@promptbook/remote-client 0.89.0-9 → 0.92.0-10

package/README.md

@@ -244,6 +244,10 @@ But unlike programming languages, it is designed to be understandable by non-pro
 
 
 
+## 🔒 Security
+
+For information on reporting security vulnerabilities, see our [Security Policy](./SECURITY.md).
+
 ## 📦 Packages _(for developers)_
 
 This library is divided into several packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
@@ -300,7 +304,7 @@ The following glossary is used to clarify certain concepts:
 ### General LLM / AI terms
 
 -   **Prompt drift** is a phenomenon where the AI model starts to generate outputs that are not aligned with the original prompt. This can happen due to the model's training data, the prompt's wording, or the model's architecture.
--   **Pipeline, workflow or chain** is a sequence of tasks that are executed in a specific order. In the context of AI, a pipeline can refer to a sequence of AI models that are used to process data.
+-   [**Pipeline, workflow scenario or chain** is a sequence of tasks that are executed in a specific order. In the context of AI, a pipeline can refer to a sequence of AI models that are used to process data.](https://github.com/webgptorg/promptbook/discussions/88)
 -   **Fine-tuning** is a process where a pre-trained AI model is further trained on a specific dataset to improve its performance on a specific task.
 -   **Zero-shot learning** is a machine learning paradigm where a model is trained to perform a task without any labeled examples. Instead, the model is provided with a description of the task and is expected to generate the correct output.
 -   **Few-shot learning** is a machine learning paradigm where a model is trained to perform a task with only a few labeled examples. This is in contrast to traditional machine learning, where models are trained on large datasets.
@@ -308,10 +312,6 @@ The following glossary is used to clarify certain concepts:
 -   **Retrieval-augmented generation** is a machine learning paradigm where a model generates text by retrieving relevant information from a large database of text. This approach combines the benefits of generative models and retrieval models.
 -   **Longtail** refers to non-common or rare events, items, or entities that are not well-represented in the training data of machine learning models. Longtail items are often challenging for models to predict accurately.
 
-
-
-
-
 _Note: This section is not complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
 
 
@@ -425,6 +425,8 @@ See [TODO.md](./TODO.md)
 
 ## 🖋️ Contributing
 
-We are open to pull requests, feedback, and suggestions.
+You can also ⭐ star the project, [follow us on GitHub](https://github.com/hejny) or [various other social networks](https://www.pavolhejny.com/contact/).We are open to [pull requests, feedback, and suggestions](./CONTRIBUTING.md).
+
+## 📞 Support
 
-You can also ⭐ star the project, [follow us on GitHub](https://github.com/hejny) or [various other social networks](https://www.pavolhejny.com/contact/).
+If you need help or have questions, please check our [Support Resources](./SUPPORT.md).

package/esm/index.es.js

@@ -20,7 +20,7 @@ const BOOK_LANGUAGE_VERSION = '1.0.0';
  * @generated
  * @see https://github.com/webgptorg/promptbook
  */
-const PROMPTBOOK_ENGINE_VERSION = '0.89.0-9';
+const PROMPTBOOK_ENGINE_VERSION = '0.92.0-10';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -238,7 +238,7 @@ class PipelineExecutionError extends Error {
     }
 }
 /**
- * TODO: !!!!!! Add id to all errors
+ * TODO: [🧠][🌂] Add id to all errors
  */
 
 /**
@@ -320,6 +320,7 @@ const ADMIN_EMAIL = 'pavol@ptbk.io';
  * @public exported from `@promptbook/core`
  */
 const ADMIN_GITHUB_NAME = 'hejny';
+//            <- TODO: [🐊] Pick the best claim
 /**
  * When the title is not provided, the default title is used
  *
@@ -443,6 +444,26 @@ class UnexpectedError extends Error {
     }
 }
 
