Merge pull request mendableai#132 from mendableai/feat/idempotency-key

[Feat] Added idempotency key to crawl route

apps/api/src/__tests__/e2e_withAuth/index.test.ts

@@ -1,6 +1,7 @@
 import request from "supertest";
 import { app } from "../../index";
 import dotenv from "dotenv";
+import { v4 as uuidv4 } from "uuid";
 
 dotenv.config();
 
@@ -175,6 +176,30 @@ describe("E2E Tests for API Routes", () => {
         /^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$/
       );
     });
+    it('should prevent duplicate requests using the same idempotency key', async () => {
+      const uniqueIdempotencyKey = uuidv4();
+
+      // First request with the idempotency key
+      const firstResponse = await request(TEST_URL)
+        .post('/v0/crawl')
+        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
+        .set("Content-Type", "application/json")
+        .set("x-idempotency-key", uniqueIdempotencyKey)
+        .send({ url: 'https://mendable.ai' });
+
+        expect(firstResponse.statusCode).toBe(200);
+
+      // Second request with the same idempotency key
+      const secondResponse = await request(TEST_URL)
+        .post('/v0/crawl')
+        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
+        .set("Content-Type", "application/json")
+        .set("x-idempotency-key", uniqueIdempotencyKey)
+        .send({ url: 'https://mendable.ai' });
+
+      expect(secondResponse.statusCode).toBe(409);
+      expect(secondResponse.body.error).toBe('Idempotency key already used');
+    });
 
     it("should return a successful response with a valid API key and valid includes option", async () => {
       const crawlResponse = await request(TEST_URL)

apps/api/src/controllers/crawl.ts

@@ -7,6 +7,8 @@ import { RateLimiterMode } from "../../src/types";
 import { addWebScraperJob } from "../../src/services/queue-jobs";
 import { isUrlBlocked } from "../../src/scraper/WebScraper/utils/blocklist";
 import { logCrawl } from "../../src/services/logging/crawl_log";
+import { validateIdempotencyKey } from "../../src/services/idempotency/validate";
+import { createIdempotencyKey } from "../../src/services/idempotency/create";
 
 export async function crawlController(req: Request, res: Response) {
   try {
@@ -19,6 +21,19 @@ export async function crawlController(req: Request, res: Response) {
       return res.status(status).json({ error });
     }
 
+    if (req.headers["x-idempotency-key"]) {
+      const isIdempotencyValid = await validateIdempotencyKey(req);
+      if (!isIdempotencyValid) {
+        return res.status(409).json({ error: "Idempotency key already used" });
+      }
+      try {
+        createIdempotencyKey(req);
+      } catch (error) {
+        console.error(error);
+        return res.status(500).json({ error: error.message });
+      }
+    }
+
     const { success: creditsCheckSuccess, message: creditsCheckMessage } =
       await checkTeamCredits(team_id, 1);
     if (!creditsCheckSuccess) {

apps/api/src/services/idempotency/create.ts

@@ -0,0 +1,22 @@
+import { Request } from "express";
+import { supabase_service } from "../supabase";
+
+export async function createIdempotencyKey(
+  req: Request,
+): Promise<string> {
+  const idempotencyKey = req.headers['x-idempotency-key'] as string;
+  if (!idempotencyKey) {
+    throw new Error("No idempotency key provided in the request headers.");
+  }
+
+  const { data, error } = await supabase_service
+    .from("idempotency_keys")
+    .insert({ key: idempotencyKey });
+
+  if (error) {
+    console.error("Failed to create idempotency key:", error);
+    throw error;
+  }
+
+  return idempotencyKey;
+}

apps/api/src/services/idempotency/validate.ts

@@ -0,0 +1,32 @@
+import { Request } from "express";
+import { supabase_service } from "../supabase";
+import { validate as isUuid } from 'uuid';
+
+export async function validateIdempotencyKey(
+  req: Request,
+): Promise<boolean> {
+  const idempotencyKey = req.headers['x-idempotency-key'];
+  if (!idempotencyKey) {
+    // // not returning for missing idempotency key for now
+    return true;
+  }
+  if (!isUuid(idempotencyKey)) {
+    console.error("Invalid idempotency key provided in the request headers.");
+    return false;
+  }
+
+  const { data, error } = await supabase_service
+    .from("idempotency_keys")
+    .select("key")
+    .eq("key", idempotencyKey);
+
+  if (error) {
+    console.error(error);
+  }
+
+  if (!data || data.length === 0) {
+    return true;
+  }
+
+  return false;
+}

apps/js-sdk/example.js

@@ -1,3 +1,4 @@
+import { v4 as uuidv4 } from 'uuid';
 import FirecrawlApp from '@mendable/firecrawl-js';
 import { z } from "zod";
 
