@emergentmethods/asknews-typescript-sdk
Version:
Typescript SDK for AskNews API
75 lines (74 loc) • 3.93 kB
JavaScript
/* tslint:disable */
/* eslint-disable */
/**
* AskNews API
* AskNews API [](https://status.asknews.app/status/prod)
*
* The version of the OpenAPI document: 0.24.22
* Contact: contact@emergentmethods.ai
*
* NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
* https://openapi-generator.tech
* Do not edit the class manually.
*/
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
import * as runtime from '../runtime';
import { WebSearchResponseFromJSON, } from '../models/index';
/**
*
*/
export class WebsearchApi extends runtime.BaseAPI {
/**
* Run a live websearch on a set of queries, get back a fully structured and LLM-distilled response (in addition to the raw text if you need that as well). Your response includes as_string and as_dicts, where as_string is a prompt-optimized distillation of the information, done by an LLM. as_dicts contains all the details necessary to feed into other parts of your application.
* Run a live websearch.
*/
liveWebSearchRaw(requestParameters, initOverrides) {
return __awaiter(this, void 0, void 0, function* () {
if (requestParameters['queries'] == null) {
throw new runtime.RequiredError('queries', 'Required parameter "queries" was null or undefined when calling liveWebSearch().');
}
const queryParameters = {};
if (requestParameters['queries'] != null) {
queryParameters['queries'] = requestParameters['queries'];
}
if (requestParameters['lookback'] != null) {
queryParameters['lookback'] = requestParameters['lookback'];
}
if (requestParameters['domains'] != null) {
queryParameters['domains'] = requestParameters['domains'];
}
if (requestParameters['strict'] != null) {
queryParameters['strict'] = requestParameters['strict'];
}
if (requestParameters['offset'] != null) {
queryParameters['offset'] = requestParameters['offset'];
}
const headerParameters = {};
const response = yield this.request({
path: `/v1/chat/websearch`,
method: 'GET',
headers: headerParameters,
query: queryParameters,
}, initOverrides);
return new runtime.JSONApiResponse(response, (jsonValue) => WebSearchResponseFromJSON(jsonValue));
});
}
/**
* Run a live websearch on a set of queries, get back a fully structured and LLM-distilled response (in addition to the raw text if you need that as well). Your response includes as_string and as_dicts, where as_string is a prompt-optimized distillation of the information, done by an LLM. as_dicts contains all the details necessary to feed into other parts of your application.
* Run a live websearch.
*/
liveWebSearch(requestParameters, initOverrides) {
return __awaiter(this, void 0, void 0, function* () {
const response = yield this.liveWebSearchRaw(requestParameters, initOverrides);
return yield response.value();
});
}
}