Compare commits
62 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
574f7a594c | ||
|
|
0b2a058550 | ||
|
|
88d15c89e5 | ||
|
|
4bf7113334 | ||
| 6bdbeae144 | |||
| 09c27379cb | |||
| 2bc6f7ee5e | |||
| 0ac50d647d | |||
| 5f9ffc7356 | |||
| 502b665224 | |||
| bda0d7ed7e | |||
| de2a60d12f | |||
| 5b3a93a43a | |||
| 6b241f8889 | |||
| 0a80ac0a8a | |||
| 6ce442354e | |||
| 9b38a3c06e | |||
| 5dead05324 | |||
| 6916dd9e2a | |||
| f89888a542 | |||
| d93b198b09 | |||
| 9e390d0fdb | |||
| 8329ee861e | |||
| b8585a0afb | |||
| c96f5118cf | |||
| 17e1a1f1e1 | |||
| de940dff75 | |||
| 4fc1e029e4 | |||
| d0a4151a2b | |||
| ad5dd4799b | |||
| 1c49af74ac | |||
| eda8ce36df | |||
| e82c510094 | |||
| 0378308721 | |||
| 189a32683f | |||
| f731b9f78d | |||
| 3701e21284 | |||
| 490d4996d2 | |||
| f099a8f1ed | |||
| a0228a0abc | |||
| a5257b52e7 | |||
| a4144fc071 | |||
| af46b3e81e | |||
| d50427937c | |||
| ffde2e0bf1 | |||
| 82abc06da4 | |||
| 3a5f2d52e5 | |||
| f628a71184 | |||
| d1465fc868 | |||
| 9e19d320e1 | |||
| 158d49fa95 | |||
| 1ce412fd00 | |||
| 92c382c16e | |||
| 63d3b7c9bb | |||
| 2e4c6aa80a | |||
| 04d505d29e | |||
| a636556fdb | |||
| a1558e6306 | |||
| 8b79cd025a | |||
| 268178f024 | |||
| 181193352e | |||
| 616ef168a5 |
191
changelog.md
Normal file
191
changelog.md
Normal file
@@ -0,0 +1,191 @@
|
||||
# Changelog
|
||||
|
||||
## 2025-08-01 - 0.5.9 - fix(documentation)
|
||||
Remove contribution section from readme
|
||||
|
||||
- Removed the contribution section from readme.md as requested
|
||||
- Kept the roadmap section for future development plans
|
||||
|
||||
## 2025-08-01 - 0.5.8 - fix(core)
|
||||
Fix SmartPdf lifecycle management and update dependencies
|
||||
|
||||
- Moved SmartPdf instance management to the MultiModalModel base class for better resource sharing
|
||||
- Fixed memory leaks by properly implementing cleanup in the base class stop() method
|
||||
- Updated SmartAi class to properly stop all providers on shutdown
|
||||
- Updated @push.rocks/smartrequest from v2.1.0 to v4.2.1 with migration to new API
|
||||
- Enhanced readme with professional documentation and feature matrix
|
||||
|
||||
## 2025-07-26 - 0.5.7 - fix(provider.openai)
|
||||
Fix stream type mismatch in audio method
|
||||
|
||||
- Fixed type error where OpenAI SDK returns a web ReadableStream but the audio method needs to return a Node.js ReadableStream
|
||||
- Added conversion using Node.js's built-in Readable.fromWeb() method
|
||||
|
||||
## 2025-07-25 - 0.5.5 - feat(documentation)
|
||||
Comprehensive documentation enhancement and test improvements
|
||||
|
||||
- Completely rewrote readme.md with detailed provider comparisons, advanced usage examples, and performance tips
|
||||
- Added comprehensive examples for all supported providers (OpenAI, Anthropic, Perplexity, Groq, XAI, Ollama, Exo)
|
||||
- Included detailed sections on chat interactions, streaming, TTS, vision processing, and document analysis
|
||||
- Added verbose flag to test script for better debugging
|
||||
|
||||
## 2025-05-13 - 0.5.4 - fix(provider.openai)
|
||||
Update dependency versions, clean test imports, and adjust default OpenAI model configurations
|
||||
|
||||
- Bump dependency versions in package.json (@git.zone/tsbuild, @push.rocks/tapbundle, openai, etc.)
