| # okto_version: "1.2"
|
| PROJECT "DeployAPIExample"
|
| DESCRIPTION "Demonstrates DEPLOY block for API deployment"
|
|
|
| ENV {
|
| accelerator: "gpu"
|
| min_memory: "8GB"
|
| precision: "fp16"
|
| }
|
|
|
| DATASET {
|
| train: "examples/datasets/demo_train.jsonl"
|
| format: "jsonl"
|
| type: "chat"
|
| }
|
|
|
| MODEL {
|
| name: "api-deploy-model"
|
| base: "oktoseek/base-mini"
|
| device: "cuda"
|
| }
|
|
|
| TRAIN {
|
| epochs: 5
|
| batch_size: 32
|
| device: "cuda"
|
| }
|
|
|
| EXPORT {
|
| format: ["onnx", "okm"]
|
| path: "export/"
|
| }
|
|
|
| DEPLOY {
|
| target: "api"
|
| host: "0.0.0.0"
|
| endpoint: "/chatbot"
|
| requires_auth: true
|
| port: 9000
|
| max_concurrent_requests: 100
|
| protocol: "http"
|
| format: "onnx"
|
| }
|
|
|
| SECURITY {
|
| input_validation {
|
| max_length: 500
|
| disallow_patterns: [
|
| "<script>",
|
| "DROP TABLE",
|
| "rm -rf",
|
| "sudo"
|
| ]
|
| }
|
|
|
| output_validation {
|
| prevent_data_leak: true
|
| mask_personal_info: true
|
| }
|
|
|
| rate_limit {
|
| max_requests_per_minute: 60
|
| }
|
|
|
| encryption {
|
| algorithm: "AES-256"
|
| }
|
| }
|
|
|
| BEHAVIOR {
|
| mode: "chat"
|
| personality: "assistant"
|
| verbosity: "medium"
|
| language: "en"
|
| fallback: "How can I help you?"
|
| }
|
|
|
|
|
