@juspay/neurolink 1.5.2 → 1.6.0

package/CHANGELOG.md

@@ -1,5 +1,92 @@
 # @juspay/neurolink
 
+## 1.6.0
+
+### Major Changes
+
+- **🎉 Universal AI Provider Support**: Expanded from 6 to 9 AI providers with support for open source models, local AI, and European compliance
+  - **🆕 Hugging Face Provider**: Access to 100,000+ open source models with community-driven AI ecosystem
+  - **🆕 Ollama Provider**: 100% local AI execution with complete data privacy and no internet required
+  - **🆕 Mistral AI Provider**: European GDPR-compliant AI with competitive pricing and multilingual models
+
+### Features
+
+- **🛠️ Enhanced CLI with Ollama Commands**: New Ollama-specific management commands
+  - `neurolink ollama list-models` - List installed local models
+  - `neurolink ollama pull <model>` - Download models locally
+  - `neurolink ollama remove <model>` - Remove installed models
+  - `neurolink ollama status` - Check Ollama service health
+  - `neurolink ollama start/stop` - Manage Ollama service
+  - `neurolink ollama setup` - Interactive setup wizard
+
+- **📚 Comprehensive Documentation**: Complete documentation for all new providers
+  - **OLLAMA-SETUP.md**: Platform-specific installation guides
+  - **PROVIDER-COMPARISON.md**: Detailed provider comparison matrix
+  - Updated all documentation to reflect 9 providers
+  - Enhanced provider configuration guides
+
+### Technical Implementation
+
+- **Provider Files**: `huggingFace.ts`, `ollama.ts`, `mistralAI.ts`
+- **Dependencies**: Added `@huggingface/inference`, `@ai-sdk/mistral`, `inquirer`
+- **MCP Integration**: All 10 MCP tools support new providers
+- **Demo Updates**: Enhanced demo to showcase all 9 providers
+- **CLI Enhancement**: Ollama command structure with 7 subcommands
+- **Provider Priority**: Updated auto-selection to include new providers
+
+### Provider Comparison
+
+| Provider | Best For | Setup Time | Privacy | Cost |
+|----------|----------|------------|---------|------|
+| OpenAI | General use | 2 min | Cloud | $$$ |
+| Ollama | Privacy | 5 min | Local | Free |
+| Hugging Face | Open source | 2 min | Cloud | Free/$$ |
+| Mistral | EU compliance | 2 min | Cloud | $$ |
+
+### Bug Fixes
+
+- **🔧 Local Provider Fallback**: Implemented no-fallback policy for Ollama
+  - When explicitly requesting `--provider ollama`, no cloud fallback occurs
+  - Preserves user privacy intent when using local providers
+  - Auto-selection still maintains intelligent fallback
+
+### Breaking Changes
+
+- None - 100% backward compatibility maintained
+
+## 1.5.3
+
+### Patch Changes
+
+- **🔧 CLI Debug Log Persistence Fix**: Fixed unwanted debug logs appearing in production deployments
+  - **Issue**: CLI showed debug logs even when `--debug` flag was not provided, cluttering production output
+  - **Root Cause**: CLI middleware had logical gap where `NEUROLINK_DEBUG` wasn't explicitly set to `'false'` when no debug flag provided, allowing inherited environment variables to persist
+  - **Solution**: Updated middleware to always set `NEUROLINK_DEBUG = 'false'` when debug mode not enabled
+  - **Impact**: **Deterministic logging behavior** - debug logs only appear when explicitly requested with `--debug` flag
+
+### Technical Changes
+
+- **Clean Production Output**: No debug logs in deployed CLI unless `--debug` flag explicitly provided
+- **Deterministic Behavior**: Logging controlled by CLI flags, not inherited environment variables
+- **Backward Compatible**: Debug mode still works perfectly when `--debug` flag is used
+- **Environment Independence**: CLI output no longer affected by external `NEUROLINK_DEBUG` settings
+
+### CLI Behavior Fix
+
+```bash
+# Before Fix (Problematic)
+neurolink generate-text "test"
+# Could show debug logs if NEUROLINK_DEBUG was set in environment
+
+# After Fix (Clean)
+neurolink generate-text "test"
+# Output: ⠋ 🤖 Generating text... ✔ ✅ Text generated successfully! [content]
+
+# Debug still works when requested
+neurolink generate-text "test" --debug
+# Output: [debug logs] + spinner + success + content
+```
+
 ## 1.5.2
 
