@juspay/neurolink 8.7.0 → 8.9.0

package/CHANGELOG.md

@@ -1,3 +1,15 @@
+## [8.9.0](https://github.com/juspay/neurolink/compare/v8.8.0...v8.9.0) (2025-12-11)
+
+### Features
+
+- **(csv):** add sampleDataFormat option for CSV metadata ([ded6ec4](https://github.com/juspay/neurolink/commit/ded6ec4ef0924ff020de079ed3a8031490e76094))
+
+## [8.8.0](https://github.com/juspay/neurolink/compare/v8.7.0...v8.8.0) (2025-12-11)
+
+### Features
+
+- **(types):** add AudioProviderConfig type definition for transcription providers ([c34f437](https://github.com/juspay/neurolink/commit/c34f437455fba20b803b84811b9dda143351427e))
+
 ## [8.7.0](https://github.com/juspay/neurolink/compare/v8.6.0...v8.7.0) (2025-12-10)
 
 ### Features

package/dist/lib/types/fileTypes.d.ts

@@ -41,7 +41,7 @@ export type FileProcessingResult = {
         rowCount?: number;
         columnCount?: number;
         columnNames?: string[];
-        sampleData?: string;
+        sampleData?: string | unknown[];
         hasEmptyColumns?: boolean;
         version?: string;
         estimatedPages?: number | null;
@@ -49,6 +49,14 @@ export type FileProcessingResult = {
         apiType?: PDFAPIType;
     };
 };
+/**
+ * Sample data format options for CSV metadata
+ * - 'json': JSON string representation (default, backward compatible)
+ * - 'object': Structured array of row objects (best for programmatic use)
+ * - 'csv': CSV formatted string preview
+ * - 'markdown': Markdown table format
+ */
+export type SampleDataFormat = "object" | "json" | "csv" | "markdown";
 /**
  * CSV processor options
  */
@@ -56,6 +64,7 @@ export type CSVProcessorOptions = {
     maxRows?: number;
     formatStyle?: "raw" | "markdown" | "json";
     includeHeaders?: boolean;
+    sampleDataFormat?: SampleDataFormat;
 };
 /**
  * PDF API types for different providers
@@ -80,6 +89,52 @@ export type PDFProcessorOptions = {
     maxSizeMB?: number;
     bedrockApiMode?: "converse" | "invokeModel";
 };
+/**
+ * Audio provider configuration for transcription services
+ *
+ * Describes the capabilities and limitations of each audio transcription provider
+ * (e.g., OpenAI Whisper, Google Speech-to-Text, Azure Speech Services).
+ *
+ * @example OpenAI Whisper configuration
+ * ```typescript
+ * const openaiConfig: AudioProviderConfig = {
+ *   maxSizeMB: 25,
+ *   maxDurationSeconds: 600,
+ *   supportedFormats: ['mp3', 'mp4', 'm4a', 'wav', 'webm'],
+ *   supportsLanguageDetection: true,
+ *   requiresApiKey: true,
+ *   costPer60s: 0.006  // $0.006 per minute
+ * };
+ * ```
+ *
+ * @example Google Speech-to-Text configuration
+ * ```typescript
+ * const googleConfig: AudioProviderConfig = {
+ *   maxSizeMB: 10,
+ *   maxDurationSeconds: 480,
+ *   supportedFormats: ['flac', 'wav', 'mp3', 'ogg'],
+ *   supportsLanguageDetection: true,
+ *   requiresApiKey: true,
+ *   costPer15s: 0.004  // $0.016 per minute ($0.004 per 15 seconds)
+ * };
+ * ```
+ */
+export type AudioProviderConfig = {
+    /** Maximum audio file size in megabytes */
+    maxSizeMB: number;
+    /** Maximum audio duration in seconds */
+    maxDurationSeconds: number;
+    /** Supported audio formats (e.g., 'mp3', 'wav', 'm4a', 'flac', 'ogg') */
+    supportedFormats: string[];
+    /** Whether the provider supports automatic language detection */
+    supportsLanguageDetection: boolean;
+    /** Whether the provider requires an API key for authentication */
+    requiresApiKey: boolean;
+    /** Optional: Cost per 60 seconds of audio in USD */
+    costPer60s?: number;
+    /** Optional: Cost per 15 seconds of audio in USD */
+    costPer15s?: number;
+};
 /**
  * Audio processor options
  */

