Linkup

1
{
2
  "mcpServers": {
3
    "respan-docs": {
4
      "url": "https://mcp.respan.ai/mcp/docs"
5
    }
6
  }
7
}

Check out the LinkUp website for more information.

1. Add Linkup Parameters to Your Request

Include linkup_params in your request’s respan_params:

1
{
2
  "messages": [
3
    {"role": "system", "content": "You are a helpful assistant."},
4
    {"role": "user", "content": "Please summarize the information about Microsoft's 2024 revenue: {% if linkup_search_response %}{{ linkup_search_response.answer }}{% endif %}"}
5
  ],
6
  "linkup_params": {
7
      "api_key": {{"YOUR_LINKUP_API_KEY"}},
8
      "q": "What is Microsoft's 2024 revenue?",
9
      "depth": "deep",
10
      "outputType": "sourcedAnswer",
11
      "includeImages": false
12
    }
13
  }

2. Use Template Variables in Your Messages

The Linkup response will be available as a variable named linkup_search_response in your templates. You can access it using Jinja2 syntax:

{% if linkup_search_response %}
  {{ linkup_search_response.answer }}
  
  Sources:
  {% for source in linkup_search_response.sources %}
    - {{ source.name }}: {{ source.url }}
      {{ source.snippet }}
  {% endfor %}
{% endif %}

3. Using with Prompts

If you’re using Respan Prompts, you can include the Linkup template variables in your prompt templates. When you make a request with linkup_params, the variables will be populated and rendered in your prompt.

How It Works

1. When a request with linkup_params is received, the system:

   • Extracts the Linkup parameters from the request
   • Calls the Linkup API to retrieve search results
   • Adds the results to the template variables as linkup_search_response
   • Renders the prompt templates with these variables

2. If you’re using stored prompts, the system:

   • Loads the prompt without rendering variables
   • Merges variables from the prompt and the request
   • Processes Linkup parameters and adds results to variables
   • Renders the prompt with all variables, including Linkup results

Parameters

The linkup_params object supports the following parameters:

Response Structure

The linkup_search_response variable will contain:

1
{
2
  "answer": "The answer text",
3
  "sources": [
4
    {
5
      "name": "Source name",
6
      "url": "Source URL",
7
      "snippet": "Text snippet from the source"
8
    },
9
   // ...
10
  ]
11
}

Example

Here’s a complete example of using the Linkup integration:

1
import requests
2
3
def demo_call(input_text, 
4
              model="gpt-4o-mini",
5
              token="YOUR_RESPAN_API_KEY"):
6
    headers = {
7
        'Content-Type': 'application/json',
8
        'Authorization': f'Bearer {token}',
9
    }
10
11
    data = {
12
        "messages": [
13
            {"role": "system", "content": "You are a helpful assistant."},
14
            {"role": "user", "content": input_text}
15
        ],
16
        "linkup_params": {
17
            "q": "What is Microsoft's 2024 revenue?",
18
            "depth": "deep",
19
            "outputType": "sourcedAnswer",
20
            "includeImages": False
21
        },
22
        "variables": {
23
            "company_name": "Microsoft"
24
        },
25
        "model": model
26
    }
27
28
    response = requests.post('https://api.respan.ai/api/chat/completions', headers=headers, json=data)
29
    return response
30
31
input_text = "Please provide information about {{ company_name }}'s 2024 revenue and cite your sources."
32
response = demo_call(input_text)
33
print(response.json())

With a prompt template like:

Please provide information about {{ company_name }}'s 2024 revenue and cite your sources.
{% if linkup_search_response %}
Here's what I found:
{{ linkup_search_response.answer }}
Sources:
{% for source in linkup_search_response.sources %}
- {{ source.name }}: {{ source.url }}
{% endfor %}
{% endif %}

Error Handling

If there’s an error with the Linkup API call, it will be added to the warnings_dict in the response with the key LINKUP_SEARCH_ERROR.