Qwen Web Search Agent product introduction

Application introduction: A brief overview of the application's purpose and core capabilities. This field is required and has a 200-character limit.

opening message: The initial message the system sends when a user starts a conversation. This field is optional and has a 500-character limit.

scene enhancement: Select multiple scenarios to combine their enhancement effects.

• Local Life: When enabled, the system can perform precise searches for nearby hotels, restaurants, and public facilities based on your current location. If you also enable rich content with images and text, the response can include POI cards with images.

intelligent query rewriting: The model reframes the original query to optimize search relevance. We recommend enabling this option.

vertical domain tools: Configure vertical domain tools to allow the model to automatically select the optimal search source based on the query context. This improves the timeliness and precision of search results.

Information timeliness range limit: Define a custom time frame to restrict the search to a specific period.

Specify retrieval scope: After you enable this option, click Configure. In the Specify Retrieval Scope dialog box, click + Add Website and enter the target domain names (up to 100), such as tieba.baidu.com and baike.baidu.com. Click OK to save the configuration. The system prioritizes retrieving information from these specified websites. If no matching information is found, the system performs a general web search. This ensures precise retrieval while maintaining comprehensive coverage.

Number of items per retrieval: A higher value returns more comprehensive information, but consumes more resources and increases processing time.

In-depth web page reading: Enabling this option improves retrieval quality but increases response time (RT).

Automatic judgment: The model automatically determines whether a web search is necessary to generate a response.

think-and-search mode: The model automatically determines the search scope and number of retrieval rounds based on the complexity of the query.

Express Mode: The system prioritizes minimizing response time (RT). This mode is suitable for high-concurrency, low-latency scenarios. We recommend enabling it only when response time (RT) is critical and you can accept lower retrieval precision.

Custom intervention search trigger strategy: Use natural language to precisely control the search scope, such as by topic or region. When a query matches the preset scope, the system triggers an external data retrieval. If the model deems the query unrelated, it responds by using its internal knowledge.

forced search: Every query automatically triggers a web search.

system prompt: The model applies constraints based on the information provided here during retrieval and generation. This field has a 10,000-character limit.

Baidu entry underline: When enabled, the model analyzes the semantic structure of the generated result and automatically underlines representative Baidu entries.

rich content with images and text: When enabled, the generated response includes text with relevant, interspersed images for a deeply integrated multimedia experience.

Related videos: When enabled, the system appends relevant video content to the bottom of the response.

follow-up question: When enabled, the system suggests one to three related questions after the response. If you select a suggested question, the model generates an answer based on the conversation history and the system prompt.

citation: When enabled, the system automatically adds numbered superscripts to parts of the response derived from retrieved sources, allowing you to trace information back to its origin.

Set subscript style: Customize the visual style of the citation markers.