package/dist/lib/utils/csvProcessor.d.ts

@@ -65,4 +65,21 @@ export declare class CSVProcessor {
      * Best for small datasets (<100 rows)
      */
     private static toMarkdownTable;
+    /**
+     * Format sample data according to the specified format
+     *
+     * @param sampleRows - Array of sample row objects
+     * @param format - Output format for sample data
+     * @param includeHeaders - Whether to include headers in CSV/markdown formats
+     * @returns Formatted sample data as string or array
+     */
+    private static formatSampleData;
+    /**
+     * Convert row objects to CSV string format
+     *
+     * @param rows - Array of row objects
+     * @param includeHeaders - Whether to include header row
+     * @returns CSV formatted string
+     */
+    private static toCSVString;
 }

package/dist/lib/utils/csvProcessor.js

@@ -62,7 +62,7 @@ export class CSVProcessor {
      * @returns Formatted CSV data ready for LLM (JSON or Markdown)
      */
     static async process(content, options) {
-        const { maxRows: rawMaxRows = 1000, formatStyle = "raw", includeHeaders = true, } = options || {};
+        const { maxRows: rawMaxRows = 1000, formatStyle = "raw", includeHeaders = true, sampleDataFormat = "json", } = options || {};
         const maxRows = Math.max(1, Math.min(10000, rawMaxRows));
         const csvString = content.toString("utf-8");
         // For raw format, return original CSV with row limit (no parsing needed)
@@ -103,9 +103,7 @@ export class CSVProcessor {
         const columnCount = columnNames.length;
         const hasEmptyColumns = columnNames.some((col) => !col || col.trim() === "");
         const sampleRows = rows.slice(0, 3);
-        const sampleData = sampleRows.length > 0
-            ? JSON.stringify(sampleRows, null, 2)
-            : "No data rows";
+        const sampleData = this.formatSampleData(sampleRows, sampleDataFormat, includeHeaders);
         // Format parsed data
         const formatted = this.formatForLLM(rows, formatStyle, includeHeaders);
         logger.info(`[CSVProcessor] ${formatStyle} format: ${rowCount} rows × ${columnCount} columns → ${formatted.length} chars`, { rowCount, columnCount, columns: columnNames, hasEmptyColumns });
@@ -274,5 +272,59 @@ export class CSVProcessor {
         });
         return markdown;
     }
+    /**
+     * Format sample data according to the specified format
+     *
+     * @param sampleRows - Array of sample row objects
+     * @param format - Output format for sample data
+     * @param includeHeaders - Whether to include headers in CSV/markdown formats
+     * @returns Formatted sample data as string or array
+     */
+    static formatSampleData(sampleRows, format, includeHeaders) {
+        if (sampleRows.length === 0) {
+            return format === "object" ? [] : "No data rows";
+        }
+        switch (format) {
+            case "object":
+                return sampleRows;
+            case "json":
+                return JSON.stringify(sampleRows, null, 2);
+            case "csv":
+                return this.toCSVString(sampleRows, includeHeaders);
+            case "markdown":
+                return this.toMarkdownTable(sampleRows, includeHeaders);
+            default:
+                return sampleRows;
+        }
+    }
+    /**
+     * Convert row objects to CSV string format
+     *
+     * @param rows - Array of row objects
+     * @param includeHeaders - Whether to include header row
+     * @returns CSV formatted string
+     */
+    static toCSVString(rows, includeHeaders) {
+        if (rows.length === 0) {
+            return "";
+        }
+        const headers = Object.keys(rows[0]);
+        // Escape CSV values (wrap in quotes if contains comma, quote, or newline)
+        const escapeCSV = (value) => {
+            if (value.includes(",") || value.includes('"') || value.includes("\n")) {
+                return `"${value.replace(/"/g, '""')}"`;
+            }
+            return value;
+        };
+        const lines = [];
+        if (includeHeaders) {
+            lines.push(headers.map(escapeCSV).join(","));
+        }
+        rows.forEach((row) => {
+            const values = headers.map((h) => escapeCSV(String(row[h] ?? "")));
+            lines.push(values.join(","));
+        });
+        return lines.join("\n");
+    }
 }
 //# sourceMappingURL=csvProcessor.js.map

