Pencarian web | Ollama

API pencarian web Ollama dapat digunakan untuk memperkaya model dengan informasi terbaru guna mengurangi halusinasi dan meningkatkan akurasi.

Pencarian web disediakan sebagai REST API dengan integrasi alat yang lebih dalam di pustaka Python dan JavaScript. Ini juga memungkinkan model seperti model gpt-oss OpenAI untuk melakukan tugas penelitian yang berjalan lama.

Autentikasi

Untuk mengakses API pencarian web Ollama, buat kunci API. Akun Ollama gratis diperlukan.

API Pencarian Web

Melakukan pencarian web untuk satu kueri dan mengembalikan hasil yang relevan.

Permintaan

POST https://ollama.com/api/web_search

query (string, wajib): string kueri pencarian
max_results (integer, opsional): jumlah hasil maksimum yang dikembalikan (default 5, maks 10)

Respons

Mengembalikan objek yang berisi:

results (array): array objek hasil pencarian, masing-masing berisi:
- title (string): judul halaman web
- url (string): URL halaman web
- content (string): cuplikan konten yang relevan dari halaman web

Contoh

Catatan

Pastikan OLLAMA_API_KEY disetel atau harus diteruskan di header Authorization.

Permintaan cURL

bash

curl https://ollama.com/api/web_search \
  --header "Authorization: Bearer $OLLAMA_API_KEY" \
	-d '{
	  "query":"what is ollama?"
	}'

Respons

json

{
  "results": [
    {
      "title": "Ollama",
      "url": "https://ollama.com/",
      "content": "Cloud models are now available..."
    },
    {
      "title": "What is Ollama? Introduction to the AI model management tool",
      "url": "https://www.hostinger.com/tutorials/what-is-ollama",
      "content": "Ariffud M. 6min Read..."
    },
    {
      "title": "Ollama Explained: Transforming AI Accessibility and Language ...",
      "url": "https://www.geeksforgeeks.org/artificial-intelligence/ollama-explained-transforming-ai-accessibility-and-language-processing/",
      "content": "Data Science Data Science Projects Data Analysis..."
    }
  ]
}

Pustaka Python

python


response = ollama.web_search("What is Ollama?")
print(response)

Contoh output

python


results = [
    {
        "title": "Ollama",
        "url": "https://ollama.com/",
        "content": "Cloud models are now available in Ollama..."
    },
    {
        "title": "What is Ollama? Features, Pricing, and Use Cases - Walturn",
        "url": "https://www.walturn.com/insights/what-is-ollama-features-pricing-and-use-cases",
        "content": "Our services..."
    },
    {
        "title": "Complete Ollama Guide: Installation, Usage & Code Examples",
        "url": "https://collabnix.com/complete-ollama-guide-installation-usage-code-examples",
        "content": "Join our Discord Server..."
    }
]

Contoh Python Ollama lainnya

Pustaka JavaScript

tsx



const client = new Ollama();
const results = await client.webSearch("what is ollama?");
console.log(JSON.stringify(results, null, 2));

Contoh output

json

{
  "results": [
    {
      "title": "Ollama",
      "url": "https://ollama.com/",
      "content": "Cloud models are now available..."
    },
    {
      "title": "What is Ollama? Introduction to the AI model management tool",
      "url": "https://www.hostinger.com/tutorials/what-is-ollama",
      "content": "Ollama is an open-source tool..."
    },
    {
      "title": "Ollama Explained: Transforming AI Accessibility and Language Processing",
      "url": "https://www.geeksforgeeks.org/artificial-intelligence/ollama-explained-transforming-ai-accessibility-and-language-processing/",
      "content": "Ollama is a groundbreaking..."
    }
  ]
}

Contoh JavaScript Ollama lainnya

API Pengambilan Web

Mengambil satu halaman web berdasarkan URL dan mengembalikan kontennya.

Permintaan

POST https://ollama.com/api/web_fetch

url (string, wajib): URL yang akan diambil

Respons

Mengembalikan objek yang berisi:

title (string): judul halaman web
content (string): konten utama halaman web
links (array): array tautan yang ditemukan di halaman

Contoh

Permintaan cURL

python

curl --request POST \
  --url https://ollama.com/api/web_fetch \
  --header "Authorization: Bearer $OLLAMA_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
      "url": "ollama.com"
  }'

Respons

json

{
  "title": "Ollama",
  "content": "[Cloud models](https://ollama.com/blog/cloud-models) are now available in Ollama...",
  "links": [
    "http://ollama.com/",
    "http://ollama.com/models",
    "https://github.com/ollama/ollama"
  ]

SDK Python

python

from ollama import web_fetch

result = web_fetch('https://ollama.com')
print(result)

Hasil

python

WebFetchResponse(
    title='Ollama',
    content='[Cloud models](https://ollama.com/blog/cloud-models) are now available in Ollama\n\n**Chat & build
with open models**\n\n[Download](https://ollama.com/download) [Explore
models](https://ollama.com/models)\n\nAvailable for macOS, Windows, and Linux',
    links=['https://ollama.com/', 'https://ollama.com/models', 'https://github.com/ollama/ollama']
)

SDK JavaScript

tsx



const client = new Ollama();
const fetchResult = await client.webFetch("https://ollama.com");
console.log(JSON.stringify(fetchResult, null, 2));

Hasil

json

{
  "title": "Ollama",
  "content": "[Cloud models](https://ollama.com/blog/cloud-models) are now available in Ollama...",
  "links": [
    "https://ollama.com/",
    "https://ollama.com/models",
    "https://github.com/ollama/ollama"
  ]
}

Membangun Agen Pencarian

Gunakan API pencarian web Ollama sebagai alat untuk membangun mini agen pencarian.