 ### Patch Changes

package/README.md

@@ -1,12 +1,15 @@
 # 🧠 NeuroLink
 
-[![npm version](https://badge.fury.io/js/%40juspay%2Fneurolink.svg)](https://badge.fury.io/js/%40juspay%2Fneurolink)
-[![TypeScript](https://img.shields.io/badge/%3C%2F%3E-TypeScript-%230074c1.svg)](http://www.typescriptlang.org/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![NPM Version](https://img.shields.io/npm/v/@juspay/neurolink)](https://www.npmjs.com/package/@juspay/neurolink)
+[![Downloads](https://img.shields.io/npm/dm/@juspay/neurolink)](https://www.npmjs.com/package/@juspay/neurolink)
+[![GitHub Stars](https://img.shields.io/github/stars/juspay/neurolink)](https://github.com/juspay/neurolink/stargazers)
+[![License](https://img.shields.io/npm/l/@juspay/neurolink)](https://github.com/juspay/neurolink/blob/main/LICENSE)
+[![TypeScript](https://img.shields.io/badge/TypeScript-Ready-blue)](https://www.typescriptlang.org/)
+[![CI](https://github.com/juspay/neurolink/workflows/CI/badge.svg)](https://github.com/juspay/neurolink/actions)
 
-> Universal AI toolkit with 5+ provider support, automatic fallback, and both CLI + SDK interfaces. Production-ready with TypeScript support.
+> Universal AI toolkit with 9 major AI providers, automatic fallback, and both CLI + SDK interfaces. Production-ready with TypeScript support.
 
-**NeuroLink** unifies OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, and Azure OpenAI with intelligent fallback and streaming support. Available as both a **programmatic SDK** and **professional CLI tool**. Extracted from production use at Juspay.
+**NeuroLink** unifies OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, Azure OpenAI, Hugging Face, Ollama, and Mistral AI with intelligent fallback and streaming support. Available as both a **programmatic SDK** and **professional CLI tool**. Extracted from production use at Juspay.
 
 ## 🚀 Quick Start
 
@@ -57,12 +60,15 @@ npx @juspay/neurolink status
 
 ## ✨ Key Features
 
-- 🔄 **5+ AI Providers** - OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, Azure
+- 🔄 **9 AI Providers** - OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, Azure, Hugging Face, Ollama, Mistral AI
 - ⚡ **Automatic Fallback** - Never fail when providers are down
 - 🖥️ **CLI + SDK** - Use from command line or integrate programmatically
 - 🛡️ **Production Ready** - TypeScript, error handling, extracted from production
 - 🔧 **MCP Integration** - Model Context Protocol support for extensibility
 - 🤖 **AI Analysis Tools** - Built-in optimization and workflow assistance
+- 🏠 **Local AI Support** - Run completely offline with Ollama
+- 🌍 **Open Source Models** - Access 100,000+ models via Hugging Face
+- 🇪🇺 **GDPR Compliance** - European data processing with Mistral AI
 
