From 5189b446f4b8d62f7a317a951628415f8a577242 Mon Sep 17 00:00:00 2001
From: George He <georgewho96@gmail.com>
Date: Mon, 17 Mar 2025 14:50:38 -0700
Subject: [PATCH] fix: add retry handling logic to parser reader and fix lint
issues (#1757)
Co-authored-by: Alex Yang <himself65@outlook.com>
---
.changeset/thirty-hats-act.md | 8 +
eslint.config.mjs | 3 +
package.json | 3 +
packages/cloud/src/reader.ts | 321 +++++++++++-------
.../src/llm/bedrock/amazon/provider.ts | 3 +-
.../community/src/llm/bedrock/amazon/utils.ts | 2 +-
packages/core/src/global/constants.ts | 1 +
packages/readers/src/cosmosdb.ts | 2 +-
pnpm-lock.yaml | 63 +++-
9 files changed, 269 insertions(+), 137 deletions(-)
create mode 100644 .changeset/thirty-hats-act.md
diff --git a/.changeset/thirty-hats-act.md b/.changeset/thirty-hats-act.md
new file mode 100644
index 000000000..a14122676
--- /dev/null
+++ b/.changeset/thirty-hats-act.md
@@ -0,0 +1,8 @@
+---
+"@llamaindex/cloud": patch
+"@llamaindex/community": patch
+"@llamaindex/core": patch
+"@llamaindex/readers": patch
+---
+
+fix: add retry handling logic to parser reader and fix lint issues
diff --git a/eslint.config.mjs b/eslint.config.mjs
index 0e48c33f1..e083d8d75 100644
--- a/eslint.config.mjs
+++ b/eslint.config.mjs
@@ -50,6 +50,9 @@ export default tseslint.config(
"**/lib/*",
"**/deps/**",
"**/.next/**",
+ "**/.source/**", // Ignore .source directories
+ "!.git", // Don't ignore .git directory
+ "**/.*", // Ignore all dot files and directories
"**/node_modules/**",
"**/build/**",
"**/.docusaurus/**",
diff --git a/package.json b/package.json
index aac556342..4829195f5 100644
--- a/package.json
+++ b/package.json
@@ -46,5 +46,8 @@
"*.{json,md,yml}": [
"prettier --write"
]
+ },
+ "dependencies": {
+ "p-retry": "^6.2.1"
}
}
diff --git a/packages/cloud/src/reader.ts b/packages/cloud/src/reader.ts
index 5a7af156a..529f74853 100644
--- a/packages/cloud/src/reader.ts
+++ b/packages/cloud/src/reader.ts
@@ -1,6 +1,8 @@
+/* eslint-disable @typescript-eslint/no-explicit-any */
import { type Client, createClient, createConfig } from "@hey-api/client-fetch";
import { Document, FileReader } from "@llamaindex/core/schema";
import { fs, getEnv, path } from "@llamaindex/env";
+import pRetry from "p-retry";
import {
type Body_upload_file_api_v1_parsing_upload_post,
type ParserLanguages,
@@ -15,16 +17,18 @@ import {
import { sleep } from "./utils";
export type Language = ParserLanguages;
-
export type ResultType = "text" | "markdown" | "json";
-//todo: should move into @llamaindex/env
+// Export the backoff pattern type.
+export type BackoffPattern = "constant" | "linear" | "exponential";
+
+// TODO: should move into @llamaindex/env
type WriteStream = {
write: (text: string) => void;
};
// Do not modify this variable or cause type errors
-// eslint-disable-next-line @typescript-eslint/no-explicit-any, no-var
+// eslint-disable-next-line no-var
var process: any;
/**
@@ -41,48 +45,57 @@ export class LlamaParseReader extends FileReader {
// The result type for the parser.
resultType: ResultType = "text";
// The interval in seconds to check if the parsing is done.
- checkInterval = 1;
+ checkInterval: number = 1;
// The maximum timeout in seconds to wait for the parsing to finish.
maxTimeout = 2000;
// Whether to print the progress of the parsing.
verbose = true;
- // The language of the text to parse.
+ // The language to parse the file in.
language: ParserLanguages[] = ["en"];
+
+ // New polling options:
+ // Controls the backoff mode: "constant", "linear", or "exponential".
+ backoffPattern: BackoffPattern = "linear";
+ // Maximum interval in seconds between polls.
+ maxCheckInterval: number = 5;
+ // Maximum number of retryable errors before giving up.
