Loading capabilities…
Loading capability…
Get a search-grounded answer for a question.
Both commands call the selected provider directly.
curl -X POST '/routes/stableenrich-exa/web/answer' \
-H 'content-type: application/json' \
-d '{"query":"What is retrieval augmented generation?"}'h402 call 'web/answer' --provider 'stableenrich-exa' --method POST --json '{"query":"What is retrieval augmented generation?"}'Fill the request fields, quote the exact per-call total, then choose x402 or eligible bonus credit explicitly before sending. Only the selected provider's listed parameters are accepted.
querystringrequired1–1000 charsQuestion to answer using web search context.
{
"query": "What is retrieval augmented generation?"
}{ "data": { "requestId": "d681c6731fdca295e3d56a55e3ed1e3f", "answer": "Retrieval-augmented generation (RAG) is an AI framework that improves large language model (LLM) responses by connecting them to external, private, or up-to-date data sources [1][2][3]. Instead of relying solely on static training data, RAG retrieves relevant information from outside sources—such as internal databases, documents, or the internet—and provides it to the model alongside the user's prompt [1][4][5]. This grounds the LLM in specific facts, increasing accuracy, reducing hallucinations, and allowing access to information that was not available during the model's original training [1][4][6][7].\n\nThe process generally involves three key stages: \n\n1. Ingestion: Data is converted into numerical vector embeddings and stored in a database to enable efficient semantic search [6][3][7].\n2. Retrieval: When a user submits a query, the system searches the database to find the most relevant snippets of information [4][6][3].\n3. Generation: These retrieved snippets are appended to the original prompt, allowing the LLM to synthesize a context-aware, grounded response [4][8][3].\n\nRAG is widely used to keep AI tools current and domain-specific without the high cost and complexity of retraining models [4][5][7].", "citations": [ { "id": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation", "title": "Retrieval-augmented generation - Wikipedia", "url": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation" }, { "id": "https://www.techtarget.com/searchenterpriseai/definition/retrieval-augmented-generation", "title": "What is Retrieval-Augmented Generation (RAG) in AI? | Definition from TechTarget", "url": "https://www.techtarget.com/searchenterpriseai/definition/retrieval-augmented-generation", "publishedDate": "2024-12-30T12:00:00.000Z", "author": "By: George Lawton" }, { "id": "https://www.elastic.co/what-is/retrieval-augmented-generation", "title": "What is Retrieval Augmented Generation (RAG)? | A Comprehensive RAG Guide | Elastic", "url": "https://www.elastic.co/what-is/retrieval-augmented-generation", "publishedDate": "2023-07-12T17:40:07.000Z" } ], "costDollars": { "total": 0.005 } }, "h402": { "routeId": "web/answer", "provider": "stableenrich-exa", "selectedCandidateId": "web/answer/stableenrich-exa", "routing": "manual", "paidBy": "x402-exact" } }
Choose a provider for this task. The catalog recommends the current default from quality, reliability, and price; your selected provider stays pinned. Listed prices are provider prices; settlement adds a 5% h402 fee.