Parse Quickstart 快速上手
本地启动 Cortex,签发开发 token,同步解析 URL,并运行异步解析 job。
这个快速上手从本地 Docker 开始,然后完整调用 Parse。下面的 API 片段是 AI 生成的 Python、JavaScript 和 Java 客户端示例。
1. 启动 Cortex
cd /path/to/cortex
test -f .env || cp .env.local.example .env
docker compose --env-file .env -p cortex-local -f compose.local.yaml \
--profile docling \
--profile eval-runtime \
--profile synthesis-runtime \
up -d --build打开 Swagger:http://127.0.0.1:8080/docs。
2. 创建本地 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())); }}运行后续示例时,把返回的 token 设置为 CORTEX_TOKEN。
3. 查看可用引擎
import osimport requestsBASE_URL = os.getenv("CORTEX_URL", "http://127.0.0.1:8080")TOKEN = os.getenv("CORTEX_TOKEN", "replace_with_token")def auth_headers(): return {"Authorization": f"Bearer {TOKEN}"}response = requests.get(f"{BASE_URL}/v1/parse/engines", headers=auth_headers())response.raise_for_status()data = response.json()print(data)const BASE_URL = process.env.CORTEX_URL ?? "http://127.0.0.1:8080";const TOKEN = process.env.CORTEX_TOKEN ?? "replace_with_token";const authHeaders = { Authorization: `Bearer ${TOKEN}`,};const response = await fetch(`${BASE_URL}/v1/parse/engines`, { headers: authHeaders,});if (!response.ok) throw new Error(await response.text());const data = await response.json();console.log(data);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 { HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(BASE_URL + "/v1/parse/engines")) .header("Authorization", "Bearer " + TOKEN) .GET() .build(); print(HTTP.send(request, HttpResponse.BodyHandlers.ofString())); }}4. 同步解析一个 URL
import osimport requestsBASE_URL = os.getenv("CORTEX_URL", "http://127.0.0.1:8080")TOKEN = os.getenv("CORTEX_TOKEN", "replace_with_token")def auth_headers(): return {"Authorization": f"Bearer {TOKEN}"}payload = { "sources": [ "https://docs.cognee.ai/core-concepts/overview" ], "engine_id": "auto"}response = requests.post( f"{BASE_URL}/v1/parse/sync", headers={**auth_headers(), "Content-Type": "application/json"}, json=payload,)response.raise_for_status()data = response.json()print(data['results'][0]['document']['markdown'][:800]);const BASE_URL = process.env.CORTEX_URL ?? "http://127.0.0.1:8080";const TOKEN = process.env.CORTEX_TOKEN ?? "replace_with_token";const authHeaders = { Authorization: `Bearer ${TOKEN}`,};const payload = { "sources": [ "https://docs.cognee.ai/core-concepts/overview" ], "engine_id": "auto"};const response = await fetch(`${BASE_URL}/v1/parse/sync`, { method: "POST", headers: { ...authHeaders, "Content-Type": "application/json" }, body: JSON.stringify(payload),});if (!response.ok) throw new Error(await response.text());const data = await response.json();console.log(data.results[0].document.markdown.slice(0, 800));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 = """ { \"sources\": [ \"https://docs.cognee.ai/core-concepts/overview\" ], \"engine_id\": \"auto\" } """; HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(BASE_URL + "/v1/parse/sync")) .header("Authorization", "Bearer " + TOKEN) .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString(json)) .build(); print(HTTP.send(request, HttpResponse.BodyHandlers.ofString())); }}5. 运行异步 job
Docling、LlamaParse 或大批量解析建议使用异步模式。