+ maxErrorCount: number = 4;
+
// The parsing instruction for the parser. Backend default is an empty string.
parsingInstruction?: string | undefined;
- // Wether to ignore diagonal text (when the text rotation in degrees is not 0, 90, 180 or 270, so not a horizontal or vertical text). Backend default is false.
+ // Whether to ignore diagonal text (when the text rotation in degrees is not 0, 90, 180, or 270). Backend default is false.
skipDiagonalText?: boolean | undefined;
- // Wheter to ignore the cache and re-process the document. All documents are kept in cache for 48hours after the job was completed to avoid processing the same document twice. Backend default is false.
+ // Whether to ignore the cache and re-process the document. Documents are cached for 48 hours after job completion. Backend default is false.
invalidateCache?: boolean | undefined;
- // Wether the document should not be cached in the first place. Backend default is false.
+ // Whether the document should not be cached. Backend default is false.
doNotCache?: boolean | undefined;
- // Wether to use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction. Note: Non-compatible with gpt4oMode. Backend default is false.
+ // Whether to use a faster mode to extract text (skipping OCR and table/heading reconstruction). Not compatible with gpt4oMode. Backend default is false.
fastMode?: boolean | undefined;
- // Wether to keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most cases.
+ // Whether to keep columns in the text according to document layout. May reduce reconstruction accuracy and LLM/embedings performance.
doNotUnrollColumns?: boolean | undefined;
- // A templated page separator to use to split the text. If the results contain `{page_number}` (e.g. JSON mode), it will be replaced by the next page number. If not set the default separator '\\n---\\n' will be used.
+ // A templated page separator for splitting text. If not set, default is "\n---\n".
pageSeparator?: string | undefined;
- //A templated prefix to add to the beginning of each page. If the results contain `{page_number}`, it will be replaced by the page number.>
+ // A templated prefix to add at the beginning of each page.
pagePrefix?: string | undefined;
- // A templated suffix to add to the end of each page. If the results contain `{page_number}`, it will be replaced by the page number.
+ // A templated suffix to add at the end of each page.
pageSuffix?: string | undefined;
- // Deprecated. Use vendorMultimodal params. Whether to use gpt-4o to extract text from documents.
+ // Deprecated. Use vendorMultimodal params. Whether to use gpt-4o to extract text.
gpt4oMode: boolean = false;
- // Deprecated. Use vendorMultimodal params. The API key for the GPT-4o API. Optional, lowers the cost of parsing. Can be set as an env variable: LLAMA_CLOUD_GPT4O_API_KEY.
+ // Deprecated. Use vendorMultimodal params. The API key for GPT-4o. Can be set via LLAMA_CLOUD_GPT4O_API_KEY.
gpt4oApiKey?: string | undefined;
- // The bounding box to use to extract text from documents. Describe as a string containing the bounding box margins.
+ // The bounding box margins as a string.
boundingBox?: string | undefined;
- // The target pages to extract text from documents. Describe as a comma separated list of page numbers. The first page of the document is page 0
+ // The target pages (comma separated list, starting at 0).
targetPages?: string | undefined;
- // Whether or not to ignore and skip errors raised during parsing.
+ // Whether to ignore errors during parsing.
ignoreErrors: boolean = true;
- // Whether to split by page using the pageSeparator or '\n---\n' as default.
+ // Whether to split by page using the pageSeparator (or "\n---\n" as default).
splitByPage: boolean = true;
// Whether to use the vendor multimodal API.
useVendorMultimodalModel: boolean = false;
- // The model name for the vendor multimodal API
+ // The model name for the vendor multimodal API.
vendorMultimodalModelName?: string | undefined;
- // The API key for the multimodal API. Can also be set as an env variable: LLAMA_CLOUD_VENDOR_MULTIMODAL_API_KEY
+ // The API key for the multimodal API. Can be set via LLAMA_CLOUD_VENDOR_MULTIMODAL_API_KEY.
vendorMultimodalApiKey?: string | undefined;
webhookUrl?: string | undefined;
@@ -173,7 +186,7 @@ export class LlamaParseReader extends FileReader {
}
this.apiKey = apiKey;
if (this.baseUrl.endsWith("/")) {
- this.baseUrl = this.baseUrl.slice(0, -"/".length);
+ this.baseUrl = this.baseUrl.slice(0, -1);
}
if (this.baseUrl.endsWith("/api/parsing")) {
this.baseUrl = this.baseUrl.slice(0, -"/api/parsing".length);
@@ -203,13 +216,19 @@ export class LlamaParseReader extends FileReader {
);
}
- // Create a job for the LlamaParse API
+ /**
+ * Creates a job for the LlamaParse API.
+ *
+ * @param data - The file data as a Uint8Array.
