ollama-ai-provider-v2 1.6.0-beta.0 → 2.0.0

package/README.md

@@ -15,7 +15,7 @@ Use Ollama with the Vercel AI SDK, implementing the official Ollama API. This pr
 - ✅ **Advanced Features** - Tool calling, streaming, thinking mode, embeddings, and completion models
 - ✅ **Type Safety** - Full TypeScript support with comprehensive type definitions
 - ✅ **Zero Configuration** - Works out-of-the-box with sensible defaults
-- ✅ **Actively Maintained** - Regular updates and AI SDK v5+ compatibility
+- ✅ **Actively Maintained** - Regular updates and AI SDK v6+ compatibility
 
 ## Quick Start
 
@@ -82,19 +82,11 @@ const { text, toolCalls } = await generateText({
 Unique feature for models that support chain-of-thought reasoning:
 
 ```typescript
-// For most models - simple boolean
 const { text } = await generateText({
   model: ollama('deepseek-r1:7b'),
   providerOptions: { ollama: { think: true } },
   prompt: 'Solve this complex math problem step by step: 2x + 5 = 17',
 });
-
-// For GPT-OSS models - use thinking levels for trace length control
-const { text } = await generateText({
-  model: ollama('gpt-oss:7b'),
-  providerOptions: { ollama: { think: 'high' } }, // 'low', 'medium', or 'high'
-  prompt: 'Analyze this complex scenario in detail',
-});
 ```
 
 ### Advanced Ollama Options
@@ -182,7 +174,7 @@ Works with any model in your Ollama installation, including:
 
 - **Chat Models**: `llama3.2`, `mistral`, `phi4-mini`, `qwen2.5`, `codellama`, `gemma3`
 - **Vision Models**: `llava`, `llama3.2-vision`, `minicpm-v`
-- **Reasoning Models**: `deepseek-r1:7b`, `deepseek-r1:1.5b`, `deepseek-r1:8b`, `gpt-oss:7b`
+- **Reasoning Models**: `deepseek-r1:7b`, `deepseek-r1:1.5b`, `deepseek-r1:8b`
 - **Code Models**: `codellama:code`, `codellama:python`, `deepseek-coder-v2`
 - **Embedding Models**: `nomic-embed-text`, `all-minilm`, `mxbai-embed-large`
 
@@ -216,4 +208,4 @@ Contributions are welcome! Here's how to get started:
 
 Apache-2.0 © [nordwestt](https://github.com/nordwestt/ollama-ai-provider-v2)
 
-See [LICENSE.md](./LICENSE.md) for details.
+See [LICENSE.md](./LICENSE.md) for details.

package/dist/index.d.mts

@@ -1,14 +1,10 @@
-import { ProviderV2, LanguageModelV2, EmbeddingModelV2 } from '@ai-sdk/provider';
+import { ProviderV3, LanguageModelV3, EmbeddingModelV3 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
 
