Overview
Inference API
agents
configurations
functions
integrations
- GETList integrations connections
- GETList integrations connections
- POSTCreate integration
- GETGet integration
- PUTUpdate integration connection
- DELDelete integration
- GETGet integration connection model endpoint configurations
- GETList integration connection models
- GETGet integration model endpoint configurations
knowledgebases
locations
API Reference
models
privateclusters
invitations
service_accounts
store
workspaces
- GETList users in workspace
- POSTInvite user to workspace
- PUTUpdate user role in workspace
- DELRemove user from workspace or revoke invitation
- GETList workspaces
- POSTCreate worspace
- GETGet workspace
- PUTUpdate workspace
- DELDelete workspace
- POSTDecline invitation to workspace
- POSTAccept invitation to workspace
- DELLeave workspace
List all functions
curl --request GET \
--url https://api.blaxel.ai/v0/functions \
--header 'Authorization: Bearer <token>'[
{
"events": [
{
"message": "<string>",
"revision": "<string>",
"status": "<string>",
"time": "<string>",
"type": "<string>"
}
],
"metadata": {
"createdAt": "<string>",
"updatedAt": "<string>",
"createdBy": "<string>",
"updatedBy": "<string>",
"displayName": "<string>",
"labels": {},
"name": "<string>",
"workspace": "<string>"
},
"spec": {
"configurations": {
"key": {
"secret": true,
"value": "<string>"
}
},
"enabled": true,
"flavors": [
{
"name": "<string>",
"type": "<string>"
}
],
"integrationConnections": [
"<string>"
],
"podTemplate": {},
"policies": [
"<string>"
],
"privateClusters": {
"baseUrl": "<string>",
"enabled": true,
"name": "<string>"
},
"revision": {
"active": "<string>",
"canary": "<string>",
"canaryPercent": 123,
"previousActive": "<string>",
"traffic": 123
},
"runtime": {
"args": [
"<any>"
],
"command": [
"<any>"
],
"cpu": 123,
"endpointName": "<string>",
"envs": [
"<any>"
],
"image": "<string>",
"memory": 123,
"metricPort": 123,
"model": "<string>",
"organization": "<string>",
"servingPort": 123,
"startupProbe": {},
"type": "<string>"
},
"sandbox": true,
"serverlessConfig": {
"maxScale": 123,
"minScale": 123,
"timeout": 123
},
"description": "<string>",
"kit": [
{
"description": "<string>",
"name": "<string>",
"parameters": [
{
"description": "<string>",
"name": "<string>",
"required": true,
"type": "<string>"
}
]
}
],
"parameters": [
{
"description": "<string>",
"name": "<string>",
"required": true,
"type": "<string>"
}
],
"storeId": "<string>"
},
"status": "<string>"
}
]Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Response
Metadata
The date and time when the resource was created
The date and time when the resource was updated
The user or service account who created the resource
The user or service account who updated the resource
Model display name
Model name
Workspace name
Function specification
Enable or disable the agent
Deployment integration connection name
Pod template specification
Policy name
Set of configurations for a deployment
The arguments to pass to the deployment runtime
The command to run the deployment
The CPU for the deployment in cores, only available for private cluster
Endpoint Name of the model. In case of hf_private_endpoint, it is the endpoint name. In case of hf_public_endpoint, it is not used.
The env variables to set in the deployment. Should be a list of Kubernetes EnvVar types
The Docker image for the deployment
The memory for the deployment in MB
The port to serve the metrics on
The slug name of the origin model at HuggingFace.
The organization of the model
The port to serve the model on
The readiness probe. Should be a Kubernetes Probe type
The type of origin for the deployment (hf_private_endpoint, hf_public_endpoint)
Sandbox mode
Configuration for a serverless deployment
The minimum number of replicas for the deployment. Can be 0 or 1 (in which case the deployment is always running in at least one location).
The maximum number of replicas for the deployment.
The timeout for the deployment in seconds
Function description, very important for the agent function to work with an LLM
The kit of the function deployment
Function kit
Description of the function kit, very important for the agent to work with your kit
The kit name, very important for the agent to work with your kit
Kit parameters, for your kit to be callable with an Agent
Store function parameter
Function parameters, for your function to be callable with Agent
Store function parameter
Store id
Function status
curl --request GET \
--url https://api.blaxel.ai/v0/functions \
--header 'Authorization: Bearer <token>'[
{
"events": [
{
"message": "<string>",
"revision": "<string>",
"status": "<string>",
"time": "<string>",
"type": "<string>"
}
],
"metadata": {
"createdAt": "<string>",
"updatedAt": "<string>",
"createdBy": "<string>",
"updatedBy": "<string>",
"displayName": "<string>",
"labels": {},
"name": "<string>",
"workspace": "<string>"
},
"spec": {
"configurations": {
"key": {
"secret": true,
"value": "<string>"
}
},
"enabled": true,
"flavors": [
{
"name": "<string>",
"type": "<string>"
}
],
"integrationConnections": [
"<string>"
],
"podTemplate": {},
"policies": [
"<string>"
],
"privateClusters": {
"baseUrl": "<string>",
"enabled": true,
"name": "<string>"
},
"revision": {
"active": "<string>",
"canary": "<string>",
"canaryPercent": 123,
"previousActive": "<string>",
"traffic": 123
},
"runtime": {
"args": [
"<any>"
],
"command": [
"<any>"
],
"cpu": 123,
"endpointName": "<string>",
"envs": [
"<any>"
],
"image": "<string>",
"memory": 123,
"metricPort": 123,
"model": "<string>",
"organization": "<string>",
"servingPort": 123,
"startupProbe": {},
"type": "<string>"
},
"sandbox": true,
"serverlessConfig": {
"maxScale": 123,
"minScale": 123,
"timeout": 123
},
"description": "<string>",
"kit": [
{
"description": "<string>",
"name": "<string>",
"parameters": [
{
"description": "<string>",
"name": "<string>",
"required": true,
"type": "<string>"
}
]
}
],
"parameters": [
{
"description": "<string>",
"name": "<string>",
"required": true,
"type": "<string>"
}
],
"storeId": "<string>"
},
"status": "<string>"
}
]