|
||||
- Change default chatModel from 'gpt-4o' to 'o4-mini' and visionModel from 'gpt-4o' to '04-mini' in provider.openai.ts
|
||||
- Remove unused 'expectAsync' import from test file
|
||||
|
||||
## 2025-04-03 - 0.5.3 - fix(package.json)
|
||||
Add explicit packageManager field to package.json
|
||||
|
||||
- Include the packageManager property to specify the pnpm version and checksum.
|
||||
- Align package metadata with current standards.
|
||||
|
||||
## 2025-04-03 - 0.5.2 - fix(readme)
|
||||
Remove redundant conclusion section from README to streamline documentation.
|
||||
|
||||
- Eliminated the conclusion block describing SmartAi's capabilities and documentation pointers.
|
||||
|
||||
## 2025-02-25 - 0.5.1 - fix(OpenAiProvider)
|
||||
Corrected audio model ID in OpenAiProvider
|
||||
|
||||
- Fixed audio model identifier from 'o3-mini' to 'tts-1-hd' in the OpenAiProvider's audio method.
|
||||
- Addressed minor code formatting issues in test suite for better readability.
|
||||
- Corrected spelling errors in test documentation and comments.
|
||||
|
||||
## 2025-02-25 - 0.5.0 - feat(documentation and configuration)
|
||||
Enhanced package and README documentation
|
||||
|
||||
- Expanded the package description to better reflect the library's capabilities.
|
||||
- Improved README with detailed usage examples for initialization, chat interactions, streaming chat, audio generation, document analysis, and vision processing.
|
||||
- Provided error handling strategies and advanced streaming customization examples.
|
||||
|
||||
## 2025-02-25 - 0.4.2 - fix(core)
|
||||
Fix OpenAI chat streaming and PDF document processing logic.
|
||||
|
||||
- Updated OpenAI chat streaming to handle new async iterable format.
|
||||
- Improved PDF document processing by filtering out empty image buffers.
|
||||
- Removed unsupported temperature options from OpenAI requests.
|
||||
|
||||
## 2025-02-25 - 0.4.1 - fix(provider)
|
||||
Fix provider modules for consistency
|
||||
|
||||
- Updated TypeScript interfaces and options in provider modules for better type safety.
|
||||
- Modified transform stream handlers in Exo, Groq, and Ollama providers for consistency.
|
||||
- Added optional model options to OpenAI provider for custom model usage.
|
||||
|
||||
## 2025-02-08 - 0.4.0 - feat(core)
|
||||
Added support for Exo AI provider
|
||||
|
||||
- Introduced ExoProvider with chat functionalities.
|
||||
- Updated SmartAi class to initialize ExoProvider.
|
||||
- Extended Conversation class to support ExoProvider.
|
||||
|
||||
## 2025-02-05 - 0.3.3 - fix(documentation)
|
||||
Update readme with detailed license and legal information.
|
||||
|
||||
- Added explicit section on License and Legal Information in the README.
|
||||
- Clarified the use of trademarks and company information.
|
||||
|
||||
## 2025-02-05 - 0.3.2 - fix(documentation)
|
||||
Remove redundant badges from readme
|
||||
|
||||
- Removed Build Status badge from the readme file.
|
||||
- Removed License badge from the readme file.
|
||||
|
||||
## 2025-02-05 - 0.3.1 - fix(documentation)
|
||||
Updated README structure and added detailed usage examples
|
||||
|
||||
- Introduced a Table of Contents
|
||||
- Included comprehensive sections for chat, streaming chat, audio generation, document processing, and vision processing
|
||||
- Added example code and detailed configuration steps for supported AI providers
|
||||
- Clarified the development setup with instructions for running tests and building the project
|
||||
|
||||
## 2025-02-05 - 0.3.0 - feat(integration-xai)
|
||||
Add support for X.AI provider with chat and document processing capabilities.
|
||||
|
||||
- Introduced XAIProvider class for integrating X.AI features.
|
||||
- Implemented chat streaming and synchronous chat for X.AI.
|
||||
- Enabled document processing capabilities with PDF conversion in X.AI.
|
||||
|
||||
## 2025-02-03 - 0.2.0 - feat(provider.anthropic)
|
||||
Add support for vision and document processing in Anthropic provider
|
||||
|
||||
- Implemented vision tasks for Anthropic provider using Claude-3-opus-20240229 model.