+ * @param filename - Optional filename for the file.
+ * @returns A Promise resolving to the job ID as a string.
+ */
async #createJob(data: Uint8Array, filename?: string): Promise<string> {
if (this.verbose) {
console.log("Started uploading the file");
}
- // todo: remove Blob usage when we drop Node.js 18 support
+ // TODO: remove Blob usage when we drop Node.js 18 support
const file: File | Blob =
globalThis.File && filename
? new File([data], filename)
@@ -320,87 +339,124 @@ export class LlamaParseReader extends FileReader {
return response.data.id;
}
- // Get the result of the job
+ /**
+ * Retrieves the result of a parsing job.
+ *
+ * Uses a polling loop with retry logic. Each API call is retried
+ * up to maxErrorCount times if it fails with a 5XX or socket error.
+ * The delay between polls increases according to the specified backoffPattern ("constant", "linear", or "exponential"),
+ * capped by maxCheckInterval.
+ *
+ * @param jobId - The job ID.
+ * @param resultType - The type of result to fetch ("text", "json", or "markdown").
+ * @returns A Promise resolving to the job result.
+ */
private async getJobResult(
jobId: string,
resultType: "text" | "json" | "markdown",
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
): Promise<any> {
- const signal = AbortSignal.timeout(this.maxTimeout * 1000);
let tries = 0;
- while (true) {
- await sleep(this.checkInterval * 1000);
+ let currentInterval = this.checkInterval;
- // Check the job status. If unsuccessful response, checks if maximum timeout has been reached. If reached, throws an error
- const result = await getJobApiV1ParsingJobJobIdGet({
- client: this.#client,
- throwOnError: true,
- path: {
- job_id: jobId,
- },
- query: {
- project_id: this.project_id ?? null,
- organization_id: this.organization_id ?? null,
- },
- signal,
- });
- const { data } = result;
+ while (true) {
+ await sleep(currentInterval * 1000);
- const status = (data as Record<string, unknown>)["status"];
- // If job has completed, return the result
- if (status === "SUCCESS") {
- let result;
- switch (resultType) {
- case "json": {
- result = await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
+ // Wraps the API call in a retry
+ let result;
+ try {
+ result = await pRetry(
+ () =>
+ getJobApiV1ParsingJobJobIdGet({
client: this.#client,
throwOnError: true,
- path: {
- job_id: jobId,
- },
+ path: { job_id: jobId },
query: {
project_id: this.project_id ?? null,
organization_id: this.organization_id ?? null,
},
- signal,
- });
+ signal: AbortSignal.timeout(this.maxTimeout * 1000),
+ }),
+ {
+ retries: this.maxErrorCount,
+ onFailedAttempt: (error) => {
+ // Retry only on 5XX or socket errors.
+ const status = (error.cause as any)?.response?.status;
+ if (
+ !(
+ (status && status >= 500 && status < 600) ||
+ ((error.cause as any)?.code &&
+ ((error.cause as any).code === "ECONNRESET" ||
+ (error.cause as any).code === "ETIMEDOUT" ||
+ (error.cause as any).code === "ECONNREFUSED"))
+ )
+ ) {
+ throw error;
+ }
+ if (this.verbose) {
+ console.warn(
+ `Attempting to get job ${jobId} result (attempt ${error.attemptNumber}) failed. Retrying...`,
+ );
+ }
+ },
+ },
+ );
+ } catch (e: any) {
+ throw new Error(
+ `Max error count reached for job ${jobId}: ${e.message}`,
+ );
+ }
+
+ const { data } = result;
+ const status = (data as Record<string, unknown>)["status"];
+
+ if (status === "SUCCESS") {
+ let resultData;
+ switch (resultType) {
+ case "json": {
+ resultData =
+ await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
+ client: this.#client,
+ throwOnError: true,
+ path: { job_id: jobId },
+ query: {
+ project_id: this.project_id ?? null,
+ organization_id: this.organization_id ?? null,
+ },
+ signal: AbortSignal.timeout(this.maxTimeout * 1000),
+ });
break;
}
case "markdown": {
- result = await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
- client: this.#client,
- throwOnError: true,
- path: {
- job_id: jobId,
- },
- query: {
- project_id: this.project_id ?? null,
- organization_id: this.organization_id ?? null,
- },
- signal,
- });
+ resultData =
+ await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
+ client: this.#client,
+ throwOnError: true,
+ path: { job_id: jobId },
+ query: {
+ project_id: this.project_id ?? null,
+ organization_id: this.organization_id ?? null,
+ },
+ signal: AbortSignal.timeout(this.maxTimeout * 1000),
+ });
break;
}
case "text": {
- result = await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
- client: this.#client,
- throwOnError: true,
- path: {
- job_id: jobId,
- },
- query: {
- project_id: this.project_id ?? null,
- organization_id: this.organization_id ?? null,
- },
- signal,
- });
+ resultData =
+ await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
+ client: this.#client,
+ throwOnError: true,