package/dist/types/fileTypes.d.ts

@@ -41,7 +41,7 @@ export type FileProcessingResult = {
         rowCount?: number;
         columnCount?: number;
         columnNames?: string[];
-        sampleData?: string;
+        sampleData?: string | unknown[];
         hasEmptyColumns?: boolean;
         version?: string;
         estimatedPages?: number | null;
@@ -49,6 +49,14 @@ export type FileProcessingResult = {
         apiType?: PDFAPIType;
     };
 };
+/**
+ * Sample data format options for CSV metadata
+ * - 'json': JSON string representation (default, backward compatible)
+ * - 'object': Structured array of row objects (best for programmatic use)
+ * - 'csv': CSV formatted string preview
+ * - 'markdown': Markdown table format
+ */
+export type SampleDataFormat = "object" | "json" | "csv" | "markdown";
 /**
  * CSV processor options
  */
@@ -56,6 +64,7 @@ export type CSVProcessorOptions = {
     maxRows?: number;
     formatStyle?: "raw" | "markdown" | "json";
     includeHeaders?: boolean;
+    sampleDataFormat?: SampleDataFormat;
 };
 /**
  * PDF API types for different providers
@@ -80,6 +89,52 @@ export type PDFProcessorOptions = {
     maxSizeMB?: number;
     bedrockApiMode?: "converse" | "invokeModel";
 };
+/**
+ * Audio provider configuration for transcription services
+ *
+ * Describes the capabilities and limitations of each audio transcription provider
+ * (e.g., OpenAI Whisper, Google Speech-to-Text, Azure Speech Services).
+ *
+ * @example OpenAI Whisper configuration
+ * ```typescript
+ * const openaiConfig: AudioProviderConfig = {
+ *   maxSizeMB: 25,
+ *   maxDurationSeconds: 600,
+ *   supportedFormats: ['mp3', 'mp4', 'm4a', 'wav', 'webm'],
+ *   supportsLanguageDetection: true,
+ *   requiresApiKey: true,
+ *   costPer60s: 0.006  // $0.006 per minute
+ * };
+ * ```
+ *
+ * @example Google Speech-to-Text configuration
+ * ```typescript
+ * const googleConfig: AudioProviderConfig = {
+ *   maxSizeMB: 10,
+ *   maxDurationSeconds: 480,
+ *   supportedFormats: ['flac', 'wav', 'mp3', 'ogg'],
+ *   supportsLanguageDetection: true,
+ *   requiresApiKey: true,
+ *   costPer15s: 0.004  // $0.016 per minute ($0.004 per 15 seconds)
+ * };
+ * ```
+ */
+export type AudioProviderConfig = {
+    /** Maximum audio file size in megabytes */
+    maxSizeMB: number;
+    /** Maximum audio duration in seconds */
+    maxDurationSeconds: number;
+    /** Supported audio formats (e.g., 'mp3', 'wav', 'm4a', 'flac', 'ogg') */
+    supportedFormats: string[];
+    /** Whether the provider supports automatic language detection */
+    supportsLanguageDetection: boolean;
+    /** Whether the provider requires an API key for authentication */
+    requiresApiKey: boolean;
+    /** Optional: Cost per 60 seconds of audio in USD */
+    costPer60s?: number;
+    /** Optional: Cost per 15 seconds of audio in USD */
+    costPer15s?: number;
+};
 /**
  * Audio processor options
  */

package/dist/utils/csvProcessor.d.ts

@@ -65,4 +65,21 @@ export declare class CSVProcessor {
      * Best for small datasets (<100 rows)
      */
     private static toMarkdownTable;
+    /**
+     * Format sample data according to the specified format
+     *
+     * @param sampleRows - Array of sample row objects
+     * @param format - Output format for sample data
+     * @param includeHeaders - Whether to include headers in CSV/markdown formats
+     * @returns Formatted sample data as string or array
+     */
+    private static formatSampleData;
+    /**
+     * Convert row objects to CSV string format
+     *
+     * @param rows - Array of row objects
+     * @param includeHeaders - Whether to include header row
+     * @returns CSV formatted string
+     */
+    private static toCSVString;
 }