|
||||
- Implemented document processing for Anthropic provider, supporting conversion of PDF documents to images and analysis with Claude-3-opus-20240229 model.
|
||||
- Updated documentation to reflect the new capabilities of the Anthropic provider.
|
||||
|
||||
## 2025-02-03 - 0.1.0 - feat(providers)
|
||||
Add vision and document processing capabilities to providers
|
||||
|
||||
- OpenAI and Ollama providers now support vision tasks using GPT-4 Vision and Llava models respectively.
|
||||
- Document processing has been implemented for OpenAI and Ollama providers, converting PDFs to images for analysis.
|
||||
- Introduced abstract methods for vision and document processing in the MultiModalModel class.
|
||||
- Updated the readme file with examples for vision and document processing.
|
||||
|
||||
## 2025-02-03 - 0.0.19 - fix(core)
|
||||
Enhanced chat streaming and error handling across providers
|
||||
|
||||
- Refactored chatStream method to properly handle input streams and processes in Perplexity, OpenAI, Ollama, and Anthropic providers.
|
||||
- Improved error handling and message parsing in chatStream implementations.
|
||||
- Defined distinct interfaces for chat options, messages, and responses.
|
||||
- Adjusted the test logic in test/test.ts for the new classification response requirement.
|
||||
|
||||
## 2024-09-19 - 0.0.18 - fix(dependencies)
|
||||
Update dependencies to the latest versions.
|
||||
|
||||
- Updated @git.zone/tsbuild from ^2.1.76 to ^2.1.84
|
||||
- Updated @git.zone/tsrun from ^1.2.46 to ^1.2.49
|
||||
- Updated @push.rocks/tapbundle from ^5.0.23 to ^5.3.0
|
||||
- Updated @types/node from ^20.12.12 to ^22.5.5
|
||||
- Updated @anthropic-ai/sdk from ^0.21.0 to ^0.27.3
|
||||
- Updated @push.rocks/smartfile from ^11.0.14 to ^11.0.21
|
||||
- Updated @push.rocks/smartpromise from ^4.0.3 to ^4.0.4
|
||||
- Updated @push.rocks/webstream from ^1.0.8 to ^1.0.10
|
||||
- Updated openai from ^4.47.1 to ^4.62.1
|
||||
|
||||
## 2024-05-29 - 0.0.17 - Documentation
|
||||
Updated project description.
|
||||
|
||||
- Improved project description for clarity and details.
|
||||
|
||||
## 2024-05-17 - 0.0.16 to 0.0.15 - Core
|
||||
Fixes and updates.
|
||||
|
||||
- Various core updates and fixes for stability improvements.
|
||||
|
||||
## 2024-04-29 - 0.0.14 to 0.0.13 - Core
|
||||
Fixes and updates.
|
||||
|
||||
- Multiple core updates and fixes for enhanced functionality.
|
||||
|
||||
## 2024-04-29 - 0.0.12 - Core
|
||||
Fixes and updates.
|
||||
|
||||
- Core update and bug fixes.
|
||||
|
||||
## 2024-04-29 - 0.0.11 - Provider
|
||||
Fix integration for anthropic provider.
|
||||
|
||||
- Correction in the integration process with anthropic provider for better compatibility.
|
||||
|
||||
## 2024-04-27 - 0.0.10 to 0.0.9 - Core
|
||||
Fixes and updates.
|
||||
|
||||
- Updates and fixes to core components.
|
||||
- Updated tsconfig for improved TypeScript configuration.
|
||||
|
||||
## 2024-04-01 - 0.0.8 to 0.0.7 - Core and npmextra
|
||||
Core updates and npmextra configuration.
|
||||
|
||||
- Core fixes and updates.
|
||||
- Updates to npmextra.json for githost configuration.
|
||||
|
||||
## 2024-03-31 - 0.0.6 to 0.0.2 - Core
|
||||
Initial core updates and fixes.
|
||||
|
||||
- Multiple updates and fixes to core following initial versions.
|
||||
|
||||
|
||||
This summarizes the relevant updates and changes based on the provided commit messages. The changelog excludes commits that are version tags without meaningful content or repeated entries.