+/**
+ * This error type indicates that somewhere in the code non-Error object was thrown and it was wrapped into the `WrappedError`
+ *
+ * @public exported from `@promptbook/core`
+ */
+class WrappedError extends Error {
+    constructor(whatWasThrown) {
+        const tag = `[🤮]`;
+        console.error(tag, whatWasThrown);
+        super(spaceTrim(`
+                Non-Error object was thrown
+
+                Note: Look for ${tag} in the console for more details
+                Please report issue on ${ADMIN_EMAIL}
+            `));
+        this.name = 'WrappedError';
+        Object.setPrototypeOf(this, WrappedError.prototype);
+    }
+}
+
 /**
  * Index of all custom errors
  *
@@ -463,7 +484,10 @@ const PROMPTBOOK_ERRORS = {
     PipelineExecutionError,
     PipelineLogicError,
     PipelineUrlError,
+    AuthenticationError,
+    PromptbookFetchError,
     UnexpectedError,
+    WrappedError,
     // TODO: [🪑]> VersionMismatchError,
 };
 /**
@@ -480,8 +504,6 @@ const COMMON_JAVASCRIPT_ERRORS = {
     TypeError,
     URIError,
     AggregateError,
-    AuthenticationError,
-    PromptbookFetchError,
     /*
   Note: Not widely supported
   > InternalError,
@@ -530,6 +552,35 @@ function deserializeError(error) {
     return deserializedError;
 }
 
+/**
+ * Tests if given string is valid URL.
+ *
+ * Note: Dataurl are considered perfectly valid.
+ * Note: There are two simmilar functions:
+ * - `isValidUrl` which tests any URL
+ * - `isValidPipelineUrl` *(this one)* which tests just promptbook URL
+ *
+ * @public exported from `@promptbook/utils`
+ */
+function isValidUrl(url) {
+    if (typeof url !== 'string') {
+        return false;
+    }
+    try {
+        if (url.startsWith('blob:')) {
+            url = url.replace(/^blob:/, '');
+        }
+        const urlObject = new URL(url /* because fail is handled */);
+        if (!['http:', 'https:', 'data:'].includes(urlObject.protocol)) {
+            return false;
+        }
+        return true;
+    }
+    catch (error) {
+        return false;
+    }
+}
+
 /**
  * Creates a connection to the remote proxy server.
  *
@@ -539,17 +590,31 @@ function deserializeError(error) {
  */
 async function createRemoteClient(options) {
     const { remoteServerUrl } = options;
-    let path = new URL(remoteServerUrl).pathname;
-    if (path.endsWith('/')) {
-        path = path.slice(0, -1);
+    if (!isValidUrl(remoteServerUrl)) {
+        throw new Error(`Invalid \`remoteServerUrl\`: "${remoteServerUrl}"`);
+    }
+    const remoteServerUrlParsed = new URL(remoteServerUrl);
+    if (remoteServerUrlParsed.pathname !== '/' && remoteServerUrlParsed.pathname !== '') {
+        remoteServerUrlParsed.pathname = '/';
+        throw new Error(spaceTrim$1((block) => `
+                        Remote server requires root url \`/\`
+
+                        You have provided \`remoteServerUrl\`:
+                        ${block(remoteServerUrl)}
+
+                        But something like this is expected:
+                        ${block(remoteServerUrlParsed.href)}
+
+                        Note: If you need to run multiple services on the same server, use 3rd or 4th degree subdomain
+
+                    `));
     }
-    path = `${path}/socket.io`;
     return new Promise((resolve, reject) => {
         const socket = io(remoteServerUrl, {
             retries: CONNECTION_RETRIES_LIMIT,
             timeout: CONNECTION_TIMEOUT_MS,
-            path,
-            transports: [/*'websocket', <- TODO: [🌬] Make websocket transport work */ 'polling'],
+            path: '/socket.io',
+            transports: ['polling', 'websocket' /*, <- TODO: [🌬] Allow to pass `transports`, add 'webtransport' */],
         });
         // console.log('Connecting to', this.options.remoteServerUrl.href, { socket });
         socket.on('connect', () => {
@@ -683,35 +748,6 @@ function isValidFilePath(filename) {
  * TODO: [🍏] Implement for MacOs
  */
 
