ai-sdk-ollama 0.8.0 → 0.9.0

package/CHANGELOG.md

@@ -1,5 +1,45 @@
 # Changelog
 
+## 0.9.0
+
+### Minor Changes
+
+- 35f19de: Add web search and web fetch tools for Ollama integration
+  - Add `webSearch` tool for performing web searches using Ollama's web search capabilities
+  - Add `webFetch` tool for fetching web content and URLs
+  - Support for both browser and Node.js environments
+  - Comprehensive integration tests and examples
+  - Updated documentation with usage examples and prerequisites
+
+## 0.8.1
+
+### Patch Changes
+
+- e57ddf2: ## Enhanced Function Renaming & Documentation Improvements
+
+  ### Function Renaming
+  - Renamed `generateTextOllama` to `generateText` (enhanced version from ai-sdk-ollama)
+  - Renamed `streamTextOllama` to `streamText` (enhanced version from ai-sdk-ollama)
+  - Maintains backward compatibility while providing clearer API
+
+  ### Documentation Improvements
+  - **README.md**: Complete restructure with better user flow
+    - Added Quick Start section with immediate installation and basic example
+    - Moved value proposition ("Why Choose") section earlier
+    - Added dedicated "Enhanced Tool Calling" section highlighting main differentiator
+    - Reorganized examples under "More Examples" for better progression
+    - Removed redundant content and improved clarity
+  - **packages/ai-sdk-ollama/README.md**: Applied same improvements
+    - Consistent structure with main README
+    - Better user journey from basic to advanced features
+    - Updated table of contents to match new structure
+
+  ### Key Benefits
+  - **Better Developer Experience**: Clearer function names and improved documentation flow
+  - **Enhanced Tool Calling**: Highlighted the main selling point with dedicated section
+  - **User-Friendly**: Users can now get started in 30 seconds and understand value immediately
+  - **Consistent**: Both READMEs now have the same improved structure and flow
+
 ## 0.8.0
 
 ### Minor Changes

package/README.md

@@ -7,30 +7,131 @@
 
 A Vercel AI SDK v5+ provider for Ollama built on the official `ollama` package. Type safe, future proof, with cross provider compatibility and native Ollama features.
 
-> **🚀 Reliable Tool Calling**: This provider includes built-in reliability features enabled by default, plus enhanced wrapper functions for guaranteed tool calling success:
->
-> - **Standard**: `generateText({ model: ollama('llama3.2'), tools, prompt })` - works with built-in reliability
-> - **Enhanced**: `generateTextOllama({ model: ollama('llama3.2'), tools, prompt })` - reliable tool calling
-> - **Streaming**: `streamTextOllama()` - enhanced streaming with tool awareness
->
-> **The Problem We Solve**: Standard Ollama providers often execute tools but return empty responses. Our enhanced functions guarantee complete, useful responses every time.
+## Quick Start
+
+```bash
+npm install ai-sdk-ollama ai@^5.0.0
+```
+
+```typescript
+import { ollama } from 'ai-sdk-ollama';
+import { generateText } from 'ai';
+
+// Works in both Node.js and browsers
+const { text } = await generateText({
+  model: ollama('llama3.2'),
+  prompt: 'Write a haiku about coding',
+  temperature: 0.8,
+});
+
+console.log(text);
+```
+
+## Why Choose AI SDK Ollama?
+
+- ✅ **Solves tool calling problems** - Response synthesis for reliable tool execution
+- ✅ **Enhanced wrapper functions** - `generateText` and `streamText` guarantees complete responses
+- ✅ **Built-in reliability** - Default reliability features enabled automatically
+- ✅ **Web search and fetch tools** - Built-in web search and fetch tools powered by [Ollama's web search API](https://ollama.com/blog/web-search). Perfect for getting current information and reducing hallucinations.
+- ✅ **Type-safe** - Full TypeScript support with strict typing
+- ✅ **Cross-environment** - Works in Node.js and browsers automatically
+- ✅ **Native Ollama power** - Access advanced features like `mirostat`, `repeat_penalty`, `num_ctx`
+- ✅ **Production ready** - Handles the core Ollama limitations other providers struggle with
+
+## Enhanced Tool Calling
+
+> **🚀 The Problem We Solve**: Standard Ollama providers often execute tools but return empty responses. Our enhanced functions guarantee complete, useful responses every time.
+
+```typescript
+import { generateText, streamText } from 'ai-sdk-ollama';
+
+// ✅ Enhanced generateText - guaranteed complete responses
+const { text } = await generateText({
+  model: ollama('llama3.2'),
+  tools: {
+    /* your tools */
+  },
+  prompt: 'Use the tools and explain the results',
+});
+
+// ✅ Enhanced streaming - tool-aware streaming
+const { textStream } = await streamText({
+  model: ollama('llama3.2'),
+  tools: {
+    /* your tools */
+  },
+  prompt: 'Stream with tools',
+});
+```
+
+## Web Search Tools
+
+> **🌐 New in v0.9.0**: Built-in web search and fetch tools powered by [Ollama's web search API](https://ollama.com/blog/web-search). Perfect for getting current information and reducing hallucinations.
+
+```typescript
+import { generateText } from 'ai';
+import { ollama } from 'ai-sdk-ollama';
+
+// 🔍 Web search for current information
+const { text } = await generateText({
+  model: ollama('qwen3-coder:480b-cloud'), // Cloud models recommended for web search
+  prompt: 'What are the latest developments in AI this week?',
+  tools: {
+    webSearch: ollama.tools.webSearch({ maxResults: 5 }),
+  },
+});
+
+// 📄 Fetch specific web content
+const { text: summary } = await generateText({
+  model: ollama('gpt-oss:120b-cloud'),
+  prompt: 'Summarize this article: https://example.com/article',
+  tools: {
+    webFetch: ollama.tools.webFetch({ maxContentLength: 5000 }),
+  },
+});
+
+// 🔄 Combine search and fetch for comprehensive research
+const { text: research } = await generateText({
+  model: ollama('gpt-oss:120b-cloud'),
+  prompt: 'Research recent TypeScript updates and provide a detailed analysis',
+  tools: {
+    webSearch: ollama.tools.webSearch({ maxResults: 3 }),
+    webFetch: ollama.tools.webFetch(),
+  },
+});
+```
+
+### Web Search Prerequisites
+
+1. **Ollama API Key**: Set `OLLAMA_API_KEY` environment variable
+2. **Cloud Models**: Use cloud models for optimal web search performance:
+   - `qwen3-coder:480b-cloud` - Best for general web search
+   - `gpt-oss:120b-cloud` - Best for complex reasoning with web data
+
+```bash
+# Set your API key
+export OLLAMA_API_KEY="your_api_key_here"
+
+# Get your API key from: https://ollama.com/account
+```
 