 ## 💻 Essential Examples
 
@@ -113,9 +119,10 @@ cd neurolink-demo && node server.js
 # Visit http://localhost:9876 for live demo
 ```
 
-- **Real AI Integration**: All 5 providers functional with live generation
+- **Real AI Integration**: All 9 providers functional with live generation
 - **Complete Use Cases**: Business, creative, and developer scenarios
 - **Performance Metrics**: Live provider analytics and response times
+- **Privacy Options**: Test local AI with Ollama
 
 ### 🖥️ CLI Demonstrations
 - **[CLI Help & Commands](./docs/visual-content/cli-videos/cli-01-cli-help.mp4)** - Complete command reference
@@ -157,6 +164,9 @@ cd neurolink-demo && node server.js
 | **Google Vertex AI** | Gemini 2.5 Flash | Service Account | ❌ |
 | **Anthropic** | Claude 3.5 Sonnet | API Key | ❌ |
 | **Azure OpenAI** | GPT-4, GPT-3.5 | API Key + Endpoint | ❌ |
+| **Hugging Face** 🆕 | 100,000+ models | API Key | ✅ |
+| **Ollama** 🆕 | Llama 2, Code Llama, Mistral | None (Local) | ✅ |
+| **Mistral AI** 🆕 | Tiny, Small, Medium, Large | API Key | ❌ |
 
 **✨ Auto-Selection**: NeuroLink automatically chooses the best available provider based on speed, reliability, and configuration.
 

package/dist/cli/commands/config.d.ts

@@ -7,7 +7,7 @@
  */
 import { z } from 'zod';
 declare const ConfigSchema: z.ZodObject<{
-    defaultProvider: z.ZodDefault<z.ZodEnum<["auto", "openai", "bedrock", "vertex", "anthropic", "azure", "google-ai", "huggingface"]>>;
+    defaultProvider: z.ZodDefault<z.ZodEnum<["auto", "openai", "bedrock", "vertex", "anthropic", "azure", "google-ai", "huggingface", "ollama", "mistral"]>>;
     providers: z.ZodDefault<z.ZodObject<{
         openai: z.ZodOptional<z.ZodObject<{
             apiKey: z.ZodOptional<z.ZodString>;
@@ -112,6 +112,29 @@ declare const ConfigSchema: z.ZodObject<{
             model?: string | undefined;
             apiKey?: string | undefined;
         }>>;
+        ollama: z.ZodOptional<z.ZodObject<{
+            baseUrl: z.ZodDefault<z.ZodString>;
+            model: z.ZodDefault<z.ZodString>;
+            timeout: z.ZodDefault<z.ZodNumber>;
+        }, "strip", z.ZodTypeAny, {
+            model: string;
+            timeout: number;
+            baseUrl: string;
+        }, {
+            model?: string | undefined;
+            timeout?: number | undefined;
+            baseUrl?: string | undefined;
+        }>>;
+        mistral: z.ZodOptional<z.ZodObject<{
+            apiKey: z.ZodOptional<z.ZodString>;
+            model: z.ZodDefault<z.ZodString>;
+        }, "strip", z.ZodTypeAny, {
+            model: string;
+            apiKey?: string | undefined;
+        }, {
+            model?: string | undefined;
+            apiKey?: string | undefined;
+        }>>;
     }, "strip", z.ZodTypeAny, {
         bedrock?: {
             model: string;
@@ -152,6 +175,15 @@ declare const ConfigSchema: z.ZodObject<{
             model: string;
             apiKey?: string | undefined;
         } | undefined;
+        ollama?: {
+            model: string;
+            timeout: number;
+            baseUrl: string;
+        } | undefined;
+        mistral?: {
+            model: string;
+            apiKey?: string | undefined;
+        } | undefined;
     }, {
         bedrock?: {
             model?: string | undefined;
@@ -192,6 +224,15 @@ declare const ConfigSchema: z.ZodObject<{
             model?: string | undefined;
             apiKey?: string | undefined;
         } | undefined;
+        ollama?: {
+            model?: string | undefined;
+            timeout?: number | undefined;
+            baseUrl?: string | undefined;
+        } | undefined;
+        mistral?: {
+            model?: string | undefined;
+            apiKey?: string | undefined;
+        } | undefined;
     }>>;
     profiles: z.ZodDefault<z.ZodRecord<z.ZodString, z.ZodAny>>;
     preferences: z.ZodDefault<z.ZodObject<{
@@ -217,7 +258,7 @@ declare const ConfigSchema: z.ZodObject<{
         cacheStrategy?: "file" | "memory" | "redis" | undefined;
     }>>;
 }, "strip", z.ZodTypeAny, {
-    defaultProvider: "bedrock" | "openai" | "vertex" | "anthropic" | "azure" | "google-ai" | "auto" | "huggingface";
+    defaultProvider: "bedrock" | "openai" | "vertex" | "anthropic" | "azure" | "google-ai" | "huggingface" | "ollama" | "mistral" | "auto";
     providers: {
         bedrock?: {
             model: string;
@@ -258,6 +299,15 @@ declare const ConfigSchema: z.ZodObject<{
             model: string;
             apiKey?: string | undefined;
         } | undefined;
+        ollama?: {
+            model: string;
+            timeout: number;
+            baseUrl: string;
+        } | undefined;
+        mistral?: {
+            model: string;
+            apiKey?: string | undefined;
+        } | undefined;
     };
     profiles: Record<string, any>;
     preferences: {
@@ -269,7 +319,7 @@ declare const ConfigSchema: z.ZodObject<{
         cacheStrategy: "file" | "memory" | "redis";
     };
 }, {
-    defaultProvider?: "bedrock" | "openai" | "vertex" | "anthropic" | "azure" | "google-ai" | "auto" | "huggingface" | undefined;
+    defaultProvider?: "bedrock" | "openai" | "vertex" | "anthropic" | "azure" | "google-ai" | "huggingface" | "ollama" | "mistral" | "auto" | undefined;
     providers?: {
         bedrock?: {
             model?: string | undefined;
@@ -310,6 +360,15 @@ declare const ConfigSchema: z.ZodObject<{
             model?: string | undefined;
             apiKey?: string | undefined;
         } | undefined;
+        ollama?: {
+            model?: string | undefined;
+            timeout?: number | undefined;
+            baseUrl?: string | undefined;
+        } | undefined;
+        mistral?: {
