chore: implement suggestions

ts/llama_cloud_services/src/reader.ts

@@ -14,7 +14,8 @@ import {
   getJobTextResultApiV1ParsingJobJobIdResultTextGet,
   uploadFileApiV1ParsingUploadPost,
 } from "./api";
-import { sleep } from "./utils";
+import { sleep, getSavePath } from "./utils";
+import type { ParseResult } from "./type";
 
 export type Language = ParserLanguages;
 export type ResultType = "text" | "markdown" | "json";
@@ -594,15 +595,15 @@ export class LlamaParseReader extends FileReader {
   }
 
   /**
-   * Loads data from a file and returns an array of JSON objects.
+   * Loads data from a file and returns an array of  ParseResult objects.
    * To be used with resultType "json".
    *
    * @param filePathOrContent - The file path or the file content as a Uint8Array.
-   * @returns A Promise that resolves to an array of JSON objects.
+   * @returns A Promise that resolves to an array of ParseResult objects, encapsulating the JSON array resulting from the parsing within the pages attribute.
    */
   async loadJson(
     filePathOrContent: string | Uint8Array,
-  ): Promise<Record<string, any>[]> {
+  ): Promise<ParseResult[]> {
     let jobId;
     const isFilePath =
       typeof filePathOrContent === "string" &&
@@ -628,7 +629,7 @@ export class LlamaParseReader extends FileReader {
       const resultJson = await this.getJobResult(jobId, "json");
       resultJson.job_id = jobId;
       resultJson.file_path = isFilePath ? filePathOrContent : undefined;
-      return [resultJson];
+      return [resultJson] as ParseResult[];
     } catch (e) {
       console.error(`Error while parsing the file under job id ${jobId}`, e);
       if (this.ignoreErrors) {
@@ -639,6 +640,80 @@ export class LlamaParseReader extends FileReader {
     }
   }
 
+  /**
+   * Loads data from a file or file bytes (or an array of those) and returns an array of ParseResult objects.
+   *
+   * @param filePathOrContent - The file path or the file content as a Uint8Array, or an array of one of those two types.
+   * @returns A Promise that resolves to an array of ParseResult objects, encapsulating the JSON array resulting from the parsing within the pages attribute.
+   */
+  async parse(
+    filePathOrContent: string | Uint8Array | string[] | Uint8Array[],
+  ): Promise<ParseResult[]> {
+    const jsonResults: Record<string, any>[][] = [];
+    if (!Array.isArray(filePathOrContent)) {
+      const jsonResult = await this.loadJson(filePathOrContent);
+      jsonResults.push(jsonResult);
+    } else {
+      for (let i = 0; i < filePathOrContent.length; i++) {
+        console.log(
+          `Processing file ${i + 1} of ${filePathOrContent.length}...`,
+        );
+        const jsonResult = await this.loadJson(
+          filePathOrContent[i] as string | Uint8Array,
+        );
+        jsonResults.push(jsonResult);
+      }
+    }
+    const parseResults: ParseResult[] = [];
+    for (const jsonResult of jsonResults) {
+      for (const result of jsonResult) {
+        const parseResult = {
+          pages: result.pages,
+          job_metadata: result.job_metadata,
+          job_id: result.job_id,
+          file_path: result?.file_path ?? "",
+          is_completed: true,
+        } as ParseResult;
+        parseResults.push(parseResult);
+      }
+    }
+    return parseResults;
+  }
+
+  /**
+   * Downloads and saves tables from a given array of ParseResult to a specified download path.
+   *
+   * @param jsonResults - The array of ParseResult containing table information.
+   * @param downloadPath - The path where the downloaded tables will be saved as CSV files.
+   * @returns A Promise that resolves to an array of strings representing the paths to the tables.
+   */
+  async getTables(
+    jsonResults: ParseResult[],
+    downloadPath: string,
+  ): Promise<string[]> {
+    const tables: string[] = [];
+    for (const result of jsonResults) {
+      for (const page of result.pages) {
+        if ("items" in page && Array.isArray(page.items)) {
+          for (let i = 0; i < page.items.length; i++) {
+            if (
+              "type" in page.items[i] &&
+              page.items[i].type === "table" &&
+              "csv" in page.items[i] &&
+              typeof page.items[i].csv === "string" &&
+              page.items[i].csv != ""
+            ) {
+              const savePath = getSavePath(downloadPath, i);
+              await fs.writeFile(savePath, page.items[i].csv);
+              tables.push(savePath);
+            }
+          }
+        }
+      }
+    }
+    return tables;
+  }
+
   /**
    * Downloads and saves images from a given JSON result to a specified download path.
    * Currently only supports resultType "json".
@@ -648,7 +723,7 @@ export class LlamaParseReader extends FileReader {
    * @returns A Promise that resolves to an array of image objects.
    */
   async getImages(
-    jsonResult: Record<string, any>[],
+    jsonResult: ParseResult[],
     downloadPath: string,
   ): Promise<Record<string, any>[]> {
     try {

