add search query

2026-02-09 16:45:17 +00:00
parent 02eac0f553
commit 5841e8a922
3 changed files with 301 additions and 0 deletions
@@ -14,6 +14,7 @@
        "@langchain/langgraph": "^1.1.2",
        "@langchain/langgraph-sdk": "^1.5.5",
        "@langchain/openai": "^1.2.3",
+        "axios": "^1.13.5",
        "compute-cosine-similarity": "^1.1.0",
        "csv-parse": "^6.1.0",
        "dotenv": "^17.2.3",
@@ -1302,6 +1303,23 @@
      "integrity": "sha512-htCUDlxyyCLMgaM3xXg0C0LW2xqfuQ6p05pCEIsXuyQ+a1koYKTuBMzRNwmybfLgvJDMd0r1LTn4+E0Ti6C2AA==",
      "license": "MIT"
    },
+    "node_modules/asynckit": {
+      "version": "0.4.0",
+      "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
+      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==",
+      "license": "MIT"
+    },
+    "node_modules/axios": {
+      "version": "1.13.5",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.13.5.tgz",
+      "integrity": "sha512-cz4ur7Vb0xS4/KUN0tPWe44eqxrIu31me+fbang3ijiNscE129POzipJJA6zniq2C/Z6sJCjMimjS8Lc/GAs8Q==",
+      "license": "MIT",
+      "dependencies": {
+        "follow-redirects": "^1.15.11",
+        "form-data": "^4.0.5",
+        "proxy-from-env": "^1.1.0"
+      }
+    },
    "node_modules/base64-js": {
      "version": "1.5.1",
      "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
@@ -1329,6 +1347,19 @@
      "deprecated": "Package no longer supported. Contact Support at https://www.npmjs.com/support for more info.",
      "license": "MIT"
    },
+    "node_modules/call-bind-apply-helpers": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
+      "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "function-bind": "^1.1.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
    "node_modules/camelcase": {
      "version": "6.3.0",
      "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-6.3.0.tgz",
@@ -1454,6 +1485,18 @@
        "node": ">=12.20"
      }
    },
+    "node_modules/combined-stream": {
+      "version": "1.0.8",
+      "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
+      "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
+      "license": "MIT",
+      "dependencies": {
+        "delayed-stream": "~1.0.0"
+      },
+      "engines": {
+        "node": ">= 0.8"
+      }
+    },
    "node_modules/compute-cosine-similarity": {
      "version": "1.1.0",
      "resolved": "https://registry.npmjs.org/compute-cosine-similarity/-/compute-cosine-similarity-1.1.0.tgz",
@@ -1547,6 +1590,15 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/delayed-stream": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
+      "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.4.0"
+      }
+    },
    "node_modules/detect-libc": {
      "version": "2.1.2",
      "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.1.2.tgz",
@@ -1574,6 +1626,20 @@
        "url": "https://dotenvx.com"
      }
    },
+    "node_modules/dunder-proto": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
+      "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
+      "license": "MIT",
+      "dependencies": {
+        "call-bind-apply-helpers": "^1.0.1",
+        "es-errors": "^1.3.0",
+        "gopd": "^1.2.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
    "node_modules/enabled": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/enabled/-/enabled-2.0.0.tgz",
@@ -1598,6 +1664,33 @@
        "node": ">= 0.4"
      }
    },
+    "node_modules/es-object-atoms": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
+      "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-set-tostringtag": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
+      "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "get-intrinsic": "^1.2.6",
+        "has-tostringtag": "^1.0.2",
+        "hasown": "^2.0.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
    "node_modules/es6-error": {
      "version": "4.1.1",
      "resolved": "https://registry.npmjs.org/es6-error/-/es6-error-4.1.1.tgz",
@@ -1682,6 +1775,42 @@
      "integrity": "sha512-GRnmB5gPyJpAhTQdSZTSp9uaPSvl09KoYcMQtsB9rQoOmzs9dH6ffeccH+Z+cv6P68Hu5bC6JjRh4Ah/mHSNRw==",
      "license": "MIT"
    },
+    "node_modules/follow-redirects": {
+      "version": "1.15.11",
+      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.11.tgz",
+      "integrity": "sha512-deG2P0JfjrTxl50XGCDyfI97ZGVCxIpfKYmfyrQ54n5FO/0gfIES8C/Psl6kWVDolizcaaxZJnTS0QSMxvnsBQ==",
+      "funding": [
+        {
+          "type": "individual",
+          "url": "https://github.com/sponsors/RubenVerborgh"
+        }
+      ],
+      "license": "MIT",
+      "engines": {
+        "node": ">=4.0"
+      },
+      "peerDependenciesMeta": {
+        "debug": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/form-data": {
+      "version": "4.0.5",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.5.tgz",
+      "integrity": "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==",
+      "license": "MIT",
+      "dependencies": {
+        "asynckit": "^0.4.0",
+        "combined-stream": "^1.0.8",
+        "es-set-tostringtag": "^2.1.0",
+        "hasown": "^2.0.2",
+        "mime-types": "^2.1.12"
+      },
+      "engines": {
+        "node": ">= 6"
+      }
+    },
    "node_modules/fs": {
