Adding search

Put your subject matter expertise to work by adding search. Search gives your AI assistant access to corporate data collections that it can mine for answers.

Your AI assistant can route complex customer inquiries as a search query. It finds information that is relevant to the query from an external data source and returns it to the AI assistant.

Add search to your AI assistant to prevent the AI assistant from having to say things like, I'm sorry. I can't help you with that. Instead, the AI assistant can query existing company documents or data to see whether any useful information can be found and shared with the customer.

You have two options to add search to your AI assistant:

You can enhance the search integration by using the AI assistant capabilities such as Search trigger, No action matches and Conversational search.

For more information about implementing the enhancements for search integration, see Search integration enhancement.

Add the search integration for Elasticsearch

You can add the search integration for Elasticsearch if you have Plus or Enterprise plans of AI assistant builder. Embedding your AI assistant with the search from Elasticsearch improves the data collection to provide accurate responses to customer queries.

You can add Elasticsearch from the Environments page or the Integrations page. For instructions on adding search integration for Elasticsearch, see Elasticsearch search integration setup.

Add the search integration for Custom service

With a Custom service integration, you can search for information using a search capability that you create. For instructions on adding search integration for Custom service, see Custom search integration setup.

Add the search integration for Milvus

Use Milvus, a high-performance and highly scalable vector database to handle large-scale datasets and for applications that require real-time search capabilities and numerous concurrent users. For more information, see Milvus search integration setup.