+ path: { job_id: jobId },
+ query: {
+ project_id: this.project_id ?? null,
+ organization_id: this.organization_id ?? null,
+ },
+ signal: AbortSignal.timeout(this.maxTimeout * 1000),
+ });
break;
}
}
- return result.data;
- // If job is still pending, check if maximum timeout has been reached. If reached, throws an error
+ return resultData.data;
} else if (status === "PENDING") {
- signal.throwIfAborted();
if (this.verbose && tries % 10 === 0) {
this.stdout?.write(".");
}
@@ -408,23 +464,35 @@ export class LlamaParseReader extends FileReader {
} else {
if (this.verbose) {
console.error(
- `Recieved Error response ${status} for job ${jobId}. Got Error Code: ${data.error_code} and Error Message: ${data.error_message}`,
+ `Received error response ${status} for job ${jobId}. Got Error Code: ${data.error_code} and Error Message: ${data.error_message}`,
);
}
throw new Error(
`Failed to parse the file: ${jobId}, status: ${status}`,
);
}
+
+ // Adjust the polling interval based on the backoff pattern.
+ if (this.backoffPattern === "exponential") {
+ currentInterval = Math.min(currentInterval * 2, this.maxCheckInterval);
+ } else if (this.backoffPattern === "linear") {
+ currentInterval = Math.min(
+ currentInterval + this.checkInterval,
+ this.maxCheckInterval,
+ );
+ } else if (this.backoffPattern === "constant") {
+ currentInterval = this.checkInterval;
+ }
}
}
/**
* Loads data from a file and returns an array of Document objects.
- * To be used with resultType = "text" and "markdown"
+ * To be used with resultType "text" or "markdown".
*
- * @param {Uint8Array} fileContent - The content of the file to be loaded.
- * @param {string} filename - The name of the file to be loaded.
- * @return {Promise<Document[]>} A Promise object that resolves to an array of Document objects.
+ * @param fileContent - The content of the file as a Uint8Array.
+ * @param filename - Optional filename for the file.
+ * @returns A Promise that resolves to an array of Document objects.
*/
async loadDataAsContent(
fileContent: Uint8Array,
@@ -436,42 +504,38 @@ export class LlamaParseReader extends FileReader {
console.log(`Started parsing the file under job id ${jobId}`);
}
- // Return results as Document objects
+ // Return results as Document objects.
const jobResults = await this.getJobResult(jobId, this.resultType);
const resultText = jobResults[this.resultType];
- // Split the text by separator if splitByPage is true
+ // Split the text by separator if splitByPage is true.
if (this.splitByPage) {
return this.splitTextBySeparator(resultText);
}
- return [
- new Document({
- text: resultText,
- }),
- ];
+ return [new Document({ text: resultText })];
})
.catch((error) => {
+ console.warn(
+ `Error while parsing the file with: ${error.message ?? error.detail}`,
+ );
if (this.ignoreErrors) {
- console.warn(
- `Error while parsing the file: ${error.message ?? error.detail}`,
- );
return [];
} else {
throw error;
}
});
}
+
/**
* Loads data from a file and returns an array of JSON objects.
- * To be used with resultType = "json"
+ * To be used with resultType "json".
*
- * @param {string} filePathOrContent - The file path to the file or the content of the file as a Buffer
- * @return {Promise<Record<string, any>[]>} A Promise that resolves to an array of JSON objects.
+ * @param filePathOrContent - The file path or the file content as a Uint8Array.
+ * @returns A Promise that resolves to an array of JSON objects.
*/
async loadJson(
filePathOrContent: string | Uint8Array,
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
): Promise<Record<string, any>[]> {
let jobId;
const isFilePath = typeof filePathOrContent === "string";
@@ -479,7 +543,7 @@ export class LlamaParseReader extends FileReader {
const data = isFilePath
? await fs.readFile(filePathOrContent)
: filePathOrContent;
- // Creates a job for the file
+ // Create a job for the file.
jobId = await this.#createJob(
data,
isFilePath ? path.basename(filePathOrContent) : undefined,
@@ -488,14 +552,14 @@ export class LlamaParseReader extends FileReader {
console.log(`Started parsing the file under job id ${jobId}`);
}
- // Return results as an array of JSON objects (same format as Python version of the reader)
+ // Return results as an array of JSON objects.
const resultJson = await this.getJobResult(jobId, "json");
resultJson.job_id = jobId;
resultJson.file_path = isFilePath ? filePathOrContent : undefined;
return [resultJson];
} catch (e) {
+ console.error(`Error while parsing the file under job id ${jobId}`, e);
if (this.ignoreErrors) {
- console.error(`Error while parsing the file under job id ${jobId}`, e);
return [];
} else {
throw e;
@@ -505,27 +569,24 @@ export class LlamaParseReader extends FileReader {
/**
* Downloads and saves images from a given JSON result to a specified download path.