      "version": "0.0.1-security",
      "resolved": "https://registry.npmjs.org/fs/-/fs-0.0.1-security.tgz",
@@ -1703,6 +1832,52 @@
        "node": "^8.16.0 || ^10.6.0 || >=11.0.0"
      }
    },
+    "node_modules/function-bind": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
+      "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
+      "license": "MIT",
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/get-intrinsic": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
+      "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
+      "license": "MIT",
+      "dependencies": {
+        "call-bind-apply-helpers": "^1.0.2",
+        "es-define-property": "^1.0.1",
+        "es-errors": "^1.3.0",
+        "es-object-atoms": "^1.1.1",
+        "function-bind": "^1.1.2",
+        "get-proto": "^1.0.1",
+        "gopd": "^1.2.0",
+        "has-symbols": "^1.1.0",
+        "hasown": "^2.0.2",
+        "math-intrinsics": "^1.1.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/get-proto": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
+      "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
+      "license": "MIT",
+      "dependencies": {
+        "dunder-proto": "^1.0.1",
+        "es-object-atoms": "^1.0.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
    "node_modules/get-tsconfig": {
      "version": "4.13.0",
      "resolved": "https://registry.npmjs.org/get-tsconfig/-/get-tsconfig-4.13.0.tgz",
@@ -1788,6 +1963,45 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/has-symbols": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
+      "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/has-tostringtag": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
+      "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
+      "license": "MIT",
+      "dependencies": {
+        "has-symbols": "^1.0.3"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/hasown": {
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
+      "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
+      "license": "MIT",
+      "dependencies": {
+        "function-bind": "^1.1.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
    "node_modules/immediate": {
      "version": "3.0.6",
      "resolved": "https://registry.npmjs.org/immediate/-/immediate-3.0.6.tgz",
@@ -1990,6 +2204,36 @@
        "node": ">=10"
      }
    },
+    "node_modules/math-intrinsics": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
+      "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/mime-db": {
+      "version": "1.52.0",
+      "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
+      "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.6"
+      }
+    },
+    "node_modules/mime-types": {
+      "version": "2.1.35",
+      "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
+      "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
+      "license": "MIT",
+      "dependencies": {
+        "mime-db": "1.52.0"
+      },
+      "engines": {
+        "node": ">= 0.6"
+      }
+    },
    "node_modules/minipass": {
      "version": "7.1.2",
      "resolved": "https://registry.npmjs.org/minipass/-/minipass-7.1.2.tgz",
@@ -2202,6 +2446,12 @@
        "node": ">=12.0.0"
      }
    },
+    "node_modules/proxy-from-env": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
+      "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==",
+      "license": "MIT"
+    },
    "node_modules/readable-stream": {
      "version": "3.6.2",
      "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.2.tgz",
@@ -15,6 +15,7 @@
    "@langchain/langgraph": "^1.1.2",
    "@langchain/langgraph-sdk": "^1.5.5",
    "@langchain/openai": "^1.2.3",
+    "axios": "^1.13.5",
    "compute-cosine-similarity": "^1.1.0",
    "csv-parse": "^6.1.0",
    "dotenv": "^17.2.3",
@@ -0,0 +1,50 @@
+import axios from "axios";
+
+export async function queryScraper(query: string) {
+    const instance = process.env.SCRAPER_INSTANCE;
+    if (!instance) {
+        throw new Error("SCRAPER_INSTANCE environment variable is not set");
+    }
+
+    const cleanQuery = query.replace(/[^A-Za-z0-9 ]+/g, "");
+
+    const url = `${instance}/api/v1/web`;
+
+    const params : Record<string, string> = Object.entries(process.env)
+        .filter(([key, value]) => key.startsWith("SCRAPER_PARAM_") && value !== undefined) 
+        .reduce((acc: Record<string, string>, [key, value]) => {
+            const paramName = key.replace(/^SCRAPER_PARAM_/, "").toLowerCase();
+            acc[paramName] = value!;
+            return acc;
+        }, {});
+
+
+    params.s = cleanQuery;
+
+    let response;
+    try {
+        response = await axios.get(url, { params });
+    } catch (err: any) {
+        if (err.response) {
+            throw new Error(
+                `HTTP error ${err.response.status}: ${JSON.stringify(err.response.data)}`
+            );
+        }
+        throw err;
+    }
+
+    const data = response.data;
+
+    // Basic validation
+    if (data?.status !== "ok") {
+        throw new Error(`API returned status: ${data?.status}`);
+    }
+
+    return data;
+}
+
+
+// import dotenv from "dotenv";
+
+// dotenv.config();
+// console.log(await queryScraper("sir kier starmer"))