DiscoveryEngineModelScoresResult
object
relevance_score
array
required
Tools
Find answers to how to use Botify.
Answer questions about the Botify application to understand product features, technical concepts, and best practices for using Botify effectively.In any case but the build of a query, if user asks what a specific filter means (for example a dimension, metric, or UI filter) and strictly for the meaning, query the Knowledge tool using the filter name plus the keyword “filters”, then explain the filter to the user using the field description and any relevant documentation you find.
Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.
Fixed cost per question asked, plus one knowledge-base lookup. Asked by an AI assistant it uses a knowledge base search; asked directly by a person it returns a written answer instead, which costs several times more.
These usage SKUs can be charged on a call.
| SKU | Credits | Description |
|---|---|---|
| Tool call | 1 per request | Charged once per successful item, on top of any usage below. |
| Knowledge base answer | 4 per query | A grounded answer built from an indexed knowledge base, several times the price of a plain search over the same index. |
| Knowledge base search | 15 per 10 query | One search over an indexed knowledge base. |
item is what you send, config how the tool behaves,
and the response is what you get back.
query
string
required
The question you want to ask to the Knowledge Agent
{
"query": "string"
}
search_results
array
required
List of search results used to generate the answer
answer
string
required
The answer generated by the Knowledge Agent
{
"search_results": [
{
"document": {
"body": "string",
"link": "string",
"title": "string",
"sequenced_group_name": "string",
"dataset_name": "string",
"description": "string"
},
"model_scores": {
"relevance_score": [
0.0
]
}
}
],
"answer": "string"
}
These are the available sub-object types that can be used in the properties above.
DiscoveryEngineModelScoresResult
object
relevance_score
array
required
DiscoveryEngineSearchResult
object
document
oneOf
required
model_scores
DiscoveryEngineModelScoresResult
required
DiscoveryEngineStructuredDocumentResult
object
body
string
required
link
string
required
title
string
required
sequenced_group_name
string
required
dataset_name
string
required
description
string
required
DiscoveryEngineUnstructuredDocumentResult
object
extractive_answers
array
required
link
string
required
title
string
required
http://agents.botify.com/{organization}/{project}/knowledge/process
http://agents.botify.com/{organization}/{project}/knowledge/batch_process
http://agents.botify.com/{organization}/{project}/knowledge/async_process
http://agents.botify.com/{organization}/{project}/knowledge/async_batch_process
See running a long job in the background for the polling flow.
curl -X POST "http://agents.botify.com/{organization}/{project}/knowledge/process" \
-H "Authorization: Bearer $BOTIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"item": {
"query": "<query>"
}
}'
This tool is exposed as the MCP tool knowledge. An MCP client passes
organization, project and item as tool arguments.
Set up MCP →