> ## Documentation Index > Fetch the complete documentation index at: https://docs.vectorshift.ai/llms.txt > Use this file to discover all available pages before exploring further. # Exa AI Web Search Node > Query the Exa AI Web Search API

This node queries the Exa AI Web Search API. ## Node Inputs 1. Search Query: The search text for the Exa AI Web Search query * Type: `Text` ## Node Parameters In the gear: 1. Loader Type: You can select the loader type (the type of search). The available loaders are: General, Companies, and Research Paper. ## Node Outputs 1. Output: The results from the query * Type: `List` * Example usage: `{{exa_ai_0.output}}` ## Considerations * Click on the “+” button on the right of the node to create and connect the node to a [semantic search node](/platform/pipelines/knowledge/semantic-search) to enable semantic search on the search results. ## Example The below example shows a pipeline that takes a user question, searches the web using Exa AI to find relevant information, and uses an LLM to provide an answer based on the search results. 1. Input Node: Allows the pipeline to accept a user question 2. Exa AI Web Search Node: * Search Query: `{{input_0.text}}` 3. LLM Node: * System Instructions: "Answer the question based on the context" * Prompt: * Question: `{{text_0.text}}` * Context: `{{exa_ai_0.output}}` 4. Output Node: Displays the answer to the question * Output: `{{openai_0.response}}`