Contoh ini menggunakan model Qwen 3 milik Alibaba dengan 4B parameter.

bash

ollama pull qwen3:4b

python

from ollama import chat, web_fetch, web_search

available_tools = {'web_search': web_search, 'web_fetch': web_fetch}

messages = [{'role': 'user', 'content': "what is ollama's new engine"}]

while True:
  response = chat(
    model='qwen3:4b',
    messages=messages,
    tools=[web_search, web_fetch],
    think=True
    )
  if response.message.thinking:
    print('Thinking: ', response.message.thinking)
  if response.message.content:
    print('Content: ', response.message.content)
  messages.append(response.message)
  if response.message.tool_calls:
    print('Tool calls: ', response.message.tool_calls)
    for tool_call in response.message.tool_calls:
      function_to_call = available_tools.get(tool_call.function.name)
      if function_to_call:
        args = tool_call.function.arguments
        result = function_to_call(**args)
        print('Result: ', str(result)[:200]+'...')
        # Hasil dipotong untuk panjang konteks yang terbatas
        messages.append({'role': 'tool', 'content': str(result)[:2000 * 4], 'tool_name': tool_call.function.name})
      else:
        messages.append({'role': 'tool', 'content': f'Tool {tool_call.function.name} not found', 'tool_name': tool_call.function.name})
  else:
    break

Hasil

Thinking:  Okay, the user is asking about Ollama's new engine. I need to figure out what they're referring to. Ollama is a company that develops large language models, so maybe they've released a new model or an updated version of their existing engine....

Tool calls:  [ToolCall(function=Function(name='web_search', arguments={'max_results': 3, 'query': 'Ollama new engine'}))]
Result:  results=[WebSearchResult(content='# New model scheduling\n\n## September 23, 2025\n\nOllama now includes a significantly improved model scheduling system. Ahead of running a model, Ollama's new engine

Thinking:  Okay, the user asked about Ollama's new engine. Let me look at the search results.

First result is from September 23, 2025, talking about new model scheduling. It mentions improved memory management, reduced crashes, better GPU utilization, and multi-GPU performance. Examples show speed improvements and accurate memory reporting. Supported models include gemma3, llama4, qwen3, etc...

Content:  Ollama has introduced two key updates to its engine, both released in 2025:

1. **Enhanced Model Scheduling (September 23, 2025)**
   - **Precision Memory Management**: Exact memory allocation reduces out-of-memory crashes and optimizes GPU utilization.
   - **Performance Gains**: Examples show significant speed improvements (e.g., 85.54 tokens/s vs 52.02 tokens/s) and full GPU layer utilization.
   - **Multi-GPU Support**: Improved efficiency across multiple GPUs, with accurate memory reporting via tools like `nvidia-smi`.
   - **Supported Models**: Includes `gemma3`, `llama4`, `qwen3`, `mistral-small3.2`, and more.

2. **Multimodal Engine (May 15, 2025)**
   - **Vision Support**: First-class support for vision models, including `llama4:scout` (109B parameters), `gemma3`, `qwen2.5vl`, and `mistral-small3.1`.
   - **Multimodal Tasks**: Examples include identifying animals in multiple images, answering location-based questions from videos, and document scanning.

These updates highlight Ollama's focus on efficiency, performance, and expanded capabilities for both text and vision tasks.

Panjang konteks dan agen

Hasil pencarian web dapat mengembalikan ribuan token. Disarankan untuk meningkatkan panjang konteks model menjadi setidaknya ~32000 token. Agen pencarian bekerja paling baik dengan panjang konteks penuh. Model cloud Ollama berjalan dengan panjang konteks penuh.

Server MCP

Anda dapat mengaktifkan pencarian web di klien MCP mana pun melalui server MCP Python.

Cline

Pencarian web Ollama dapat diintegrasikan dengan Cline dengan mudah menggunakan konfigurasi server MCP.

Kelola Server MCP > Konfigurasikan Server MCP > Tambahkan konfigurasi berikut:

json

{
  "mcpServers": {
    "web_search_and_fetch": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "path/to/web-search-mcp.py"],
      "env": { "OLLAMA_API_KEY": "your_api_key_here" }
    }
  }
}

Codex

Ollama bekerja baik dengan alat Codex OpenAI.

Tambahkan konfigurasi berikut ke ~/.codex/config.toml

python

[mcp_servers.web_search]
command = "uv"
args = ["run", "path/to/web-search-mcp.py"]
env = { "OLLAMA_API_KEY" = "your_api_key_here" }

Goose

Ollama dapat diintegrasikan dengan Goose melalui fitur MCP-nya.

Integrasi lainnya

Ollama dapat diintegrasikan ke dalam sebagian besar alat yang tersedia baik melalui integrasi langsung API Ollama, pustaka Python/JavaScript, API yang kompatibel dengan OpenAI, maupun integrasi server MCP.

Autentikasi ​

API Pencarian Web ​

Permintaan ​

Respons ​

Contoh ​

Permintaan cURL ​

Pustaka Python ​

Pustaka JavaScript ​

API Pengambilan Web ​

Permintaan ​

Respons ​

Contoh ​

Permintaan cURL ​

SDK Python ​

SDK JavaScript ​

Membangun Agen Pencarian ​

Panjang konteks dan agen ​

Server MCP ​

Cline ​

Codex ​

Goose ​

Integrasi lainnya ​

Autentikasi

API Pencarian Web

Permintaan

Respons

Contoh

Permintaan cURL

Pustaka Python

Pustaka JavaScript

API Pengambilan Web

Permintaan

Respons

Contoh

Permintaan cURL

SDK Python

SDK JavaScript

Membangun Agen Pencarian

Panjang konteks dan agen

Server MCP

Cline

Codex

Goose

Integrasi lainnya