 ## Contents
 
 - [AI SDK Ollama Provider](#ai-sdk-ollama-provider)
+  - [Quick Start](#quick-start)
+  - [Why Choose AI SDK Ollama?](#why-choose-ai-sdk-ollama)
+  - [Enhanced Tool Calling](#enhanced-tool-calling)
+  - [Web Search Tools](#web-search-tools)
+    - [Web Search Prerequisites](#web-search-prerequisites)
   - [Contents](#contents)
   - [Prerequisites](#prerequisites)
-  - [Quick Start](#quick-start)
-    - [Installation](#installation)
-    - [Basic Usage](#basic-usage)
   - [Browser Support](#browser-support)
     - [Browser Usage](#browser-usage)
     - [Explicit Browser Import](#explicit-browser-import)
     - [CORS Configuration](#cors-configuration)
-  - [Key Features](#key-features)
+  - [More Examples](#more-examples)
     - [Cross Provider Compatibility](#cross-provider-compatibility)
     - [Native Ollama Power](#native-ollama-power)
-    - [Tool Calling Support](#tool-calling-support)
     - [Enhanced Tool Calling Wrappers](#enhanced-tool-calling-wrappers)
     - [Simple and Predictable](#simple-and-predictable)
   - [Advanced Features](#advanced-features)
@@ -78,16 +179,6 @@ const { text: advancedText } = await generateText({
 - AI SDK v5+ (`ai` package)
 - TypeScript 5.9+ (for TypeScript users)
 
-## Quick Start
-
-### Installation
-
-```bash
-npm install ai-sdk-ollama ai@^5.0.0
-```
-
-Ensure you have Ollama running locally:
-
 ```bash
 # Install Ollama from ollama.com
 ollama serve
@@ -96,39 +187,6 @@ ollama serve
 ollama pull llama3.2
 ```
 
-### Basic Usage
-
-```typescript
-import { ollama } from 'ai-sdk-ollama';
-import { generateText, streamText, embed } from 'ai';
-
-// Simple text generation
-const { text } = await generateText({
-  model: ollama('llama3.2'),
-  prompt: 'What is the capital of France?',
-});
-
-console.log(text); // "The capital of France is Paris."
-
-// Streaming responses
-const { textStream } = await streamText({
-  model: ollama('llama3.2'),
-  prompt: 'Tell me a story about a robot',
-});
-
-for await (const chunk of textStream) {
-  process.stdout.write(chunk);
-}
-
-// Embeddings
-const { embedding } = await embed({
-  model: ollama.embedding('nomic-embed-text'),
-  value: 'Hello world',
-});
-
-console.log(embedding.length); // 768 dimensions
-```
-
 ## Browser Support
 
 See the [browser example](../../examples/browser/).
@@ -175,7 +233,7 @@ OLLAMA_ORIGINS="http://localhost:3000,https://myapp.com" ollama serve
 
 **Recommended**: Use a development proxy (like Vite proxy) to avoid CORS issues entirely. See the browser example for a complete working setup.
 