- * Currently only supports resultType = "json"
+ * Currently only supports resultType "json".
*
- * @param {Record<string, any>[]} jsonResult - The JSON result containing image information.
- * @param {string} downloadPath - The path to save the downloaded images.
- * @return {Promise<Record<string, any>[]>} A Promise that resolves to an array of image objects.
+ * @param jsonResult - The JSON result containing image information.
+ * @param downloadPath - The path where the downloaded images will be saved.
+ * @returns A Promise that resolves to an array of image objects.
*/
async getImages(
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
jsonResult: Record<string, any>[],
downloadPath: string,
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
): Promise<Record<string, any>[]> {
try {
- // Create download directory if it doesn't exist (Actually check for write access, not existence, since fsPromises does not have a `existsSync` method)
+ // Create download directory if it doesn't exist (checks for write access).
try {
await fs.access(downloadPath);
} catch {
await fs.mkdir(downloadPath, { recursive: true });
}
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
const images: Record<string, any>[] = [];
for (const result of jsonResult) {
const jobId = result.job_id;
@@ -541,7 +602,7 @@ export class LlamaParseReader extends FileReader {
imageName,
);
await this.fetchAndSaveImage(imageName, imagePath, jobId);
- // Assign metadata to the image
+ // Assign metadata to the image.
image.path = imagePath;
image.job_id = jobId;
image.original_pdf_path = result.file_path;
@@ -561,6 +622,14 @@ export class LlamaParseReader extends FileReader {
}
}
+ /**
+ * Constructs the file path for an image.
+ *
+ * @param downloadPath - The base download directory.
+ * @param jobId - The job ID.
+ * @param imageName - The image name.
+ * @returns A Promise that resolves to the full image path.
+ */
private async getImagePath(
downloadPath: string,
jobId: string,
@@ -569,6 +638,13 @@ export class LlamaParseReader extends FileReader {
return path.join(downloadPath, `${jobId}-${imageName}`);
}
+ /**
+ * Fetches an image from the API and saves it to the specified path.
+ *
+ * @param imageName - The name of the image.
+ * @param imagePath - The local path to save the image.
+ * @param jobId - The associated job ID.
+ */
private async fetchAndSaveImage(
imageName: string,
imagePath: string,
@@ -590,18 +666,21 @@ export class LlamaParseReader extends FileReader {
throw new Error(`Failed to download image: ${response.error.detail}`);
}
const blob = (await response.data) as Blob;
- // Write the image buffer to the specified imagePath
+ // Write the image buffer to the specified imagePath.
await fs.writeFile(imagePath, new Uint8Array(await blob.arrayBuffer()));
}
- // Filters out invalid values (null, undefined, empty string) of specific params.
+ /**
+ * Filters out invalid values (null, undefined, empty string) for specific parameters.
+ *
+ * @param params - The parameters object.
+ * @param keysToCheck - The keys to check for valid values.
+ * @returns A new object with filtered parameters.
+ */
private filterSpecificParams(
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
params: Record<string, any>,
keysToCheck: string[],
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
): Record<string, any> {
- // eslint-disable-next-line @typescript-eslint/no-explicit-any
const filteredParams: Record<string, any> = {};
for (const [key, value] of Object.entries(params)) {
if (keysToCheck.includes(key)) {
@@ -615,6 +694,12 @@ export class LlamaParseReader extends FileReader {
return filteredParams;
}
+ /**
+ * Splits text into Document objects using the page separator.
+ *
+ * @param text - The text to be split.
+ * @returns An array of Document objects.
