:8b", "llama3.1:70b", "llama3.1:405b", "llava", "llava:7b", "llava:13b", "llava:34b", "llava-llama3", "llava-llama3:8b", "llava-phi3", "llava-phi3:3.8b", "mistral", "mistral:7b", "mistral-large", "mistral-large:123b", "mistral-nemo", "mistral-nemo:12b", "mixtral", "mixtral:8x7b", "mixtral:8x22b", "moondream", "moondream:1.8b", "openhermes", "openhermes:v2.5", "phi3", "phi3:3.8b", "phi3:14b", "phi3.5", "phi3.5:3.8b", "qwen", "qwen:7b", "qwen:14b", "qwen:32b", "qwen:72b", "qwen:110b", "qwen2", "qwen2:0.5b", "qwen2:1.5b", "qwen2:7b", "qwen2:72b", "smollm", "smollm:135m", "smollm:360m", "smollm:1.7b"] as const
-		// ),
+		model: configEnum(
+			'Ollama model to use.',
+			'llama3.1',
+			["codegemma", "codegemma:2b", "codegemma:7b", "codellama", "codellama:7b", "codellama:13b", "codellama:34b", "codellama:70b", "codellama:code", "codellama:python", "command-r", "command-r:35b", "command-r-plus", "command-r-plus:104b", "deepseek-coder-v2", "deepseek-coder-v2:16b", "deepseek-coder-v2:236b", "falcon2", "falcon2:11b", "firefunction-v2", "firefunction-v2:70b", "gemma", "gemma:2b", "gemma:7b", "gemma2", "gemma2:2b", "gemma2:9b", "gemma2:27b", "llama2", "llama2:7b", "llama2:13b", "llama2:70b", "llama3", "llama3:8b", "llama3:70b", "llama3-chatqa", "llama3-chatqa:8b", "llama3-chatqa:70b", "llama3-gradient", "llama3-gradient:8b", "llama3-gradient:70b", "llama3.1", "llama3.2", "llama3.1:8b", "llama3.1:70b", "llama3.1:405b", "llava", "llava:7b", "llava:13b", "llava:34b", "llava-llama3", "llava-llama3:8b", "llava-phi3", "llava-phi3:3.8b", "mistral", "mistral:7b", "mistral-large", "mistral-large:123b", "mistral-nemo", "mistral-nemo:12b", "mixtral", "mixtral:8x7b", "mixtral:8x22b", "moondream", "moondream:1.8b", "openhermes", "openhermes:v2.5", "phi3", "phi3:3.8b", "phi3:14b", "phi3.5", "phi3.5:3.8b", "qwen", "qwen:7b", "qwen:14b", "qwen:32b", "qwen:72b", "qwen:110b", "qwen2", "qwen2:0.5b", "qwen2:1.5b", "qwen2:7b", "qwen2:72b", "smollm", "smollm:135m", "smollm:360m", "smollm:1.7b"] as const
+		),
 	},
 	openRouter: {
 		model: configString(