In this section, we will create a Search Agent Flow with the goal of encapsulating and automating search operations. This agent can integrate multiple built-in tools such as:
Serp Google Search
Tavily Search
Wikipedia Search
By leveraging these tools, the Search Agent can automatically perform web searches based on user input and return structured results for downstream use or display.
We will demonstrate this using both a flow-based agent and an instruction-based agent, allowing you to understand and compare their differences in structure and behavior.
Implementation Method for Flow-based Agent
Overview of Flow Structure
Tool Node
Both built-in tools—Serp Google Search and Tavily Search—only require the user's input query to be passed in directly, without any additional processing or variable transformation.
Answer Node
The End Node receives results from both the Serp and Tavily search tools and combines them into a single unified output for the user.
Implementation Method for Instruction-based Agent
Since search-related tools are relatively simple to use, an Instruction-based Agent can be employed. This agent is capable of autonomously selecting the appropriate search tool to retrieve relevant information and further processing the results before generating an output.
Prompt
You can freely customize the prompt based on your specific needs to guide the agent in performing desired tasks or generating targeted outputs.
Tools
Add both Serp Google Search and Tavily Search tools separately, and make sure they are enabled.
You will be given a user query.
Your task is to call both the Serp Google Search tool and the Tavily Search tool using this query as input.
Once both tools return results, summarize and consolidate the key information from both sources into a single, cohesive summary.
⚠️ Do NOT directly answer the user's question. Just provide a merged and well-organized summary of the retrieved information.
User Query: {{user_query}}