+ */
private splitTextBySeparator(text: string): Document[] {
const separator = this.pageSeparator ?? "\n---\n";
const textChunks = text.split(separator);
diff --git a/packages/community/src/llm/bedrock/amazon/provider.ts b/packages/community/src/llm/bedrock/amazon/provider.ts
index e4f30919b..d3a8544a8 100644
--- a/packages/community/src/llm/bedrock/amazon/provider.ts
+++ b/packages/community/src/llm/bedrock/amazon/provider.ts
@@ -24,6 +24,7 @@ import {
} from "./utils";
export class AmazonProvider extends Provider<ConverseStreamOutput> {
+ // eslint-disable-next-line @typescript-eslint/no-explicit-any
getResultFromResponse(response: Record<string, any>): ConverseResponse {
return JSON.parse(toUtf8(response.body));
}
@@ -52,7 +53,7 @@ export class AmazonProvider extends Provider<ConverseStreamOutput> {
}
getTextFromStreamResponse(response: ResponseStream): string {
- let event: ConverseStreamOutput | undefined =
+ const event: ConverseStreamOutput | undefined =
this.getStreamingEventResponse(response);
if (!event || !event.contentBlockDelta) return "";
const delta: ContentBlockDelta | undefined = event.contentBlockDelta.delta;
diff --git a/packages/community/src/llm/bedrock/amazon/utils.ts b/packages/community/src/llm/bedrock/amazon/utils.ts
index 9c1fe5e0e..51833c6ed 100644
--- a/packages/community/src/llm/bedrock/amazon/utils.ts
+++ b/packages/community/src/llm/bedrock/amazon/utils.ts
@@ -56,7 +56,7 @@ export const mapImageContent = (imageUrl: string): ImageBlock => {
mimeType as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP
],
- // @ts-ignore: there's a mistake in the "@aws-sdk/client-bedrock-runtime" compared to the actual api
+ // @ts-expect-error: there's a mistake in the "@aws-sdk/client-bedrock-runtime" compared to the actual api
source: { bytes: data },
};
};
diff --git a/packages/core/src/global/constants.ts b/packages/core/src/global/constants.ts
index 442f5e684..f4d99fa6b 100644
--- a/packages/core/src/global/constants.ts
+++ b/packages/core/src/global/constants.ts
@@ -20,4 +20,5 @@ export const DEFAULT_NAMESPACE = "docstore";
//#region llama cloud
export const DEFAULT_PROJECT_NAME = "Default";
export const DEFAULT_BASE_URL = "https://api.cloud.llamaindex.ai";
+export const DEFAULT_EU_BASE_URL = "https://api.cloud.eu.llamaindex.ai";
//#endregion
diff --git a/packages/readers/src/cosmosdb.ts b/packages/readers/src/cosmosdb.ts
index 6a8e4f6c4..7e0e93a5c 100644
--- a/packages/readers/src/cosmosdb.ts
+++ b/packages/readers/src/cosmosdb.ts
@@ -60,7 +60,7 @@ export class SimpleCosmosDBReader implements BaseReader {
const metadataFields = config.metadataFields;
try {
- let res = await container.items.query(query).fetchAll();
+ const res = await container.items.query(query).fetchAll();
const documents: Document[] = [];
for (const item of res.resources) {
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 9fa0108c1..d8216154a 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -7,6 +7,10 @@ settings:
importers:
.:
+ dependencies:
+ p-retry:
+ specifier: ^6.2.1
+ version: 6.2.1
devDependencies:
'@changesets/cli':
specifier: ^2.27.5
@@ -5528,6 +5532,9 @@ packages:
'@types/resolve@1.20.2':
resolution: {integrity: sha512-60BCwRFOZCQhDncwQdxxeOEEkbc5dIMccYLwbxsS4TUNeVECQ/pBJ0j09mrHOl/JJvpRPGwO9SvE4nR2Nb/a4Q==}
+ '@types/retry@0.12.2':
+ resolution: {integrity: sha512-XISRgDJ2Tc5q4TRqvgJtzsRkFYNJzZrhTdtMoGVBttwzzQJkPnS3WWTFc7kuDRoPtPakl+T+OfdEUjYJj7Jbow==}
+
'@types/statuses@2.0.5':
resolution: {integrity: sha512-jmIUGWrAiwu3dZpxntxieC+1n/5c3mjrImkmOSQ2NC5uP6cYO4aAZDdSmRcI5C1oiTmqlZGHC+/NmJrKogbP5A==}
@@ -8261,6 +8268,10 @@ packages:
is-module@1.0.0:
resolution: {integrity: sha512-51ypPSPCoTEIN9dy5Oy+h4pShgJmPCygKfyRCISBI+JoWT/2oJvK8QPxmwv7b/p239jXrm9M1mlQbyKJ5A152g==}
+ is-network-error@1.1.0:
+ resolution: {integrity: sha512-tUdRRAnhT+OtCZR/LxZelH/C7QtjtFrTu5tXCA8pl55eTUElUHT+GPYV8MBMBvea/j+NxQqVt3LbWMRir7Gx9g==}
+ engines: {node: '>=16'}
+
is-node-process@1.2.0:
resolution: {integrity: sha512-Vg4o6/fqPxIjtxgUH5QLJhwZ7gW5diGCVlXpuUfELC62CuxM1iHcRe51f2W1FDy04Ai4KJkagKjx3XaqyfRKXw==}
@@ -9826,6 +9837,10 @@ packages:
resolution: {integrity: sha512-y3b8Kpd8OAN444hxfBbFfj1FY/RjtTd8tzYwhUqNYXx0fXx2iX4maP4Qr6qhIKbQXI02wTLAda4fYUbDagTUFw==}
engines: {node: '>=6'}
+ p-retry@6.2.1:
+ resolution: {integrity: sha512-hEt02O4hUct5wtwg4H4KcWgDdm+l1bOaEy/hWzd8xtXB9BqxTWBBhb+2ImAtH4Cv4rPjV76xN3Zumqk3k3AhhQ==}
+ engines: {node: '>=16.17'}
+
p-try@2.2.0:
resolution: {integrity: sha512-R4nPAVTAU0B9D35/Gk3uJf/7XYbQcyohSKdvAxIRSNghFl4e71hVoGnBNQz9cWaXxO2I10KTC+3jMdvvoKw6dQ==}
engines: {node: '>=6'}
@@ -10676,6 +10691,10 @@ packages:
resolution: {integrity: sha512-dUOvLMJ0/JJYEn8NrpOaGNE7X3vpI5XlZS/u0ANjqtcZVKnIxP7IgCFwrKTxENw29emmwug53awKtaMm4i9g5w==}
engines: {node: '>=14'}
+ retry@0.13.1:
+ resolution: {integrity: sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg==}
+ engines: {node: '>= 4'}
+
reusify@1.0.4:
resolution: {integrity: sha512-U9nH88a3fc/ekCF1l0/UP1IosiuIjyTh7hBvXVMHYgVcfGvt897Xguj2UOLDeI5BG2m7/uwyaLVT6fbtCwTyzw==}
engines: {iojs: '>=1.0.0', node: '>=0.10.0'}
@@ -16604,6 +16623,8 @@ snapshots:
'@types/resolve@1.20.2': {}
+ '@types/retry@0.12.2': {}
+
'@types/statuses@2.0.5': {}
'@types/tough-cookie@4.0.5': {}
@@ -16629,10 +16650,10 @@ snapshots:
'@types/node': 22.9.0
optional: true
- '@typescript-eslint/eslint-plugin@8.24.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)':
+ '@typescript-eslint/eslint-plugin@8.24.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)':
dependencies:
'@eslint-community/regexpp': 4.12.1
- '@typescript-eslint/parser': 8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
+ '@typescript-eslint/parser': 8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3)
'@typescript-eslint/scope-manager': 8.24.0
'@typescript-eslint/type-utils': 8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
'@typescript-eslint/utils': 8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
@@ -18550,12 +18571,12 @@ snapshots:
dependencies:
'@next/eslint-plugin-next': 15.1.0
'@rushstack/eslint-patch': 1.10.5
- '@typescript-eslint/eslint-plugin': 8.24.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
+ '@typescript-eslint/eslint-plugin': 8.24.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
'@typescript-eslint/parser': 8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
eslint: 9.16.0(jiti@2.4.2)
eslint-import-resolver-node: 0.3.9
- eslint-import-resolver-typescript: 3.7.0(eslint-plugin-import@2.31.0)(eslint@9.16.0(jiti@2.4.2))
- eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2))
+ eslint-import-resolver-typescript: 3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2))
+ eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-typescript@3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2))
eslint-plugin-jsx-a11y: 6.10.2(eslint@9.16.0(jiti@2.4.2))
eslint-plugin-react: 7.37.2(eslint@9.16.0(jiti@2.4.2))
eslint-plugin-react-hooks: 5.1.0(eslint@9.16.0(jiti@2.4.2))
@@ -18575,7 +18596,7 @@ snapshots:
eslint: 9.22.0(jiti@2.4.2)
eslint-import-resolver-node: 0.3.9
eslint-import-resolver-typescript: 3.7.0(eslint-plugin-import@2.31.0)(eslint@9.22.0(jiti@2.4.2))
- eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-typescript@3.7.0)(eslint@9.22.0(jiti@2.4.2))
+ eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2))
eslint-plugin-jsx-a11y: 6.10.2(eslint@9.22.0(jiti@2.4.2))
eslint-plugin-react: 7.37.2(eslint@9.22.0(jiti@2.4.2))
eslint-plugin-react-hooks: 5.1.0(eslint@9.22.0(jiti@2.4.2))
@@ -18604,7 +18625,7 @@ snapshots:
transitivePeerDependencies:
- supports-color