|
||||
19
license
Normal file
19
license
Normal file
@@ -0,0 +1,19 @@
|
||||
Copyright (c) 2024 Task Venture Capital GmbH (hello@task.vc)
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
@@ -5,14 +5,41 @@
|
||||
"githost": "code.foss.global",
|
||||
"gitscope": "push.rocks",
|
||||
"gitrepo": "smartai",
|
||||
"description": "a standardaized interface to talk to AI models",
|
||||
"description": "SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.",
|
||||
"npmPackagename": "@push.rocks/smartai",
|
||||
"license": "MIT",
|
||||
"projectDomain": "push.rocks"
|
||||
"projectDomain": "push.rocks",
|
||||
"keywords": [
|
||||
"AI integration",
|
||||
"TypeScript",
|
||||
"chatbot",
|
||||
"OpenAI",
|
||||
"Anthropic",
|
||||
"multi-model",
|
||||
"audio generation",
|
||||
"text-to-speech",
|
||||
"document processing",
|
||||
"vision processing",
|
||||
"streaming chat",
|
||||
"API",
|
||||
"multiple providers",
|
||||
"AI models",
|
||||
"synchronous chat",
|
||||
"asynchronous chat",
|
||||
"real-time interaction",
|
||||
"content analysis",
|
||||
"image description",
|
||||
"document classification",
|
||||
"AI toolkit",
|
||||
"provider switching"
|
||||
]
|
||||
}
|
||||
},
|
||||
"npmci": {
|
||||
"npmGlobalTools": [],
|
||||
"npmAccessLevel": "public"
|
||||
},
|
||||
"tsdoc": {
|
||||
"legal": "\n## License and Legal Information\n\nThis repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. \n\n**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.\n\n### Trademarks\n\nThis project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.\n\n### Company Information\n\nTask Venture Capital GmbH \nRegistered at District court Bremen HRB 35230 HB, Germany\n\nFor any legal inquiries or if you require further information, please contact us via email at hello@task.vc.\n\nBy using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.\n"
|
||||
}
|
||||
}
|
||||
68
package.json
68
package.json
@@ -1,41 +1,46 @@
|
||||
{
|
||||
"name": "@push.rocks/smartai",
|
||||
"version": "0.0.6",
|
||||
"version": "0.5.9",
|
||||
"private": false,
|
||||
"description": "a standardaized interface to talk to AI models",
|
||||
"description": "SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.",
|
||||
"main": "dist_ts/index.js",
|
||||
"typings": "dist_ts/index.d.ts",
|
||||
"type": "module",
|
||||
"author": "Task Venture Capital GmbH",
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"test": "(tstest test/ --web)",
|
||||
"test": "(tstest test/ --web --verbose)",
|
||||
"build": "(tsbuild --web --allowimplicitany)",
|
||||
"buildDocs": "(tsdoc)"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@git.zone/tsbuild": "^2.1.25",
|
||||
"@git.zone/tsbundle": "^2.0.5",
|
||||
"@git.zone/tsrun": "^1.2.46",
|
||||
"@git.zone/tstest": "^1.0.44",
|
||||
"@push.rocks/tapbundle": "^5.0.15",
|
||||
"@types/node": "^20.8.7"
|
||||
"@git.zone/tsbuild": "^2.6.4",
|
||||
"@git.zone/tsbundle": "^2.5.1",
|
||||
"@git.zone/tsrun": "^1.3.3",
|
||||
"@git.zone/tstest": "^2.3.2",
|
||||
"@push.rocks/qenv": "^6.1.0",
|
||||
"@push.rocks/tapbundle": "^6.0.3",
|
||||
"@types/node": "^22.15.17"
|
||||
},
|
||||
"dependencies": {
|
||||
"@push.rocks/qenv": "^6.0.5",
|
||||
"@push.rocks/smartfile": "^11.0.4",
|
||||
"@push.rocks/smartpath": "^5.0.11",
|
||||
"@push.rocks/smartpromise": "^4.0.3",
|
||||
"openai": "^4.31.0"
|
||||
"@anthropic-ai/sdk": "^0.57.0",
|
||||
"@push.rocks/smartarray": "^1.1.0",
|
||||
"@push.rocks/smartfile": "^11.2.5",
|
||||
"@push.rocks/smartpath": "^6.0.0",
|
||||
"@push.rocks/smartpdf": "^3.3.0",
|
||||