import osimport requestsBASE_URL = os.getenv("CORTEX_URL", "http://127.0.0.1:8080")TOKEN = os.getenv("CORTEX_TOKEN", "replace_with_token")def auth_headers(): return {"Authorization": f"Bearer {TOKEN}"}payload = { "sources": [ "https://docs.crawl4ai.com/advanced/advanced-features/" ], "engine_id": "crawl4ai", "priority": 5}response = requests.post( f"{BASE_URL}/v1/parse/jobs", headers={**auth_headers(), "Content-Type": "application/json"}, json=payload,)response.raise_for_status()data = response.json()print(data)const BASE_URL = process.env.CORTEX_URL ?? "http://127.0.0.1:8080";const TOKEN = process.env.CORTEX_TOKEN ?? "replace_with_token";const authHeaders = { Authorization: `Bearer ${TOKEN}`,};const payload = { "sources": [ "https://docs.crawl4ai.com/advanced/advanced-features/" ], "engine_id": "crawl4ai", "priority": 5};const response = await fetch(`${BASE_URL}/v1/parse/jobs`, { method: "POST", headers: { ...authHeaders, "Content-Type": "application/json" }, body: JSON.stringify(payload),});if (!response.ok) throw new Error(await response.text());const data = await response.json();console.log(data);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 = """ { \"sources\": [ \"https://docs.crawl4ai.com/advanced/advanced-features/\" ], \"engine_id\": \"crawl4ai\", \"priority\": 5 } """; HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(BASE_URL + "/v1/parse/jobs")) .header("Authorization", "Bearer " + TOKEN) .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString(json)) .build(); print(HTTP.send(request, HttpResponse.BodyHandlers.ofString())); }}然后轮询通用 job endpoint,并读取 Parse 结果:
import osimport requestsBASE_URL = os.getenv("CORTEX_URL", "http://127.0.0.1:8080")TOKEN = os.getenv("CORTEX_TOKEN", "replace_with_token")def auth_headers(): return {"Authorization": f"Bearer {TOKEN}"}response = requests.get(f"{BASE_URL}/v1/jobs/job_xxx", headers=auth_headers())response.raise_for_status()data = response.json()print(data)const BASE_URL = process.env.CORTEX_URL ?? "http://127.0.0.1:8080";const TOKEN = process.env.CORTEX_TOKEN ?? "replace_with_token";const authHeaders = { Authorization: `Bearer ${TOKEN}`,};const response = await fetch(`${BASE_URL}/v1/jobs/job_xxx`, { headers: authHeaders,});if (!response.ok) throw new Error(await response.text());const data = await response.json();console.log(data);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 { HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(BASE_URL + "/v1/jobs/job_xxx")) .header("Authorization", "Bearer " + TOKEN) .GET() .build(); print(HTTP.send(request, HttpResponse.BodyHandlers.ofString())); }}import osimport requestsBASE_URL = os.getenv("CORTEX_URL", "http://127.0.0.1:8080")TOKEN = os.getenv("CORTEX_TOKEN", "replace_with_token")def auth_headers(): return {"Authorization": f"Bearer {TOKEN}"}response = requests.get(f"{BASE_URL}/v1/parse/jobs/job_xxx/result", headers=auth_headers())response.raise_for_status()data = response.json()print(data)const BASE_URL = process.env.CORTEX_URL ?? "http://127.0.0.1:8080";const TOKEN = process.env.CORTEX_TOKEN ?? "replace_with_token";const authHeaders = { Authorization: `Bearer ${TOKEN}`,};const response = await fetch(`${BASE_URL}/v1/parse/jobs/job_xxx/result`, { headers: authHeaders,});if (!response.ok) throw new Error(await response.text());const data = await response.json();console.log(data);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 { HttpRequest request = HttpRequest.newBuilder() .uri(URI.create(BASE_URL + "/v1/parse/jobs/job_xxx/result")) .header("Authorization", "Bearer " + TOKEN) .GET() .build(); print(HTTP.send(request, HttpResponse.BodyHandlers.ofString())); }}现在你已经把原始 Web 内容转换成了标准化 Markdown,可以继续上传到 Storage 或摄入 Knowledge。