ts/llama_cloud_services/src/type.ts

@@ -49,3 +49,13 @@ export type ExtractResult = {
       | null;
   };
 };
+
+export type ParseResult = {
+  // eslint-disable-next-line  @typescript-eslint/no-explicit-any
+  pages: Record<string, any>[];
+  // eslint-disable-next-line  @typescript-eslint/no-explicit-any
+  job_metadata: Record<string, any>;
+  job_id: string;
+  is_completed: boolean;
+  file_path: string;
+};

ts/llama_cloud_services/src/utils.ts

@@ -6,6 +6,8 @@ import {
 import { DEFAULT_BASE_URL } from "@llamaindex/core/global";
 import { getEnv } from "@llamaindex/env";
 import type { ClientParams } from "./type.js";
+import fs from "fs";
+import path from "path";
 
 function getBaseUrl(baseUrl?: string): string {
   return baseUrl ?? getEnv("LLAMA_CLOUD_BASE_URL") ?? DEFAULT_BASE_URL;
@@ -99,3 +101,19 @@ export async function getPipelineId(
 export async function sleep(ms: number): Promise<void> {
   return new Promise((resolve) => setTimeout(resolve, ms));
 }
+
+export function getSavePath(downloadPath: string, i: number): string {
+  const now = new Date();
+  const formatted =
+    now.toISOString().replace(/[-:T]/g, "_").replace(/\..+/, "") +
+    "_" +
+    now.getMilliseconds().toString().padStart(3, "0");
+
+  let savePath = path.join(downloadPath, `table_${formatted}.csv`);
+
+  if (fs.existsSync(savePath)) {
+    savePath = savePath.replace(".csv", "_") + i.toString() + ".csv";
+  }
+
+  return savePath;
+}

ts/llama_cloud_services/tests/integration.test.ts

@@ -5,6 +5,7 @@ import { LlamaExtract, LlamaExtractAgent } from "../src/LlamaExtract.js";
 import { Document } from "@llamaindex/core/schema";
 import { fs } from "@llamaindex/env";
 import { ExtractConfig } from "../src/api.js";
+import { ParseResult } from "../src/type.js";
 
 // Integration tests that require actual API keys and files
 describe("Integration Tests", () => {
@@ -284,6 +285,78 @@ describe("Integration Tests", () => {
       },
       60000,
     );
+
+    it.skipIf(skipIfNoApiKey)(
+      "should parse a file and return a ParseResult array",
+      async () => {
+        const parseReader = new LlamaParseReader({
+          apiKey: process.env.LLAMA_CLOUD_API_KEY!,
+          verbose: false,
+        });
+
+        const testContent = "Test document for JSON parsing";
+        const testFilePath = "test-json.txt";
+
+        await fs.writeFile(testFilePath, new TextEncoder().encode(testContent));
+
+        try {
+          const result = await parseReader.parse(testFilePath);
+
+          expect(result).toBeDefined();
+          expect(Array.isArray(result)).toBe(true);
+          expect(result.length).toBeGreaterThan(0);
+          expect(result[0]).toHaveProperty("job_id");
+          expect(result[0]).toHaveProperty("job_metadata");
+          expect(result[0]).toHaveProperty("file_path");
+          expect(result[0]).toHaveProperty("pages");
+
+          await fs.unlink(testFilePath);
+        } catch (error) {
+          try {
+            await fs.unlink(testFilePath);
+          } catch {}
+          throw error;
+        }
+      },
+      60000,
+    );
+
+    it.skipIf(skipIfNoApiKey)(
+      "should extract tables correctly from a JSON result",
+      async () => {
+        const parseReader = new LlamaParseReader({
+          apiKey: process.env.LLAMA_CLOUD_API_KEY!,
+          verbose: false,
+        });
+        const pseudoJsonResult = [
+          {
+            pages: [
+              {
+                items: [
+                  {
+                    type: "table",
+                    csv: "Name,Age,Height (cm)\nAnna,12,140\nBob,22,175\nClaire,33,173\nDenis,44,185\n",
+                  },
+                ],
+              },
+            ],
+            job_id: "jobId",
+            job_metadata: { job_id: "jobId" },
+            file_path: "table.csv",
+            is_completed: true,
+          },
+        ] as ParseResult[];
+
+        const tmpdir = await fs.mkdtemp("tables");
+        const result = await parseReader.getTables(pseudoJsonResult, tmpdir);
+
+        expect(result).toBeDefined();
+        expect(Array.isArray(result)).toBe(true);
+        expect(result.length).toBeGreaterThan(0);
+        expect(typeof result[0] === "string").toBe(true);
+      },
+      60000,
+    );
   });
 
   describe("LlamaCloudIndex Integration", () => {