- eslint-import-resolver-typescript@3.7.0(eslint-plugin-import@2.31.0)(eslint@9.16.0(jiti@2.4.2)):
+ eslint-import-resolver-typescript@3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)):
dependencies:
'@nolyfill/is-core-module': 1.0.39
debug: 4.4.0
@@ -18616,7 +18637,7 @@ snapshots:
is-glob: 4.0.3
stable-hash: 0.0.4
optionalDependencies:
- eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2))
+ eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2))
transitivePeerDependencies:
- supports-color
@@ -18632,18 +18653,18 @@ snapshots:
is-glob: 4.0.3
stable-hash: 0.0.4
optionalDependencies:
- eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-typescript@3.7.0)(eslint@9.22.0(jiti@2.4.2))
+ eslint-plugin-import: 2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2))
transitivePeerDependencies:
- supports-color
- eslint-module-utils@2.12.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-node@0.3.9)(eslint-import-resolver-typescript@3.7.0)(eslint@9.16.0(jiti@2.4.2)):
+ eslint-module-utils@2.12.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-node@0.3.9)(eslint-import-resolver-typescript@3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)):
dependencies:
debug: 3.2.7
optionalDependencies:
- '@typescript-eslint/parser': 8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
+ '@typescript-eslint/parser': 8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3)
eslint: 9.16.0(jiti@2.4.2)
eslint-import-resolver-node: 0.3.9
- eslint-import-resolver-typescript: 3.7.0(eslint-plugin-import@2.31.0)(eslint@9.16.0(jiti@2.4.2))
+ eslint-import-resolver-typescript: 3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2))
transitivePeerDependencies:
- supports-color
@@ -18658,7 +18679,7 @@ snapshots:
transitivePeerDependencies:
- supports-color
- eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.16.0(jiti@2.4.2)):
+ eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-typescript@3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)):
dependencies:
'@rtsao/scc': 1.1.0
array-includes: 3.1.8
@@ -18669,7 +18690,7 @@ snapshots:
doctrine: 2.1.0
eslint: 9.16.0(jiti@2.4.2)
eslint-import-resolver-node: 0.3.9
- eslint-module-utils: 2.12.0(@typescript-eslint/parser@8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-node@0.3.9)(eslint-import-resolver-typescript@3.7.0)(eslint@9.16.0(jiti@2.4.2))
+ eslint-module-utils: 2.12.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-node@0.3.9)(eslint-import-resolver-typescript@3.7.0(eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2)))(eslint@9.16.0(jiti@2.4.2))
hasown: 2.0.2
is-core-module: 2.16.1
is-glob: 4.0.3
@@ -18681,13 +18702,13 @@ snapshots:
string.prototype.trimend: 1.0.9
tsconfig-paths: 3.15.0
optionalDependencies:
- '@typescript-eslint/parser': 8.24.0(eslint@9.16.0(jiti@2.4.2))(typescript@5.7.3)
+ '@typescript-eslint/parser': 8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3)
transitivePeerDependencies:
- eslint-import-resolver-typescript
- eslint-import-resolver-webpack
- supports-color
- eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint-import-resolver-typescript@3.7.0)(eslint@9.22.0(jiti@2.4.2)):
+ eslint-plugin-import@2.31.0(@typescript-eslint/parser@8.24.0(eslint@9.22.0(jiti@2.4.2))(typescript@5.7.3))(eslint@9.22.0(jiti@2.4.2)):
dependencies:
'@rtsao/scc': 1.1.0
array-includes: 3.1.8
@@ -20303,6 +20324,8 @@ snapshots:
is-module@1.0.0: {}
+ is-network-error@1.1.0: {}
+
is-node-process@1.2.0: {}
is-number-object@1.1.1:
@@ -22395,6 +22418,12 @@ snapshots:
p-map@2.1.0: {}
+ p-retry@6.2.1:
+ dependencies:
+ '@types/retry': 0.12.2
+ is-network-error: 1.1.0
+ retry: 0.13.1
+
p-try@2.2.0: {}
pac-proxy-agent@7.1.0:
@@ -23393,6 +23422,8 @@ snapshots:
- encoding
- supports-color
+ retry@0.13.1: {}
+
reusify@1.0.4: {}
rfdc@1.4.1: {}
--
GitLab