-/**
- * Tests if given string is valid URL.
- *
- * Note: Dataurl are considered perfectly valid.
- * Note: There are two simmilar functions:
- * - `isValidUrl` which tests any URL
- * - `isValidPipelineUrl` *(this one)* which tests just promptbook URL
- *
- * @public exported from `@promptbook/utils`
- */
-function isValidUrl(url) {
-    if (typeof url !== 'string') {
-        return false;
-    }
-    try {
-        if (url.startsWith('blob:')) {
-            url = url.replace(/^blob:/, '');
-        }
-        const urlObject = new URL(url /* because fail is handled */);
-        if (!['http:', 'https:', 'data:'].includes(urlObject.protocol)) {
-            return false;
-        }
-        return true;
-    }
-    catch (error) {
-        return false;
-    }
-}
-
 const defaultDiacriticsRemovalMap = [
     {
         base: 'A',
@@ -1539,6 +1575,34 @@ const bookVersionCommandParser = {
     },
 };
 
+/**
+ * Helper used in catch blocks to assert that the error is an instance of `Error`
+ *
+ * @param whatWasThrown Any object that was thrown
+ * @returns Nothing if the error is an instance of `Error`
+ * @throws `WrappedError` or `UnexpectedError` if the error is not standard
+ *
+ * @private within the repository
+ */
+function assertsError(whatWasThrown) {
+    // Case 1: Handle error which was rethrown as `WrappedError`
+    if (whatWasThrown instanceof WrappedError) {
+        const wrappedError = whatWasThrown;
+        throw wrappedError;
+    }
+    // Case 2: Handle unexpected errors
+    if (whatWasThrown instanceof UnexpectedError) {
+        const unexpectedError = whatWasThrown;
+        throw unexpectedError;
+    }
+    // Case 3: Handle standard errors - keep them up to consumer
+    if (whatWasThrown instanceof Error) {
+        return;
+    }
+    // Case 4: Handle non-standard errors - wrap them into `WrappedError` and throw
+    throw new WrappedError(whatWasThrown);
+}
+
 /**
  * Units of text measurement
  *
@@ -1619,6 +1683,8 @@ function parseNumber(value) {
  */
 
 /**
+import { WrappedError } from '../../errors/WrappedError';
+import { assertsError } from '../../errors/assertsError';
  * Parses the expect command
  *
  * @see `documentationUrl` for more details
@@ -1710,9 +1776,7 @@ const expectCommandParser = {
             };
         }
         catch (error) {
-            if (!(error instanceof Error)) {
-                throw error;
-            }
+            assertsError(error);
             throw new ParseError(spaceTrim$1((block) => `
                             Invalid FORMAT command
                             ${block(error.message)}:
@@ -1770,6 +1834,46 @@ const MANDATORY_CSV_SETTINGS = Object.freeze({
     // encoding: 'utf-8',
 });
 