 type OllamaChatModelId = "athene-v2" | "athene-v2:72b" | "aya-expanse" | "aya-expanse:8b" | "aya-expanse:32b" | "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" | "command-r7b" | "command-r7b:7b" | "deepseek-r1" | "deepseek-r1:1.5b" | "deepseek-r1:7b" | "deepseek-r1:8b" | "deepseek-r1:14b" | "deepseek-r1:32b" | "deepseek-r1:70b" | "deepseek-r1:671b" | "deepseek-coder-v2" | "deepseek-coder-v2:16b" | "deepseek-coder-v2:236b" | "deepseek-v3" | "deepseek-v3:671b" | "devstral" | "devstral:24b" | "dolphin3" | "dolphin3:8b" | "exaone3.5" | "exaone3.5:2.4b" | "exaone3.5:7.8b" | "exaone3.5:32b" | "falcon2" | "falcon2:11b" | "falcon3" | "falcon3:1b" | "falcon3:3b" | "falcon3:7b" | "falcon3:10b" | "firefunction-v2" | "firefunction-v2:70b" | "gemma" | "gemma:2b" | "gemma:7b" | "gemma2" | "gemma2:2b" | "gemma2:9b" | "gemma2:27b" | "gemma3" | "gemma3:1b" | "gemma3:4b" | "gemma3:12b" | "gemma3:27b" | "granite3-dense" | "granite3-dense:2b" | "granite3-dense:8b" | "granite3-guardian" | "granite3-guardian:2b" | "granite3-guardian:8b" | "granite3-moe" | "granite3-moe:1b" | "granite3-moe:3b" | "granite3.1-dense" | "granite3.1-dense:2b" | "granite3.1-dense:8b" | "granite3.1-moe" | "granite3.1-moe:1b" | "granite3.1-moe:3b" | "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" | "llama3.2" | "llama3.2:1b" | "llama3.2:3b" | "llama3.2-vision" | "llama3.2-vision:11b" | "llama3.2-vision:90b" | "llama3.3" | "llama3.3:70b" | "llama4" | "llama4:16x17b" | "llama4:128x17b" | "llama-guard3" | "llama-guard3:1b" | "llama-guard3:8b" | "llava" | "llava:7b" | "llava:13b" | "llava:34b" | "llava-llama3" | "llava-llama3:8b" | "llava-phi3" | "llava-phi3:3.8b" | "marco-o1" | "marco-o1:7b" | "mistral" | "mistral:7b" | "mistral-large" | "mistral-large:123b" | "mistral-nemo" | "mistral-nemo:12b" | "mistral-small" | "mistral-small:22b" | "mixtral" | "mixtral:8x7b" | "mixtral:8x22b" | "moondream" | "moondream:1.8b" | "openhermes" | "openhermes:v2.5" | "nemotron" | "nemotron:70b" | "nemotron-mini" | "nemotron-mini:4b" | "olmo" | "olmo:7b" | "olmo:13b" | "opencoder" | "opencoder:1.5b" | "opencoder:8b" | "phi3" | "phi3:3.8b" | "phi3:14b" | "phi3.5" | "phi3.5:3.8b" | "phi4" | "phi4:14b" | "qwen" | "qwen:7b" | "qwen:14b" | "qwen:32b" | "qwen:72b" | "qwen:110b" | "qwen2" | "qwen2:0.5b" | "qwen2:1.5b" | "qwen2:7b" | "qwen2:72b" | "qwen2.5" | "qwen2.5:0.5b" | "qwen2.5:1.5b" | "qwen2.5:3b" | "qwen2.5:7b" | "qwen2.5:14b" | "qwen2.5:32b" | "qwen2.5:72b" | "qwen2.5-coder" | "qwen2.5-coder:0.5b" | "qwen2.5-coder:1.5b" | "qwen2.5-coder:3b" | "qwen2.5-coder:7b" | "qwen2.5-coder:14b" | "qwen2.5-coder:32b" | "qwen3" | "qwen3:0.6b" | "qwen3:1.7b" | "qwen3:4b" | "qwen3:8b" | "qwen3:14b" | "qwen3:30b" | "qwen3:32b" | "qwen3:235b" | "qwq" | "qwq:32b" | "sailor2" | "sailor2:1b" | "sailor2:8b" | "sailor2:20b" | "shieldgemma" | "shieldgemma:2b" | "shieldgemma:9b" | "shieldgemma:27b" | "smallthinker" | "smallthinker:3b" | "smollm" | "smollm:135m" | "smollm:360m" | "smollm:1.7b" | "tinyllama" | "tinyllama:1.1b" | "tulu3" | "tulu3:8b" | "tulu3:70b" | (string & {});
 declare const ollamaProviderOptions: z.ZodObject<{
-    think: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodEnum<{
-        low: "low";
-        medium: "medium";
-        high: "high";
-    }>]>>;
+    think: z.ZodOptional<z.ZodBoolean>;
     options: z.ZodOptional<z.ZodObject<{
         num_ctx: z.ZodOptional<z.ZodNumber>;
         repeat_last_n: z.ZodOptional<z.ZodNumber>;
@@ -31,12 +27,9 @@ interface OllamaCompletionSettings {
      * the model's thinking from the model's output. When disabled, the model will not think
      * and directly output the content.
      *
-     * For GPT-OSS models: accepts "low", "medium", or "high" to tune trace length.
-     * For other models: accepts boolean true/false.
-     *
-     * Only supported by certain models like DeepSeek R1, Qwen 3, and GPT-OSS.
+     * Only supported by certain models like DeepSeek R1 and Qwen 3.
      */
-    think?: boolean | "low" | "medium" | "high";
+    think?: boolean;
     /**
      * Echo back the prompt in addition to the completion.
      */
@@ -72,36 +65,44 @@ interface OllamaEmbeddingSettings {
   monitor and detect abuse. Learn more.
   */
     user?: string;
+    /**
+  Whether to truncate input text to fit within model's context length.
+     */
+    truncate?: boolean;
+    /**
+  How long to keep the model loaded in memory (e.g., "5m" for 5 minutes).
+     */
+    keepAlive?: string;
 }
 
