retrieve_knowledge
Runs a semantic search (RAG) over a project's indexed knowledge. Returns an answer (when post-processing is enabled) and source citations with relevance scores. Use it to ground responses in the actual content of a DEON project.
Tool name: retrieve_knowledge
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
projectId | string | Yes | — | Project (map) id to scope the search to. |
query | string | Yes | — | Natural-language question or search query. |
keywords | string[] | No | — | Optional keywords to bias the hybrid search. |
maxResults | number | No | — | Maximum citations to return. Positive integer, max 50. |
postProcess | boolean | No | — | When true, an LLM composes a final answer from the retrieved context. |
itemIds | string[] | No | — | Restrict the search to these item ids. |
Returns
{
"answer": "The launch is planned for the first week of September, pending the security review.",
"citations": [
{
"itemId": "11aa22bb-...",
"text": "Launch: week 36, blocked on security review sign-off",
"score": 0.91
}
],
"costInEuros": 0.0021
}
answer is null when postProcess is not enabled — in that case use the citations directly.
Example
"According to the project, when are we launching?"
{
"projectId": "a1b2c3d4-...",
"query": "When is the launch planned?",
"maxResults": 5,
"postProcess": true
}