-## Key Features
+## More Examples
 
 ### Cross Provider Compatibility
 
@@ -212,47 +270,17 @@ const { text } = await generateText({
 
 > **Parameter Precedence**: When both AI SDK parameters and Ollama options are specified, **Ollama options take precedence**. For example, if you set `temperature: 0.5` in Ollama options and `temperature: 0.8` in the `generateText` call, the final value will be `0.5`. This allows you to use standard AI SDK parameters for portability while having fine-grained control with Ollama-specific options when needed.
 
-### Tool Calling Support
-
-Ollama supports tool calling with compatible models.
-
-```typescript
-import { z } from 'zod';
-import { generateText, tool } from 'ai';
-import { ollama } from 'ai-sdk-ollama';
-
-const { text, toolCalls } = await generateText({
-  model: ollama('llama3.2'),
-  prompt: 'What is the weather in San Francisco?',
-  tools: {
-    getWeather: tool({
-      description: 'Get current weather for a location',
-      inputSchema: z.object({
-        location: z.string().describe('City name'),
-        unit: z.enum(['celsius', 'fahrenheit']).optional(),
-      }),
-      execute: async ({ location, unit = 'celsius' }) => {
-        // Your actual weather API call here
-        return { temp: 18, unit, condition: 'sunny' };
-      },
-    }),
-  },
-});
-```
-
-> **Note on Tool Parameters**: Due to Zod version compatibility issues, tool schemas may not always convert properly. When this happens, Ollama may use different parameter names than defined in your schema. It's recommended to handle parameter variations in your tool's execute function (e.g., checking for both `location` and `city`).
-
 ### Enhanced Tool Calling Wrappers
 
 For maximum tool calling reliability, use our enhanced wrapper functions that guarantee complete responses:
 
 ```typescript
-import { ollama, generateTextOllama, streamTextOllama } from 'ai-sdk-ollama';
+import { ollama, generateText, streamText } from 'ai-sdk-ollama';
 import { tool } from 'ai';
 import { z } from 'zod';
 
 // Enhanced generateText with automatic response synthesis
-const result = await generateTextOllama({
+const result = await generateText({
   model: ollama('llama3.2'),
   prompt: 'What is 15 + 27? Use the math tool to calculate it.',
   tools: {
@@ -285,7 +313,7 @@ console.log(result.text); // "15 + 27 equals 42. Using the math tool, I calculat
 
 **Standard vs Enhanced Comparison:**
 
-| Function                   | Standard `generateText`   | Enhanced `generateTextOllama`        |
+| Function                   | Standard `generateText`   | Enhanced `generateText`              |
 | -------------------------- | ------------------------- | ------------------------------------ |
 | **Simple prompts**         | ✅ Perfect                | ✅ Works (slight overhead)           |
 | **Tool calling**           | ⚠️ May return empty text  | ✅ **Guarantees complete responses** |
@@ -473,6 +501,7 @@ Works with any model in your Ollama installation:
 - **Vision**: `llava`, `bakllava`, `llama3.2-vision`, `minicpm-v`
 - **Embeddings**: `nomic-embed-text`, `all-minilm`, `mxbai-embed-large`
 - **Reasoning**: `deepseek-r1:7b`, `deepseek-r1:1.5b`, `deepseek-r1:8b`
+- **Cloud Models** (for web search): `qwen3-coder:480b-cloud`, `gpt-oss:120b-cloud`
 
 ## Testing
 
@@ -495,17 +524,19 @@ For detailed testing information, see [Integration Tests Documentation](./src/in
 
 ## Learn More
 
-📚 **[Examples Directory](./examples/)** - Comprehensive usage patterns with real working code
+📚 **[Examples Directory](../../examples/)** - Comprehensive usage patterns with real working code
+
+🚀 **[Quick Start Guide](../../examples/node/src/basic-chat.ts)** - Get running in 2 minutes
 
-🚀 **[Quick Start Guide](./examples/basic-chat.ts)** - Get running in 2 minutes
+⚙️ **[Dual Parameters Demo](../../examples/node/src/dual-parameter-example.ts)** - See the key feature in action
 
-⚙️ **[Dual Parameters Demo](./examples/dual-parameter-example.ts)** - See the key feature in action
+🔧 **[Tool Calling Guide](../../examples/node/src/simple-tool-test.ts)** - Function calling with Ollama
 
-🔧 **[Tool Calling Guide](./examples/tool-calling-example.ts)** - Function calling with Ollama
+🖼️ **[Image Processing Guide](../../examples/node/src/image-handling-example.ts)** - Vision models with LLaVA
 
-🖼️ **[Image Processing Guide](./examples/image-handling-example.ts)** - Vision models with LLaVA
+📡 **[Streaming Examples](../../examples/node/src/streaming-simple-test.ts)** - Real-time responses
 
-📡 **[Streaming Examples](./examples/streaming-simple-test.ts)** - Real-time responses
+🌐 **[Web Search Tools](../../examples/node/src/web-search-example.ts)** - Web search and fetch capabilities
 
 ## License