"@push.rocks/smartpromise": "^4.2.3",
|
||||
"@push.rocks/smartrequest": "^4.2.1",
|
||||
"@push.rocks/webstream": "^1.0.10",
|
||||
"openai": "^5.11.0"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "git+https://code.foss.global/push.rocks/smartai.git"
|
||||
"url": "https://code.foss.global/push.rocks/smartai.git"
|
||||
},
|
||||
"bugs": {
|
||||
"url": "https://code.foss.global/push.rocks/smartai/issues"
|
||||
},
|
||||
"homepage": "https://code.foss.global/push.rocks/smartai#readme",
|
||||
"homepage": "https://code.foss.global/push.rocks/smartai",
|
||||
"browserslist": [
|
||||
"last 1 chrome versions"
|
||||
],
|
||||
@@ -50,5 +55,36 @@
|
||||
"cli.js",
|
||||
"npmextra.json",
|
||||
"readme.md"
|
||||
],
|
||||
"keywords": [
|
||||
"AI integration",
|
||||
"TypeScript",
|
||||
"chatbot",
|
||||
"OpenAI",
|
||||
"Anthropic",
|
||||
"multi-model",
|
||||
"audio generation",
|
||||
"text-to-speech",
|
||||
"document processing",
|
||||
"vision processing",
|
||||
"streaming chat",
|
||||
"API",
|
||||
"multiple providers",
|
||||
"AI models",
|
||||
"synchronous chat",
|
||||
"asynchronous chat",
|
||||
"real-time interaction",
|
||||
"content analysis",
|
||||
"image description",
|
||||
"document classification",
|
||||
"AI toolkit",
|
||||
"provider switching"
|
||||
],
|
||||
"pnpm": {
|
||||
"onlyBuiltDependencies": [
|
||||
"esbuild",
|
||||
"puppeteer"
|
||||
]
|
||||
},
|
||||
"packageManager": "pnpm@10.7.0+sha512.6b865ad4b62a1d9842b61d674a393903b871d9244954f652b8842c2b553c72176b278f64c463e52d40fff8aba385c235c8c9ecf5cc7de4fd78b8bb6d49633ab6"
|
||||
}
|
||||
|
||||
13251
pnpm-lock.yaml
generated
13251
pnpm-lock.yaml
generated
File diff suppressed because it is too large
Load Diff
1
readme.hints.md
Normal file
1
readme.hints.md
Normal file
@@ -0,0 +1 @@
|
||||
|
||||
501
readme.md
501
readme.md
@@ -1,31 +1,482 @@
|
||||
# @push.rocks/smartai
|
||||
a standardaized interface to talk to AI models
|
||||
**One API to rule them all** 🚀
|
||||
|
||||
## Availabililty and Links
|
||||
* [npmjs.org (npm package)](https://www.npmjs.com/package/@push.rocks/smartai)
|
||||
* [gitlab.com (source)](https://code.foss.global/push.rocks/smartai)
|
||||
* [github.com (source mirror)](https://github.com/push.rocks/smartai)
|
||||
* [docs (typedoc)](https://push.rocks.gitlab.io/smartai/)
|
||||
[](https://www.npmjs.com/package/@push.rocks/smartai)
|
||||
[](https://www.typescriptlang.org/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
|
||||
## Status for master
|
||||
SmartAI unifies the world's leading AI providers - OpenAI, Anthropic, Perplexity, Ollama, Groq, XAI, and Exo - under a single, elegant TypeScript interface. Build AI applications at lightning speed without vendor lock-in.
|
||||
|
||||
Status Category | Status Badge
|
||||
-- | --
|
||||
GitLab Pipelines | [](https://lossless.cloud)
|
||||
GitLab Pipline Test Coverage | [](https://lossless.cloud)
|
||||
npm | [](https://lossless.cloud)
|
||||
Snyk | [](https://lossless.cloud)
|
||||
TypeScript Support | [](https://lossless.cloud)
|
||||
node Support | [](https://nodejs.org/dist/latest-v10.x/docs/api/)
|
||||
Code Style | [](https://lossless.cloud)
|
||||
PackagePhobia (total standalone install weight) | [](https://lossless.cloud)
|
||||
PackagePhobia (package size on registry) | [](https://lossless.cloud)
|
||||
BundlePhobia (total size when bundled) | [](https://lossless.cloud)
|
||||
## 🎯 Why SmartAI?
|
||||
|
||||
## Usage
|
||||
Use TypeScript for best in class intellisense
|
||||
For further information read the linked docs at the top of this readme.
