Create knowledge base
curl --request POST \
--url https://prod-platform-core-api.20x.business/api/v1/knowledge-bases \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"kbKey": "<string>",
"kbName": "<string>"
}
'import requests
url = "https://prod-platform-core-api.20x.business/api/v1/knowledge-bases"
payload = {
"kbKey": "<string>",
"kbName": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({kbKey: '<string>', kbName: '<string>'})
};
fetch('https://prod-platform-core-api.20x.business/api/v1/knowledge-bases', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));Knowledge Bases
Create knowledge base
Create a knowledge base and its vector collection
POST
/
knowledge-bases
Create knowledge base
curl --request POST \
--url https://prod-platform-core-api.20x.business/api/v1/knowledge-bases \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"kbKey": "<string>",
"kbName": "<string>"
}
'import requests
url = "https://prod-platform-core-api.20x.business/api/v1/knowledge-bases"
payload = {
"kbKey": "<string>",
"kbName": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({kbKey: '<string>', kbName: '<string>'})
};
fetch('https://prod-platform-core-api.20x.business/api/v1/knowledge-bases', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));Creates a knowledge base your agents can retrieve answers from. Creating it also
provisions the underlying vector collection, so this is the first step before
adding sources or uploading documents.
Body parameters
string
required
Short key, unique within your tenant — e.g.
supportstring
required
Display name — e.g.
Support Knowledge Basestring
What this knowledge base contains
number
Cosine relevance floor for retrieval, between
0 and 1. Overrides the
platform default — raise it to return fewer, more relevant chunksobject
Arbitrary key/value data stored with the knowledge base
curl -X POST https://prod-comms-engine-api.20x.business/api/v1/knowledge-bases \
-H "Authorization: Bearer $AGENTIC_OS_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "kbKey": "support", "kbName": "Support Knowledge Base" }'
requests.post(
"https://prod-comms-engine-api.20x.business/api/v1/knowledge-bases",
headers={"Authorization": f"Bearer {API_KEY}"},
json={"kbKey": "support", "kbName": "Support Knowledge Base"},
)
await fetch("https://prod-comms-engine-api.20x.business/api/v1/knowledge-bases", {
method: "POST",
headers: {
Authorization: `Bearer ${API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({ kbKey: "support", kbName: "Support Knowledge Base" }),
});
Next steps
Add content withPOST /knowledge-bases/{kbId}/sources, or upload a file to
POST /knowledge-bases/{kbId}/documents/upload, then queue ingestion with
POST /knowledge-bases/{kbId}/ingestion-jobs.