package/dist/utils/csvProcessor.js

@@ -62,7 +62,7 @@ export class CSVProcessor {
      * @returns Formatted CSV data ready for LLM (JSON or Markdown)
      */
     static async process(content, options) {
-        const { maxRows: rawMaxRows = 1000, formatStyle = "raw", includeHeaders = true, } = options || {};
+        const { maxRows: rawMaxRows = 1000, formatStyle = "raw", includeHeaders = true, sampleDataFormat = "json", } = options || {};
         const maxRows = Math.max(1, Math.min(10000, rawMaxRows));
         const csvString = content.toString("utf-8");
         // For raw format, return original CSV with row limit (no parsing needed)
@@ -103,9 +103,7 @@ export class CSVProcessor {
         const columnCount = columnNames.length;
         const hasEmptyColumns = columnNames.some((col) => !col || col.trim() === "");
         const sampleRows = rows.slice(0, 3);
-        const sampleData = sampleRows.length > 0
-            ? JSON.stringify(sampleRows, null, 2)
-            : "No data rows";
+        const sampleData = this.formatSampleData(sampleRows, sampleDataFormat, includeHeaders);
         // Format parsed data
         const formatted = this.formatForLLM(rows, formatStyle, includeHeaders);
         logger.info(`[CSVProcessor] ${formatStyle} format: ${rowCount} rows × ${columnCount} columns → ${formatted.length} chars`, { rowCount, columnCount, columns: columnNames, hasEmptyColumns });
@@ -274,4 +272,58 @@ export class CSVProcessor {
         });
         return markdown;
     }
+    /**
+     * Format sample data according to the specified format
+     *
+     * @param sampleRows - Array of sample row objects
+     * @param format - Output format for sample data
+     * @param includeHeaders - Whether to include headers in CSV/markdown formats
+     * @returns Formatted sample data as string or array
+     */
+    static formatSampleData(sampleRows, format, includeHeaders) {
+        if (sampleRows.length === 0) {
+            return format === "object" ? [] : "No data rows";
+        }
+        switch (format) {
+            case "object":
+                return sampleRows;
+            case "json":
+                return JSON.stringify(sampleRows, null, 2);
+            case "csv":
+                return this.toCSVString(sampleRows, includeHeaders);
+            case "markdown":
+                return this.toMarkdownTable(sampleRows, includeHeaders);
+            default:
+                return sampleRows;
+        }
+    }
+    /**
+     * Convert row objects to CSV string format
+     *
+     * @param rows - Array of row objects
+     * @param includeHeaders - Whether to include header row
+     * @returns CSV formatted string
+     */
+    static toCSVString(rows, includeHeaders) {
+        if (rows.length === 0) {
+            return "";
+        }
+        const headers = Object.keys(rows[0]);
+        // Escape CSV values (wrap in quotes if contains comma, quote, or newline)
+        const escapeCSV = (value) => {
+            if (value.includes(",") || value.includes('"') || value.includes("\n")) {
+                return `"${value.replace(/"/g, '""')}"`;
+            }
+            return value;
+        };
+        const lines = [];
+        if (includeHeaders) {
+            lines.push(headers.map(escapeCSV).join(","));
+        }
+        rows.forEach((row) => {
+            const values = headers.map((h) => escapeCSV(String(row[h] ?? "")));
+            lines.push(values.join(","));
+        });
+        return lines.join("\n");
+    }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@juspay/neurolink",
-  "version": "8.7.0",
+  "version": "8.9.0",
   "description": "Universal AI Development Platform with working MCP integration, multi-provider support, and professional CLI. Built-in tools operational, 58+ external MCP servers discoverable. Connect to filesystem, GitHub, database operations, and more. Build, test, and deploy AI applications with 9 major providers: OpenAI, Anthropic, Google AI, AWS Bedrock, Azure, Hugging Face, Ollama, and Mistral AI.",
   "author": {
     "name": "Juspay Technologies",