|
||||
- **🔌 Universal Interface**: Write once, run with any AI provider. Switch between GPT-4, Claude, Llama, or Grok with a single line change.
|
||||
- **🛡️ Type-Safe**: Full TypeScript support with comprehensive type definitions for all operations
|
||||
- **🌊 Streaming First**: Built for real-time applications with native streaming support
|
||||
- **🎨 Multi-Modal**: Seamlessly work with text, images, audio, and documents
|
||||
- **🏠 Local & Cloud**: Support for both cloud providers and local models via Ollama
|
||||
- **⚡ Zero Lock-In**: Your code remains portable across all AI providers
|
||||
|
||||
## Legal
|
||||
> MIT licensed | **©** [Task Venture Capital GmbH](https://task.vc)
|
||||
| By using this npm module you agree to our [privacy policy](https://lossless.gmbH/privacy)
|
||||
## 🚀 Quick Start
|
||||
|
||||
```bash
|
||||
npm install @push.rocks/smartai
|
||||
```
|
||||
|
||||
```typescript
|
||||
import { SmartAi } from '@push.rocks/smartai';
|
||||
|
||||
// Initialize with your favorite providers
|
||||
const ai = new SmartAi({
|
||||
openaiToken: 'sk-...',
|
||||
anthropicToken: 'sk-ant-...'
|
||||
});
|
||||
|
||||
await ai.start();
|
||||
|
||||
// Same API, multiple providers
|
||||
const response = await ai.openaiProvider.chat({
|
||||
systemMessage: 'You are a helpful assistant.',
|
||||
userMessage: 'Explain quantum computing in simple terms',
|
||||
messageHistory: []
|
||||
});
|
||||
```
|
||||
|
||||
## 📊 Provider Capabilities Matrix
|
||||
|
||||
Choose the right provider for your use case:
|
||||
|
||||
| Provider | Chat | Streaming | TTS | Vision | Documents | Highlights |
|
||||
|----------|:----:|:---------:|:---:|:------:|:---------:|------------|
|
||||
| **OpenAI** | ✅ | ✅ | ✅ | ✅ | ✅ | • GPT-4, DALL-E 3<br>• Industry standard<br>• Most features |
|
||||
| **Anthropic** | ✅ | ✅ | ❌ | ✅ | ✅ | • Claude 3 Opus<br>• Superior reasoning<br>• 200k context |
|
||||
| **Ollama** | ✅ | ✅ | ❌ | ✅ | ✅ | • 100% local<br>• Privacy-first<br>• No API costs |
|
||||
| **XAI** | ✅ | ✅ | ❌ | ❌ | ✅ | • Grok models<br>• Real-time data<br>• Uncensored |
|
||||
| **Perplexity** | ✅ | ✅ | ❌ | ❌ | ❌ | • Web-aware<br>• Research-focused<br>• Citations |
|
||||
| **Groq** | ✅ | ✅ | ❌ | ❌ | ❌ | • 10x faster<br>• LPU inference<br>• Low latency |
|
||||
| **Exo** | ✅ | ✅ | ❌ | ❌ | ❌ | • Distributed<br>• P2P compute<br>• Decentralized |
|
||||
|
||||
## 🎮 Core Features
|
||||
|
||||
### 💬 Universal Chat Interface
|
||||
|
||||
Works identically across all providers:
|
||||
|
||||
```typescript
|
||||
// Use GPT-4 for complex reasoning
|
||||
const gptResponse = await ai.openaiProvider.chat({
|
||||
systemMessage: 'You are a expert physicist.',
|
||||
userMessage: 'Explain the implications of quantum entanglement',
|
||||
messageHistory: []
|
||||
});
|
||||
|
||||
// Use Claude for safety-critical applications
|
||||
const claudeResponse = await ai.anthropicProvider.chat({
|
||||
systemMessage: 'You are a medical advisor.',
|
||||
userMessage: 'Review this patient data for concerns',
|
||||
messageHistory: []
|
||||
});
|
||||
|
||||
// Use Groq for lightning-fast responses
|
||||
const groqResponse = await ai.groqProvider.chat({
|
||||
systemMessage: 'You are a code reviewer.',
|
||||
userMessage: 'Quick! Find the bug in this code: ...',
|
||||
messageHistory: []
|
||||
});
|
||||
```
|
||||
|
||||
### 🌊 Real-Time Streaming
|
||||
|
||||
Build responsive chat interfaces with token-by-token streaming:
|
||||
|
||||
```typescript
|
||||
// Create a chat stream
|
||||
const stream = await ai.openaiProvider.chatStream(inputStream);
|
||||
const reader = stream.getReader();
|
||||
|
||||
// Display responses as they arrive
|
||||
while (true) {
|
||||
const { done, value } = await reader.read();
|
||||
if (done) break;
|
||||
|
||||
// Update UI in real-time
|
||||
process.stdout.write(value);
|
||||
}
|
||||
```
|
||||
|
||||
### 🎙️ Text-to-Speech
|
||||
|
||||
Generate natural voices with OpenAI:
|
||||
|
||||
```typescript
|
||||
const audioStream = await ai.openaiProvider.audio({
|
||||
message: 'Welcome to the future of AI development!'