@@ -8,7 +9,8 @@ const scrapeResult = await app.scrapeUrl('firecrawl.dev');
 console.log(scrapeResult.data.content)
 
 // Crawl a website:
-const crawlResult = await app.crawlUrl('mendable.ai', {crawlerOptions: {excludes: ['blog/*'], limit: 5}}, false);
+const idempotencyKey = uuidv4(); // optional
+const crawlResult = await app.crawlUrl('mendable.ai', {crawlerOptions: {excludes: ['blog/*'], limit: 5}}, false, 2, idempotencyKey);
 console.log(crawlResult)
 
 const jobId = await crawlResult['jobId'];

apps/js-sdk/firecrawl/build/index.js

@@ -110,11 +110,12 @@ export default class FirecrawlApp {
      * @param {Params | null} params - Additional parameters for the crawl request.
      * @param {boolean} waitUntilDone - Whether to wait for the crawl job to complete.
      * @param {number} timeout - Timeout in seconds for job status checks.
+     * @param {string} idempotencyKey - Optional idempotency key for the request.
      * @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
      */
     crawlUrl(url_1) {
-        return __awaiter(this, arguments, void 0, function* (url, params = null, waitUntilDone = true, timeout = 2) {
-            const headers = this.prepareHeaders();
+        return __awaiter(this, arguments, void 0, function* (url, params = null, waitUntilDone = true, timeout = 2, idempotencyKey) {
+            const headers = this.prepareHeaders(idempotencyKey);
             let jsonData = { url };
             if (params) {
                 jsonData = Object.assign(Object.assign({}, jsonData), params);
@@ -172,11 +173,8 @@ export default class FirecrawlApp {
      * Prepares the headers for an API request.
      * @returns {AxiosRequestHeaders} The prepared headers.
      */
-    prepareHeaders() {
-        return {
-            "Content-Type": "application/json",
-            Authorization: `Bearer ${this.apiKey}`,
-        };
+    prepareHeaders(idempotencyKey) {
+        return Object.assign({ 'Content-Type': 'application/json', 'Authorization': `Bearer ${this.apiKey}` }, (idempotencyKey ? { 'x-idempotency-key': idempotencyKey } : {}));
     }
     /**
      * Sends a POST request to the specified URL.

apps/js-sdk/firecrawl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mendable/firecrawl-js",
-  "version": "0.0.21",
+  "version": "0.0.22",
   "description": "JavaScript SDK for Firecrawl API",
   "main": "build/index.js",
   "types": "types/index.d.ts",

apps/js-sdk/firecrawl/src/index.ts

@@ -173,15 +173,17 @@ export default class FirecrawlApp {
    * @param {Params | null} params - Additional parameters for the crawl request.
    * @param {boolean} waitUntilDone - Whether to wait for the crawl job to complete.
    * @param {number} timeout - Timeout in seconds for job status checks.
+   * @param {string} idempotencyKey - Optional idempotency key for the request.
    * @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
    */
   async crawlUrl(
     url: string,
     params: Params | null = null,
     waitUntilDone: boolean = true,
-    timeout: number = 2
+    timeout: number = 2,
+    idempotencyKey?: string
   ): Promise<CrawlResponse | any> {
-    const headers = this.prepareHeaders();
+    const headers = this.prepareHeaders(idempotencyKey);
     let jsonData: Params = { url };
     if (params) {
       jsonData = { ...jsonData, ...params };
@@ -240,11 +242,12 @@ export default class FirecrawlApp {
    * Prepares the headers for an API request.
    * @returns {AxiosRequestHeaders} The prepared headers.
    */
-  prepareHeaders(): AxiosRequestHeaders {
+  prepareHeaders(idempotencyKey?: string): AxiosRequestHeaders {
     return {
-      "Content-Type": "application/json",
-      Authorization: `Bearer ${this.apiKey}`,
-    } as AxiosRequestHeaders;
+      'Content-Type': 'application/json',
+      'Authorization': `Bearer ${this.apiKey}`,
+      ...(idempotencyKey ? { 'x-idempotency-key': idempotencyKey } : {}),
+    } as AxiosRequestHeaders & { 'x-idempotency-key'?: string };
   }
 