+            model?: string | undefined;
+            apiKey?: string | undefined;
+        } | undefined;
     } | undefined;
     profiles?: Record<string, any> | undefined;
     preferences?: {
@@ -375,6 +434,14 @@ export declare class ConfigManager {
      * Hugging Face provider setup
      */
     private setupHuggingFace;
+    /**
+     * Ollama provider setup
+     */
+    private setupOllama;
+    /**
+     * Mistral AI provider setup
+     */
+    private setupMistral;
     /**
      * Get current configuration
      */

package/dist/cli/commands/config.js

@@ -13,7 +13,7 @@ import chalk from 'chalk';
 import { z } from 'zod';
 // Configuration schema for validation
 const ConfigSchema = z.object({
-    defaultProvider: z.enum(['auto', 'openai', 'bedrock', 'vertex', 'anthropic', 'azure', 'google-ai', 'huggingface']).default('auto'),
+    defaultProvider: z.enum(['auto', 'openai', 'bedrock', 'vertex', 'anthropic', 'azure', 'google-ai', 'huggingface', 'ollama', 'mistral']).default('auto'),
     providers: z.object({
         openai: z.object({
             apiKey: z.string().optional(),
@@ -53,6 +53,15 @@ const ConfigSchema = z.object({
         huggingface: z.object({
             apiKey: z.string().optional(),
             model: z.string().default('microsoft/DialoGPT-large')
+        }).optional(),
+        ollama: z.object({
+            baseUrl: z.string().default('http://localhost:11434'),
+            model: z.string().default('llama2'),
+            timeout: z.number().default(60000)
+        }).optional(),
+        mistral: z.object({
+            apiKey: z.string().optional(),
+            model: z.string().default('mistral-small')
         }).optional()
     }).default({}),
     profiles: z.record(z.string(), z.any()).default({}),
@@ -128,7 +137,8 @@ export class ConfigManager {
                         { name: 'Anthropic - Claude models (direct)', value: 'anthropic' },
                         { name: 'Azure OpenAI - Enterprise GPT', value: 'azure' },
                         { name: 'Google AI Studio - Gemini models (direct)', value: 'google-ai' },
-                        { name: 'Hugging Face - Open source models', value: 'huggingface' }
+                        { name: 'Hugging Face - Open source models', value: 'huggingface' },
+                        { name: 'Mistral AI - European AI with competitive pricing', value: 'mistral' }
                     ],
                     default: this.config.defaultProvider
                 },
@@ -190,7 +200,9 @@ export class ConfigManager {
                     { name: 'Anthropic Direct (Claude)', value: 'anthropic' },
                     { name: 'Azure OpenAI (Enterprise)', value: 'azure' },
                     { name: 'Google AI Studio (Gemini Direct)', value: 'google-ai' },
-                    { name: 'Hugging Face (Open Source)', value: 'huggingface' }
+                    { name: 'Hugging Face (Open Source)', value: 'huggingface' },
+                    { name: 'Ollama (Local AI Models)', value: 'ollama' },
+                    { name: 'Mistral AI (European AI)', value: 'mistral' }
                 ]
             }
         ]);
@@ -225,6 +237,12 @@ export class ConfigManager {
             case 'huggingface':
                 await this.setupHuggingFace();
                 break;
+            case 'ollama':
+                await this.setupOllama();
+                break;
+            case 'mistral':
+                await this.setupMistral();
+                break;
         }
     }
     /**
@@ -496,6 +514,60 @@ export class ConfigManager {
         ]);
         this.config.providers.huggingface = answers;
     }
+    /**
+     * Ollama provider setup
+     */
+    async setupOllama() {
+        const answers = await inquirer.prompt([
+            {
+                type: 'input',
+                name: 'baseUrl',
+                message: 'Ollama base URL:',
+                default: 'http://localhost:11434',
+                validate: (value) => value.startsWith('http') || 'URL should start with http:// or https://'
+            },
+            {
+                type: 'input',
+                name: 'model',
+                message: 'Default model:',
+                default: 'llama2'
+            },
+            {
+                type: 'number',
+                name: 'timeout',
+                message: 'Request timeout (milliseconds):',
+                default: 60000,
+                validate: (value) => value > 0 || 'Timeout must be positive'
+            }
+        ]);
+        this.config.providers.ollama = answers;
+    }
+    /**
+     * Mistral AI provider setup
+     */
+    async setupMistral() {
+        const answers = await inquirer.prompt([
+            {
+                type: 'password',
+                name: 'apiKey',
+                message: 'Mistral AI API Key:',
+                validate: (value) => value.length > 0 || 'API key is required'
+            },
+            {
+                type: 'list',
+                name: 'model',
+                message: 'Default model:',
+                choices: [
+                    'mistral-small',
+                    'mistral-medium',
+                    'mistral-large',
+                    'mistral-tiny'
+                ],
+                default: 'mistral-small'
+            }
+        ]);
+        this.config.providers.mistral = answers;
+    }
     /**
      * Get current configuration
      */

package/dist/cli/commands/ollama.d.ts

@@ -0,0 +1,8 @@
+import type { Argv } from 'yargs';
+export declare const ollamaCommand: {
+    command: string;
+    describe: string;
+    builder: (yargs: Argv) => Argv<{}>;
+    handler: () => void;
+};
+export default ollamaCommand;