样例
Cortex 本地认证、解析、存储、知识、评测和合成工作流样例。
以下样例假设本地 Cortex 运行在 http://127.0.0.1:8080，并启用了 CORTEX_AUTH_MODE=dev。下面的 API 片段是 AI 生成的 Python、JavaScript 和 Java 客户端示例。
获取本地 token
import requestsbase_url = "http://127.0.0.1:8080"payload = { "subject": "cortex-quickstart", "tenant_id": "tenant_demo", "roles": ["tenant_admin"], "expires_in": 3600,}response = requests.post(f"{base_url}/v1/dev/auth/token", json=payload)response.raise_for_status()token = response.json()["access_token"]print(token)const baseUrl = "http://127.0.0.1:8080";const response = await fetch(`${baseUrl}/v1/dev/auth/token`, { method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ subject: "cortex-quickstart", tenant_id: "tenant_demo", roles: ["tenant_admin"], expires_in: 3600, }),});if (!response.ok) throw new Error(await response.text());const { access_token: token } = await response.json();console.log(token);import java.net.URI;import java.net.http.HttpClient;import java.net.http.HttpRequest;import java.net.http.HttpResponse;public class CortexExample { static final String BASE_URL = System.getenv().getOrDefault("CORTEX_URL", "http://127.0.0.1:8080"); static final String TOKEN = System.getenv().getOrDefault("CORTEX_TOKEN", "replace_with_token"); static final HttpClient HTTP = HttpClient.newHttpClient(); static void print(HttpResponse<String> response) { System.out.println(response.statusCode()); System.out.println(response.body()); } public static void main(String[] args) throws Exception { String json = """ { "subject": "cortex-quickstart", "tenant_id": "tenant_demo", "roles": ["tenant_admin"], "expires_in": 3600 } """; HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(BASE_URL + "/v1/dev/auth/token")) .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString(json)) .build(); print(HTTP.send(request, HttpResponse.BodyHandlers.ofString())); }}后续片段使用返回的 access token 作为 CORTEX_TOKEN。你也可以直接在 http://127.0.0.1:8080/docs 的 Swagger 中授权。
选择流程
| 流程 | 适用场景 |
|---|---|
| TensorZero + Cortex 矩阵评测 | 需要完整 Parse -> Storage -> Knowledge -> TensorZero -> Evaluation 闭环，并可扩展 Synthesis。 |
| Parse 和 Knowledge | 解析 URL 或对象，摄入数据集并搜索。 |
| Evaluation 和 Synthesis | 通过异步 Job 运行 RAG 评测或生成 RAG goldens。 |
本地服务
| 服务 | 地址 |
|---|---|
| Swagger UI | http://127.0.0.1:8080/docs |
| MinIO Console | http://127.0.0.1:9001 |
| Jaeger | http://127.0.0.1:16686 |
| Prometheus | http://127.0.0.1:9090 |
| Grafana | http://127.0.0.1:3000 |