ollama-ai-provider - npm Package Compare versions

Comparing version 1.1.0 to 1.2.0

dist/index.d.ts

 import { ProviderV1, LanguageModelV1, EmbeddingModelV1 } from '@ai-sdk/provider';
 
-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' | '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' | 'granite3-dense' | 'granite3-dense:2b' | 'granite3-dense:8b' | 'granite3-guardian' | 'granite3-guardian:2b' | 'granite3-guardian:8b' | 'granite3-moe' | 'granite3-moe:1b' | 'granite3-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' | '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' | 'opencoder' | 'opencoder:1.5b' | 'opencoder:8b' | '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' | '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' | 'qwq' | 'qwq:32b' | 'sailor2' | 'sailor2:1b' | 'sailor2:8b' | 'sailor2:20b' | 'shieldgemma' | 'shieldgemma:2b' | 'shieldgemma:9b' | 'shieldgemma:27b' | 'smollm' | 'smollm:135m' | 'smollm:360m' | 'smollm:1.7b' | 'tinyllama' | 'tinyllama:1.1b' | 'tulu3' | 'tulu3:8b' | 'tulu3:70b' | (string & NonNullable<unknown>);
+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-coder-v2' | 'deepseek-coder-v2:16b' | 'deepseek-coder-v2:236b' | 'deepseek-v3' | 'deepseek-v3:671b' | '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' | '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' | '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' | '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 & NonNullable<unknown>);
 interface OllamaChatSettings {
@@ -8,2 +8,4 @@ /**
      * default to maintain backward compatibility, disable it if you encounter any issues.
+     *
+     * @deprecated Use `simulateStreaming` instead.
      */
@@ -83,2 +85,9 @@ experimentalStreamTools?: boolean;
     /**
+     Simulates streaming by using a normal generate call and returning it as a stream.
+     Enable this if the model that you are using does not support streaming.
+  
+     Defaults to `false`.
+     */
+    simulateStreaming?: boolean;
+    /**
      * Whether to use structured outputs. Defaults to false.
@@ -112,3 +121,3 @@ *
 
-type OllamaEmbeddingModelId = 'all-minilm' | 'all-minilm:22m' | 'all-minilm:33m' | 'bge-large' | 'bge-m3' | 'mxbai-embed-large' | 'nomic-embed-text' | 'paraphrase-multilingual' | 'snowflake-arctic-embed' | 'snowflake-arctic-embed:110m' | 'snowflake-arctic-embed:137m' | 'snowflake-arctic-embed:22m' | 'snowflake-arctic-embed:335m' | 'snowflake-arctic-embed:33m' | 'snowflake-arctic-embed2' | 'snowflake-arctic-embed2:568m' | OllamaChatModelId | (string & NonNullable<unknown>);
+type OllamaEmbeddingModelId = 'all-minilm' | 'all-minilm:22m' | 'all-minilm:33m' | 'bge-large' | 'bge-m3' | 'granite-embedding' | 'granite-embedding:30m' | 'granite-embedding:278m' | 'mxbai-embed-large' | 'nomic-embed-text' | 'paraphrase-multilingual' | 'snowflake-arctic-embed' | 'snowflake-arctic-embed:110m' | 'snowflake-arctic-embed:137m' | 'snowflake-arctic-embed:22m' | 'snowflake-arctic-embed:335m' | 'snowflake-arctic-embed:33m' | 'snowflake-arctic-embed2' | 'snowflake-arctic-embed2:568m' | OllamaChatModelId | (string & NonNullable<unknown>);
 interface OllamaEmbeddingSettings {
@@ -115,0 +124,0 @@ maxEmbeddingsPerCall?: number;

dist/index.js

@@ -542,2 +542,45 @@ "use strict";
   async doStream(options) {
+    if (this.settings.simulateStreaming) {
+      const result = await this.doGenerate(options);
+      const simulatedStream = new ReadableStream({
+        start(controller) {
+          controller.enqueue({ type: "response-metadata", ...result.response });
+          if (result.text) {
+            controller.enqueue({
+              textDelta: result.text,
+              type: "text-delta"
+            });
+          }
+          if (result.toolCalls) {
+            for (const toolCall of result.toolCalls) {
+              controller.enqueue({
+                argsTextDelta: toolCall.args,
+                toolCallId: toolCall.toolCallId,
+                toolCallType: "function",
+                toolName: toolCall.toolName,
+                type: "tool-call-delta"
+              });
+              controller.enqueue({
+                type: "tool-call",
+                ...toolCall
+              });
+            }
+          }
+          controller.enqueue({
+            finishReason: result.finishReason,
+            logprobs: result.logprobs,
+            providerMetadata: result.providerMetadata,
+            type: "finish",
+            usage: result.usage
+          });
+          controller.close();
+        }
+      });
+      return {
+        rawCall: result.rawCall,
+        rawResponse: result.rawResponse,
+        stream: simulatedStream,
+        warnings: result.warnings
+      };
+    }
     const { args: body, type, warnings } = this.getArguments(options);
@@ -544,0 +587,0 @@ const { responseHeaders, value: response } = await (0, import_provider_utils5.postJsonToApi)({

package.json

 {
   "name": "ollama-ai-provider",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "description": "Vercel AI Provider for running LLMs locally using Ollama",
@@ -5,0 +5,0 @@ "main": "./dist/index.js",

No alert changes

Improved metrics

Total package byte prevSize

161033

increased by5.93%

Lines of code

1725

increased by5.89%

No dependency changes