|
||||
});
|
||||
|
||||
// Stream directly to speakers
|
||||
audioStream.pipe(speakerOutput);
|
||||
|
||||
// Or save to file
|
||||
audioStream.pipe(fs.createWriteStream('welcome.mp3'));
|
||||
```
|
||||
|
||||
### 👁️ Vision Analysis
|
||||
|
||||
Understand images with multiple providers:
|
||||
|
||||
```typescript
|
||||
const image = fs.readFileSync('product-photo.jpg');
|
||||
|
||||
// OpenAI: General purpose vision
|
||||
const gptVision = await ai.openaiProvider.vision({
|
||||
image,
|
||||
prompt: 'Describe this product and suggest marketing angles'
|
||||
});
|
||||
|
||||
// Anthropic: Detailed analysis
|
||||
const claudeVision = await ai.anthropicProvider.vision({
|
||||
image,
|
||||
prompt: 'Identify any safety concerns or defects'
|
||||
});
|
||||
|
||||
// Ollama: Private, local analysis
|
||||
const ollamaVision = await ai.ollamaProvider.vision({
|
||||
image,
|
||||
prompt: 'Extract all text and categorize the content'
|
||||
});
|
||||
```
|
||||
|
||||
### 📄 Document Intelligence
|
||||
|
||||
Extract insights from PDFs with AI:
|
||||
|
||||
```typescript
|
||||
const contract = fs.readFileSync('contract.pdf');
|
||||
const invoice = fs.readFileSync('invoice.pdf');
|
||||
|
||||
// Analyze documents
|
||||
const analysis = await ai.openaiProvider.document({
|
||||
systemMessage: 'You are a legal expert.',
|
||||
userMessage: 'Compare these documents and highlight key differences',
|
||||
messageHistory: [],
|
||||
pdfDocuments: [contract, invoice]
|
||||
});
|
||||
|
||||
// Multi-document analysis
|
||||
const taxDocs = [form1099, w2, receipts];
|
||||
const taxAnalysis = await ai.anthropicProvider.document({
|
||||
systemMessage: 'You are a tax advisor.',
|
||||
userMessage: 'Prepare a tax summary from these documents',
|
||||
messageHistory: [],
|
||||
pdfDocuments: taxDocs
|
||||
});
|
||||
```
|
||||
|
||||
### 🔄 Persistent Conversations
|
||||
|
||||
Maintain context across interactions:
|
||||
|
||||
```typescript
|
||||
// Create a coding assistant conversation
|
||||
const assistant = ai.createConversation('openai');
|
||||
await assistant.setSystemMessage('You are an expert TypeScript developer.');
|
||||
|
||||
// First question
|
||||
const inputWriter = assistant.getInputStreamWriter();
|
||||
await inputWriter.write('How do I implement a singleton pattern?');
|
||||
|
||||
// Continue the conversation
|
||||
await inputWriter.write('Now show me how to make it thread-safe');
|
||||
|
||||
// The assistant remembers the entire context
|
||||
```
|
||||
|
||||
## 🚀 Real-World Examples
|
||||
|
||||
### Build a Customer Support Bot
|
||||
|
||||
```typescript
|
||||
const supportBot = new SmartAi({
|
||||
anthropicToken: process.env.ANTHROPIC_KEY // Claude for empathetic responses
|
||||
});
|
||||
|
||||
async function handleCustomerQuery(query: string, history: ChatMessage[]) {
|
||||
try {
|
||||
const response = await supportBot.anthropicProvider.chat({
|
||||
systemMessage: `You are a helpful customer support agent.