-interface OllamaProvider extends ProviderV2 {
-    (modelId: OllamaChatModelId): LanguageModelV2;
+interface OllamaProvider extends ProviderV3 {
+    (modelId: OllamaChatModelId): LanguageModelV3;
     /**
   Creates an Ollama model for text generation.
      */
-    languageModel(modelId: OllamaChatModelId): LanguageModelV2;
+    languageModel(modelId: OllamaChatModelId): LanguageModelV3;
     /**
   Creates an Ollama chat model for text generation.
      */
-    chat(modelId: OllamaChatModelId, settings?: OllamaProviderOptions): LanguageModelV2;
+    chat(modelId: OllamaChatModelId, settings?: OllamaProviderOptions): LanguageModelV3;
     /**
   Creates an Ollama completion model for text generation.
      */
-    completion(modelId: OllamaCompletionModelId, settings?: OllamaCompletionSettings): LanguageModelV2;
+    completion(modelId: OllamaCompletionModelId, settings?: OllamaCompletionSettings): LanguageModelV3;
     /**
   Creates a model for text embeddings.
      */
-    embedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV2<string>;
+    embedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV3;
     /**
   Creates a model for text embeddings.
   
   @deprecated Use `textEmbeddingModel` instead.
      */
-    textEmbedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV3;
     /**
   Creates a model for text embeddings.
      */
-    textEmbeddingModel(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbeddingModel(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV3;
 }
 interface OllamaProviderSettings {
     /**
@@ -153,11 +154,7 @@ declare const ollamaEmbeddingProviderOptions: z.ZodObject<{
 type OllamaEmbeddingProviderOptions = z.infer<typeof ollamaEmbeddingProviderOptions>;
 
 declare const ollamaCompletionProviderOptions: z.ZodObject<{
-    think: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodEnum<{
-        low: "low";
-        medium: "medium";
-        high: "high";
-    }>]>>;
+    think: z.ZodOptional<z.ZodBoolean>;
     user: z.ZodOptional<z.ZodString>;
     suffix: z.ZodOptional<z.ZodString>;
     echo: z.ZodOptional<z.ZodBoolean>;

package/dist/index.d.ts

@@ -1,14 +1,10 @@
-import { ProviderV2, LanguageModelV2, EmbeddingModelV2 } from '@ai-sdk/provider';
+import { ProviderV3, LanguageModelV3, EmbeddingModelV3 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
 
