Hermes is a popular fine-tuned model series for agentic use cases, but like all LLMs, it hallucinates when asked about events after its training cutoff. Adding search grounding via the Scavio API gives Hermes access to real-time web data during inference. This tutorial integrates a search tool into Hermes Agent's tool-use loop, so the agent can autonomously decide when to search and incorporate results into its responses. Each search costs $0.005.
Prerequisites
- Python 3.9+ installed
- requests library installed
- A Scavio API key from scavio.dev
- Hermes model running via Ollama, vLLM, or similar
Walkthrough
Step 1: Build the search grounding function
Create a search function that returns formatted results suitable for inclusion in the Hermes context window.
Python
import os, requests, json
SCAVIO_KEY = os.environ['SCAVIO_API_KEY']
H = {'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json'}
URL = 'https://api.scavio.dev/api/v1/search'
def grounded_search(query: str, num: int = 5) -> str:
"""Search the web and format results for LLM context."""
resp = requests.post(URL, headers=H,
json={'query': query, 'country_code': 'us', 'num_results': num})
resp.raise_for_status()
results = resp.json().get('organic_results', [])
if not results:
return 'No search results found.'
formatted = []
for i, r in enumerate(results, 1):
formatted.append(f'[{i}] {r["title"]}')
if r.get('snippet'):
formatted.append(f' {r["snippet"]}')
formatted.append(f' Source: {r["link"]}')
return '\n'.join(formatted)
results = grounded_search('Hermes 3 model capabilities 2026')
print(results[:400])Step 2: Define the tool schema for Hermes
Hermes uses the ChatML tool-use format. Define the search tool with proper schema so Hermes knows when and how to call it.
Python
HERMES_TOOLS = [
{
'type': 'function',
'function': {
'name': 'web_search',
'description': 'Search the web for current information. Use this tool when you need up-to-date data, facts about recent events, or information beyond your training cutoff.',
'parameters': {
'type': 'object',
'properties': {
'query': {
'type': 'string',
'description': 'The search query. Be specific and include the year 2026 for recent information.'
}
},
'required': ['query']
}
}
}
]
def format_tools_for_hermes(tools: list) -> str:
"""Format tools for Hermes ChatML system prompt."""
tool_descriptions = []
for t in tools:
fn = t['function']
tool_descriptions.append(
f'Tool: {fn["name"]}\n'
f'Description: {fn["description"]}\n'
f'Parameters: {json.dumps(fn["parameters"], indent=2)}'
)
return '\n\n'.join(tool_descriptions)
print(format_tools_for_hermes(HERMES_TOOLS))Step 3: Wire search into the Hermes inference loop
Integrate the search tool into the Hermes conversation loop. When Hermes outputs a tool call, execute the search and feed results back.
Python
import ollama
def run_hermes_with_search(prompt: str, model: str = 'hermes3') -> str:
messages = [{'role': 'user', 'content': prompt}]
response = ollama.chat(model=model, messages=messages, tools=HERMES_TOOLS)
# Check if Hermes wants to use tools
if response.message.tool_calls:
for tc in response.message.tool_calls:
if tc.function.name == 'web_search':
query = tc.function.arguments.get('query', prompt)
search_results = grounded_search(query)
print(f'Hermes searched: "{query}"')
# Feed results back
messages.append(response.message)
messages.append({'role': 'tool', 'content': search_results})
final = ollama.chat(model=model, messages=messages)
return final.message.content
return response.message.content
result = run_hermes_with_search('What are the latest developments in AI regulation in 2026?')
print(f'\nHermes response:\n{result[:500]}')Python Example
Python
import os, requests
SCAVIO_KEY = os.environ['SCAVIO_API_KEY']
H = {'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json'}
def grounded_search(query, num=5):
resp = requests.post('https://api.scavio.dev/api/v1/search', headers=H,
json={'query': query, 'country_code': 'us', 'num_results': num})
results = resp.json().get('organic_results', [])
return '\n'.join(f'[{i+1}] {r["title"]}: {r.get("snippet", "")}' for i, r in enumerate(results))
def hermes_search(prompt):
# Simulate Hermes deciding to search
results = grounded_search(prompt)
print(f'Search grounding for Hermes:')
print(results[:400])
print(f'\nCost: $0.005')
hermes_search('AI regulation developments 2026')JavaScript Example
JavaScript
const SCAVIO_KEY = process.env.SCAVIO_API_KEY;
async function groundedSearch(query) {
const resp = await fetch('https://api.scavio.dev/api/v1/search', {
method: 'POST',
headers: { 'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json' },
body: JSON.stringify({ query, country_code: 'us', num_results: 5 })
});
const data = await resp.json();
return (data.organic_results || []).map((r, i) => `[${i + 1}] ${r.title}: ${r.snippet || ''}`).join('\n');
}
async function hermesSearch(prompt) {
const results = await groundedSearch(prompt);
console.log('Search grounding for Hermes:');
console.log(results.slice(0, 400));
console.log('Cost: $0.005');
}
hermesSearch('AI regulation 2026');Expected Output
JSON
Hermes searched: "AI regulation developments 2026"
[1] EU AI Act Enforcement Begins: What Companies Need to Know
The EU AI Act officially entered enforcement in March 2026...
Source: https://reuters.com/technology/eu-ai-act-enforcement
[2] US Congress Passes Bipartisan AI Safety Bill
The American AI Safety Act of 2026 introduces mandatory...
Source: https://nytimes.com/2026/04/us-ai-safety-bill
[3] China Updates AI Governance Framework
China's Cyberspace Administration released updated guidelines...
Source: https://scmp.com/tech/china-ai-governance
Cost: $0.005