+/**
+ * Function to check if a string is valid CSV
+ *
+ * @param value The string to check
+ * @returns True if the string is a valid CSV string, false otherwise
+ *
+ * @public exported from `@promptbook/utils`
+ */
+function isValidCsvString(value) {
+    try {
+        // A simple check for CSV format: at least one comma and no invalid characters
+        if (value.includes(',') && /^[\w\s,"']+$/.test(value)) {
+            return true;
+        }
+        return false;
+    }
+    catch (error) {
+        assertsError(error);
+        return false;
+    }
+}
+
+/**
+ * Converts a CSV string into an object
+ *
+ * Note: This is wrapper around `papaparse.parse()` with better autohealing
+ *
+ * @private - for now until `@promptbook/csv` is released
+ */
+function csvParse(value /* <- TODO: string_csv */, settings, schema /* <- TODO: Make CSV Schemas */) {
+    settings = { ...settings, ...MANDATORY_CSV_SETTINGS };
+    // Note: Autoheal invalid '\n' characters
+    if (settings.newline && !settings.newline.includes('\r') && value.includes('\r')) {
+        console.warn('CSV string contains carriage return characters, but in the CSV settings the `newline` setting does not include them. Autohealing the CSV string.');
+        value = value.replace(/\r\n/g, '\n').replace(/\r/g, '\n');
+    }
+    const csv = parse(value, settings);
+    return csv;
+}
+
 /**
  * Definition for CSV spreadsheet
  *
@@ -1780,7 +1884,7 @@ const CsvFormatDefinition = {
     formatName: 'CSV',
     aliases: ['SPREADSHEET', 'TABLE'],
     isValid(value, settings, schema) {
-        return true;
+        return isValidCsvString(value);
     },
     canBeValid(partialValue, settings, schema) {
         return true;
@@ -1792,8 +1896,7 @@ const CsvFormatDefinition = {
         {
             subvalueName: 'ROW',
             async mapValues(value, outputParameterName, settings, mapCallback) {
-                // TODO: [👨🏾‍🤝‍👨🏼] DRY csv parsing
-                const csv = parse(value, { ...settings, ...MANDATORY_CSV_SETTINGS });
+                const csv = csvParse(value, settings);
                 if (csv.errors.length !== 0) {
                     throw new CsvFormatError(spaceTrim$1((block) => `
                                 CSV parsing error
@@ -1823,8 +1926,7 @@ const CsvFormatDefinition = {
         {
             subvalueName: 'CELL',
             async mapValues(value, outputParameterName, settings, mapCallback) {
-                // TODO: [👨🏾‍🤝‍👨🏼] DRY csv parsing
-                const csv = parse(value, { ...settings, ...MANDATORY_CSV_SETTINGS });
+                const csv = csvParse(value, settings);
                 if (csv.errors.length !== 0) {
                     throw new CsvFormatError(spaceTrim$1((block) => `
                                 CSV parsing error
@@ -1861,6 +1963,9 @@ const CsvFormatDefinition = {
 /**
  * Function isValidJsonString will tell you if the string is valid JSON or not
  *
+ * @param value The string to check
+ * @returns True if the string is a valid JSON string, false otherwise
+ *
  * @public exported from `@promptbook/utils`
  */
 function isValidJsonString(value /* <- [👨‍⚖️] */) {
@@ -1869,9 +1974,7 @@ function isValidJsonString(value /* <- [👨‍⚖️] */) {
         return true;
     }
     catch (error) {
-        if (!(error instanceof Error)) {
-            throw error;
-        }
+        assertsError(error);
         if (error.message.includes('Unexpected token')) {
             return false;
         }
@@ -1955,6 +2058,30 @@ const TextFormatDefinition = {
  * TODO: [🏢] Allow to expect something inside each item of list and other formats
  */
 
+/**
+ * Function to check if a string is valid XML
+ *
+ * @param value
+ * @returns True if the string is a valid XML string, false otherwise
+ *
+ * @public exported from `@promptbook/utils`
+ */
+function isValidXmlString(value) {
+    try {
+        const parser = new DOMParser();
+        const parsedDocument = parser.parseFromString(value, 'application/xml');
+        const parserError = parsedDocument.getElementsByTagName('parsererror');
+        if (parserError.length > 0) {
+            return false;
+        }
+        return true;
+    }
+    catch (error) {
+        assertsError(error);
+        return false;
+    }
+}
+
 /**
  * Definition for XML format
  *
@@ -1964,7 +2091,7 @@ const XmlFormatDefinition = {
     formatName: 'XML',
     mimeType: 'application/xml',
     isValid(value, settings, schema) {
-        return true;
+        return isValidXmlString(value);
     },
     canBeValid(partialValue, settings, schema) {
         return true;
@@ -2189,9 +2316,7 @@ function checkSerializableAsJson(options) {
                 JSON.stringify(value); // <- TODO: [0]
             }
             catch (error) {
-                if (!(error instanceof Error)) {
-                    throw error;
-                }
+                assertsError(error);
                 throw new UnexpectedError(spaceTrim$1((block) => `
                             \`${name}\` is not serializable
 
@@ -4846,9 +4971,7 @@ function extractVariablesFromJavascript(script) {
             }
     }
     catch (error) {
-        if (!(error instanceof Error)) {
-            throw error;
-        }
+        assertsError(error);
         throw new ParseError(spaceTrim((block) => `
                     Can not extract variables from the script
                     ${block(error.stack || error.message)}