web_reader / build /services /brave-search.js
Mohammad Shahid
Include pre-built files for HF deployment
f316cce
"use strict";
var __decorate = (this && this.__decorate) || function (decorators, target, key, desc) {
var c = arguments.length, r = c < 3 ? target : desc === null ? desc = Object.getOwnPropertyDescriptor(target, key) : desc, d;
if (typeof Reflect === "object" && typeof Reflect.decorate === "function") r = Reflect.decorate(decorators, target, key, desc);
else for (var i = decorators.length - 1; i >= 0; i--) if (d = decorators[i]) r = (c < 3 ? d(r) : c > 3 ? d(target, key, r) : d(target, key)) || r;
return c > 3 && r && Object.defineProperty(target, key, r), r;
};
var __metadata = (this && this.__metadata) || function (k, v) {
if (typeof Reflect === "object" && typeof Reflect.metadata === "function") return Reflect.metadata(k, v);
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.BraveSearchExplicitOperatorsDto = exports.BraveSearchService = void 0;
const civkit_1 = require("civkit");
const tsyringe_1 = require("tsyringe");
const logger_1 = require("./logger");
const secrets_1 = require("../shared/services/secrets");
const brave_search_1 = require("../shared/3rd-party/brave-search");
const geoip_1 = require("./geoip");
const async_context_1 = require("./async-context");
const blackhole_detector_1 = require("./blackhole-detector");
let BraveSearchService = class BraveSearchService extends civkit_1.AsyncService {
constructor(globalLogger, secretExposer, geoipControl, threadLocal, blackHoleDetector) {
super(...arguments);
this.globalLogger = globalLogger;
this.secretExposer = secretExposer;
this.geoipControl = geoipControl;
this.threadLocal = threadLocal;
this.blackHoleDetector = blackHoleDetector;
this.logger = this.globalLogger.child({ service: this.constructor.name });
}
async init() {
await this.dependencyReady();
this.emit('ready');
this.braveSearchHTTP = new brave_search_1.BraveSearchHTTP(this.secretExposer.BRAVE_SEARCH_API_KEY);
}
async webSearch(query) {
const ip = this.threadLocal.get('ip');
const extraHeaders = {};
if (ip) {
const geoip = await this.geoipControl.lookupCity(ip, geoip_1.GEOIP_SUPPORTED_LANGUAGES.EN);
if (geoip?.city) {
extraHeaders['X-Loc-City'] = encodeURIComponent(geoip.city);
}
if (geoip?.country) {
extraHeaders['X-Loc-Country'] = geoip.country.code;
}
if (geoip?.timezone) {
extraHeaders['X-Loc-Timezone'] = geoip.timezone;
}
if (geoip?.coordinates) {
extraHeaders['X-Loc-Lat'] = `${geoip.coordinates[0]}`;
extraHeaders['X-Loc-Long'] = `${geoip.coordinates[1]}`;
}
if (geoip?.subdivisions?.length) {
extraHeaders['X-Loc-State'] = encodeURIComponent(`${geoip.subdivisions[0].code}`);
extraHeaders['X-Loc-State-Name'] = encodeURIComponent(`${geoip.subdivisions[0].name}`);
}
}
if (this.threadLocal.get('userAgent')) {
extraHeaders['User-Agent'] = this.threadLocal.get('userAgent');
}
const encoded = { ...query };
if (encoded.q) {
encoded.q = (Buffer.from(encoded.q).toString('ascii') === encoded.q) ? encoded.q : encodeURIComponent(encoded.q);
}
let maxTries = 11;
while (maxTries--) {
try {
const r = await this.braveSearchHTTP.webSearch(encoded, { headers: extraHeaders });
this.blackHoleDetector.itWorked();
return r.parsed;
}
catch (err) {
this.logger.error(`Web search failed: ${err?.message}`, { err: (0, civkit_1.marshalErrorLike)(err) });
if (err?.status === 429) {
await (0, civkit_1.delay)(500 + 1000 * Math.random());
continue;
}
throw new civkit_1.DownstreamServiceFailureError({ message: `Search failed` });
}
}
throw new civkit_1.DownstreamServiceFailureError({ message: `Search failed` });
}
};
exports.BraveSearchService = BraveSearchService;
exports.BraveSearchService = BraveSearchService = __decorate([
(0, tsyringe_1.singleton)(),
__metadata("design:paramtypes", [logger_1.GlobalLogger,
secrets_1.SecretExposer,
geoip_1.GeoIPService,
async_context_1.AsyncLocalContext,
blackhole_detector_1.BlackHoleDetector])
], BraveSearchService);
class BraveSearchExplicitOperatorsDto extends civkit_1.AutoCastable {
addTo(searchTerm) {
const chunks = [];
for (const [key, value] of Object.entries(this)) {
if (value) {
const values = Array.isArray(value) ? value : [value];
const textValue = values.map((v) => `${key}:${v}`).join(' OR ');
if (textValue) {
chunks.push(textValue);
}
}
}
const opPart = chunks.length > 1 ? chunks.map((x) => `(${x})`).join(' AND ') : chunks;
if (opPart.length) {
return [searchTerm, opPart].join(' ');
}
return searchTerm;
}
static from(input) {
const instance = super.from(input);
const ctx = Reflect.get(input, civkit_1.RPC_CALL_ENVIRONMENT);
const params = ['ext', 'filetype', 'inbody', 'intitle', 'inpage', 'lang', 'loc', 'site'];
for (const p of params) {
const customValue = ctx?.req.get(`x-${p}`) || ctx?.req.get(`${p}`);
if (!customValue) {
continue;
}
const filtered = customValue.split(', ').filter(Boolean);
if (filtered.length) {
Reflect.set(instance, p, filtered);
}
}
return instance;
}
}
exports.BraveSearchExplicitOperatorsDto = BraveSearchExplicitOperatorsDto;
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns web pages with a specific file extension. Example: to find the Honda GX120 Owner’s manual in PDF, type “Honda GX120 ownners manual ext:pdf”.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "ext", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns web pages created in the specified file type. Example: to find a web page created in PDF format about the evaluation of age-related cognitive changes, type “evaluation of age cognitive changes filetype:pdf”.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "filetype", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns web pages containing the specified term in the body of the page. Example: to find information about the Nvidia GeForce GTX 1080 Ti, making sure the page contains the keywords “founders edition” in the body, type “nvidia 1080 ti inbody:“founders edition””.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "inbody", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns webpages containing the specified term in the title of the page. Example: to find pages about SEO conferences making sure the results contain 2023 in the title, type “seo conference intitle:2023”.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "intitle", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns webpages containing the specified term either in the title or in the body of the page. Example: to find pages about the 2024 Oscars containing the keywords “best costume design” in the page, type “oscars 2024 inpage:“best costume design””.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "inpage", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns web pages written in the specified language. The language code must be in the ISO 639-1 two-letter code format. Example: to find information on visas only in Spanish, type “visas lang:es”.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "lang", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns web pages written in the specified language. The language code must be in the ISO 639-1 two-letter code format. Example: to find information on visas only in Spanish, type “visas lang:es”.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "loc", void 0);
__decorate([
(0, civkit_1.Prop)({
arrayOf: String,
desc: `Returns web pages coming only from a specific web site. Example: to find information about Goggles only on Brave pages, type “goggles site:brave.com”.`
}),
__metadata("design:type", Object)
], BraveSearchExplicitOperatorsDto.prototype, "site", void 0);
//# sourceMappingURL=brave-search.js.map