 type OllamaChatModelId = "athene-v2" | "athene-v2:72b" | "aya-expanse" | "aya-expanse:8b" | "aya-expanse:32b" | "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" | "command-r7b" | "command-r7b:7b" | "deepseek-r1" | "deepseek-r1:1.5b" | "deepseek-r1:7b" | "deepseek-r1:8b" | "deepseek-r1:14b" | "deepseek-r1:32b" | "deepseek-r1:70b" | "deepseek-r1:671b" | "deepseek-coder-v2" | "deepseek-coder-v2:16b" | "deepseek-coder-v2:236b" | "deepseek-v3" | "deepseek-v3:671b" | "devstral" | "devstral:24b" | "dolphin3" | "dolphin3:8b" | "exaone3.5" | "exaone3.5:2.4b" | "exaone3.5:7.8b" | "exaone3.5:32b" | "falcon2" | "falcon2:11b" | "falcon3" | "falcon3:1b" | "falcon3:3b" | "falcon3:7b" | "falcon3:10b" | "firefunction-v2" | "firefunction-v2:70b" | "gemma" | "gemma:2b" | "gemma:7b" | "gemma2" | "gemma2:2b" | "gemma2:9b" | "gemma2:27b" | "gemma3" | "gemma3:1b" | "gemma3:4b" | "gemma3:12b" | "gemma3:27b" | "granite3-dense" | "granite3-dense:2b" | "granite3-dense:8b" | "granite3-guardian" | "granite3-guardian:2b" | "granite3-guardian:8b" | "granite3-moe" | "granite3-moe:1b" | "granite3-moe:3b" | "granite3.1-dense" | "granite3.1-dense:2b" | "granite3.1-dense:8b" | "granite3.1-moe" | "granite3.1-moe:1b" | "granite3.1-moe:3b" | "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" | "llama3.2" | "llama3.2:1b" | "llama3.2:3b" | "llama3.2-vision" | "llama3.2-vision:11b" | "llama3.2-vision:90b" | "llama3.3" | "llama3.3:70b" | "llama4" | "llama4:16x17b" | "llama4:128x17b" | "llama-guard3" | "llama-guard3:1b" | "llama-guard3:8b" | "llava" | "llava:7b" | "llava:13b" | "llava:34b" | "llava-llama3" | "llava-llama3:8b" | "llava-phi3" | "llava-phi3:3.8b" | "marco-o1" | "marco-o1:7b" | "mistral" | "mistral:7b" | "mistral-large" | "mistral-large:123b" | "mistral-nemo" | "mistral-nemo:12b" | "mistral-small" | "mistral-small:22b" | "mixtral" | "mixtral:8x7b" | "mixtral:8x22b" | "moondream" | "moondream:1.8b" | "openhermes" | "openhermes:v2.5" | "nemotron" | "nemotron:70b" | "nemotron-mini" | "nemotron-mini:4b" | "olmo" | "olmo:7b" | "olmo:13b" | "opencoder" | "opencoder:1.5b" | "opencoder:8b" | "phi3" | "phi3:3.8b" | "phi3:14b" | "phi3.5" | "phi3.5:3.8b" | "phi4" | "phi4:14b" | "qwen" | "qwen:7b" | "qwen:14b" | "qwen:32b" | "qwen:72b" | "qwen:110b" | "qwen2" | "qwen2:0.5b" | "qwen2:1.5b" | "qwen2:7b" | "qwen2:72b" | "qwen2.5" | "qwen2.5:0.5b" | "qwen2.5:1.5b" | "qwen2.5:3b" | "qwen2.5:7b" | "qwen2.5:14b" | "qwen2.5:32b" | "qwen2.5:72b" | "qwen2.5-coder" | "qwen2.5-coder:0.5b" | "qwen2.5-coder:1.5b" | "qwen2.5-coder:3b" | "qwen2.5-coder:7b" | "qwen2.5-coder:14b" | "qwen2.5-coder:32b" | "qwen3" | "qwen3:0.6b" | "qwen3:1.7b" | "qwen3:4b" | "qwen3:8b" | "qwen3:14b" | "qwen3:30b" | "qwen3:32b" | "qwen3:235b" | "qwq" | "qwq:32b" | "sailor2" | "sailor2:1b" | "sailor2:8b" | "sailor2:20b" | "shieldgemma" | "shieldgemma:2b" | "shieldgemma:9b" | "shieldgemma:27b" | "smallthinker" | "smallthinker:3b" | "smollm" | "smollm:135m" | "smollm:360m" | "smollm:1.7b" | "tinyllama" | "tinyllama:1.1b" | "tulu3" | "tulu3:8b" | "tulu3:70b" | (string & {});
 declare const ollamaProviderOptions: z.ZodObject<{
-    think: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodEnum<{
-        low: "low";
-        medium: "medium";
-        high: "high";
-    }>]>>;
+    think: z.ZodOptional<z.ZodBoolean>;
     options: z.ZodOptional<z.ZodObject<{
         num_ctx: z.ZodOptional<z.ZodNumber>;
         repeat_last_n: z.ZodOptional<z.ZodNumber>;
@@ -31,12 +27,9 @@ interface OllamaCompletionSettings {
      * the model's thinking from the model's output. When disabled, the model will not think
      * and directly output the content.
      *
-     * For GPT-OSS models: accepts "low", "medium", or "high" to tune trace length.
-     * For other models: accepts boolean true/false.
-     *
-     * Only supported by certain models like DeepSeek R1, Qwen 3, and GPT-OSS.
+     * Only supported by certain models like DeepSeek R1 and Qwen 3.
      */
-    think?: boolean | "low" | "medium" | "high";
+    think?: boolean;
     /**
      * Echo back the prompt in addition to the completion.
      */
@@ -72,36 +65,44 @@ interface OllamaEmbeddingSettings {
   monitor and detect abuse. Learn more.
   */
     user?: string;
+    /**
+  Whether to truncate input text to fit within model's context length.
+     */
+    truncate?: boolean;
+    /**
+  How long to keep the model loaded in memory (e.g., "5m" for 5 minutes).
+     */
+    keepAlive?: string;
 }
 