   /**

apps/js-sdk/firecrawl/types/index.d.ts

@@ -82,9 +82,10 @@ export default class FirecrawlApp {
      * @param {Params | null} params - Additional parameters for the crawl request.
      * @param {boolean} waitUntilDone - Whether to wait for the crawl job to complete.
      * @param {number} timeout - Timeout in seconds for job status checks.
+     * @param {string} idempotencyKey - Optional idempotency key for the request.
      * @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
      */
-    crawlUrl(url: string, params?: Params | null, waitUntilDone?: boolean, timeout?: number): Promise<CrawlResponse | any>;
+    crawlUrl(url: string, params?: Params | null, waitUntilDone?: boolean, timeout?: number, idempotencyKey?: string): Promise<CrawlResponse | any>;
     /**
      * Checks the status of a crawl job using the Firecrawl API.
      * @param {string} jobId - The job ID of the crawl operation.
@@ -95,7 +96,7 @@ export default class FirecrawlApp {
      * Prepares the headers for an API request.
      * @returns {AxiosRequestHeaders} The prepared headers.
      */
-    prepareHeaders(): AxiosRequestHeaders;
+    prepareHeaders(idempotencyKey?: string): AxiosRequestHeaders;
     /**
      * Sends a POST request to the specified URL.
      * @param {string} url - The URL to send the request to.

apps/js-sdk/package.json

@@ -11,8 +11,9 @@
   "author": "",
   "license": "ISC",
   "dependencies": {
-    "@mendable/firecrawl-js": "^0.0.19",
     "axios": "^1.6.8",
+    "uuid": "^9.0.1",
+    "@mendable/firecrawl-js": "^0.0.19",
     "ts-node": "^10.9.2",
     "typescript": "^5.4.5",
     "zod": "^3.23.8"

apps/python-sdk/example.py

@@ -1,4 +1,5 @@
-from firecrawl import FirecrawlApp
+import uuid
+from firecrawl.firecrawl import FirecrawlApp
 
 app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
 
@@ -7,7 +8,8 @@
 print(scrape_result['markdown'])
 
 # Crawl a website:
-crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}})
+idempotency_key = str(uuid.uuid4()) # optional idempotency key
+crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}}, True, 2, idempotency_key)
 print(crawl_result)
 
 # LLM Extraction:

apps/python-sdk/firecrawl/firecrawl.py

@@ -127,7 +127,7 @@ def search(self, query, params=None):
         else:
             raise Exception(f'Failed to search. Status code: {response.status_code}')
 
-    def crawl_url(self, url, params=None, wait_until_done=True, timeout=2):
+    def crawl_url(self, url, params=None, wait_until_done=True, timeout=2, idempotency_key=None):
         """
         Initiate a crawl job for the specified URL using the Firecrawl API.
 
@@ -136,14 +136,15 @@ def crawl_url(self, url, params=None, wait_until_done=True, timeout=2):
             params (Optional[Dict[str, Any]]): Additional parameters for the crawl request.
             wait_until_done (bool): Whether to wait until the crawl job is completed.
             timeout (int): Timeout between status checks when waiting for job completion.
+            idempotency_key (Optional[str]): A unique uuid key to ensure idempotency of requests.
 
         Returns:
             Any: The crawl job ID or the crawl results if waiting until completion.
 
         Raises:
             Exception: If the crawl job initiation or monitoring fails.
         """
-        headers = self._prepare_headers()
+        headers = self._prepare_headers(idempotency_key)
         json_data = {'url': url}
         if params:
             json_data.update(params)
@@ -177,16 +178,26 @@ def check_crawl_status(self, job_id):
         else:
             self._handle_error(response, 'check crawl status')
 
-    def _prepare_headers(self):
+    def _prepare_headers(self, idempotency_key=None):
         """
         Prepare the headers for API requests.
 
+        Args:
+            idempotency_key (Optional[str]): A unique key to ensure idempotency of requests.
+
         Returns:
-            Dict[str, str]: The headers including content type and authorization.
+            Dict[str, str]: The headers including content type, authorization, and optionally idempotency key.
         """
+        if idempotency_key:
+            return {
+                'Content-Type': 'application/json',
+                'Authorization': f'Bearer {self.api_key}',
+                'x-idempotency-key': idempotency_key
+            }
+
         return {
             'Content-Type': 'application/json',
-            'Authorization': f'Bearer {self.api_key}'
+            'Authorization': f'Bearer {self.api_key}',
         }
 
     def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5):