-interface OllamaProvider extends ProviderV2 {
-    (modelId: OllamaChatModelId): LanguageModelV2;
+interface OllamaProvider extends ProviderV3 {
+    (modelId: OllamaChatModelId): LanguageModelV3;
     /**
   Creates an Ollama model for text generation.
      */
-    languageModel(modelId: OllamaChatModelId): LanguageModelV2;
+    languageModel(modelId: OllamaChatModelId): LanguageModelV3;
     /**
   Creates an Ollama chat model for text generation.
      */
-    chat(modelId: OllamaChatModelId, settings?: OllamaProviderOptions): LanguageModelV2;
+    chat(modelId: OllamaChatModelId, settings?: OllamaProviderOptions): LanguageModelV3;
     /**
   Creates an Ollama completion model for text generation.
      */
-    completion(modelId: OllamaCompletionModelId, settings?: OllamaCompletionSettings): LanguageModelV2;
+    completion(modelId: OllamaCompletionModelId, settings?: OllamaCompletionSettings): LanguageModelV3;
     /**
   Creates a model for text embeddings.
      */
-    embedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV2<string>;
+    embedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV3;
     /**
   Creates a model for text embeddings.
   
   @deprecated Use `textEmbeddingModel` instead.
      */
-    textEmbedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbedding(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV3;
     /**
   Creates a model for text embeddings.
      */
-    textEmbeddingModel(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbeddingModel(modelId: OllamaEmbeddingModelId, settings?: OllamaEmbeddingSettings): EmbeddingModelV3;
 }
 interface OllamaProviderSettings {
     /**
@@ -153,11 +154,7 @@ declare const ollamaEmbeddingProviderOptions: z.ZodObject<{
 type OllamaEmbeddingProviderOptions = z.infer<typeof ollamaEmbeddingProviderOptions>;
 
 declare const ollamaCompletionProviderOptions: z.ZodObject<{
-    think: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodEnum<{
-        low: "low";
-        medium: "medium";
-        high: "high";
-    }>]>>;
+    think: z.ZodOptional<z.ZodBoolean>;
     user: z.ZodOptional<z.ZodString>;
     suffix: z.ZodOptional<z.ZodString>;
     echo: z.ZodOptional<z.ZodBoolean>;