|
||||
Be empathetic, professional, and solution-oriented.`,
|
||||
userMessage: query,
|
||||
messageHistory: history
|
||||
});
|
||||
|
||||
return response.message;
|
||||
} catch (error) {
|
||||
// Fallback to another provider if needed
|
||||
return await supportBot.openaiProvider.chat({...});
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Create a Code Review Assistant
|
||||
|
||||
```typescript
|
||||
const codeReviewer = new SmartAi({
|
||||
groqToken: process.env.GROQ_KEY // Groq for speed
|
||||
});
|
||||
|
||||
async function reviewCode(code: string, language: string) {
|
||||
const startTime = Date.now();
|
||||
|
||||
const review = await codeReviewer.groqProvider.chat({
|
||||
systemMessage: `You are a ${language} expert. Review code for:
|
||||
- Security vulnerabilities
|
||||
- Performance issues
|
||||
- Best practices
|
||||
- Potential bugs`,
|
||||
userMessage: `Review this code:\n\n${code}`,
|
||||
messageHistory: []
|
||||
});
|
||||
|
||||
console.log(`Review completed in ${Date.now() - startTime}ms`);
|
||||
return review.message;
|
||||
}
|
||||
```
|
||||
|
||||
### Build a Research Assistant
|
||||
|
||||
```typescript
|
||||
const researcher = new SmartAi({
|
||||
perplexityToken: process.env.PERPLEXITY_KEY
|
||||
});
|
||||
|
||||
async function research(topic: string) {
|
||||
// Perplexity excels at web-aware research
|
||||
const findings = await researcher.perplexityProvider.chat({
|
||||
systemMessage: 'You are a research assistant. Provide factual, cited information.',
|
||||
userMessage: `Research the latest developments in ${topic}`,
|
||||
messageHistory: []
|
||||
});
|
||||
|
||||
return findings.message;
|
||||
}
|
||||
```
|
||||
|
||||
### Local AI for Sensitive Data
|
||||
|
||||
```typescript
|
||||
const localAI = new SmartAi({
|
||||
ollama: {
|
||||
baseUrl: 'http://localhost:11434',
|
||||
model: 'llama2',
|
||||
visionModel: 'llava'
|
||||
}
|
||||
});
|
||||
|
||||
// Process sensitive documents without leaving your infrastructure
|
||||
async function analyzeSensitiveDoc(pdfBuffer: Buffer) {
|
||||
const analysis = await localAI.ollamaProvider.document({
|
||||
systemMessage: 'Extract and summarize key information.',
|
||||
userMessage: 'Analyze this confidential document',
|
||||
messageHistory: [],
|
||||
pdfDocuments: [pdfBuffer]
|
||||
});
|
||||
|
||||
// Data never leaves your servers
|
||||
return analysis.message;
|
||||
}
|
||||
```
|
||||
|
||||
## ⚡ Performance Tips
|
||||
|
||||
### 1. Provider Selection Strategy
|
||||
|
||||
```typescript
|
||||
class SmartAIRouter {
|
||||
constructor(private ai: SmartAi) {}
|
||||
|
||||
async query(message: string, requirements: {
|
||||
speed?: boolean;
|
||||
accuracy?: boolean;
|
||||
cost?: boolean;
|
||||
privacy?: boolean;
|
||||
}) {
|
||||
if (requirements.privacy) {
|
||||
return this.ai.ollamaProvider.chat({...}); // Local only
|
||||
}
|
||||
if (requirements.speed) {
|
||||
return this.ai.groqProvider.chat({...}); // 10x faster
|
||||
}
|
||||
if (requirements.accuracy) {
|
||||
return this.ai.anthropicProvider.chat({...}); // Best reasoning
|
||||
}
|
||||
// Default fallback
|
||||
return this.ai.openaiProvider.chat({...});
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 2. Streaming for Large Responses
|
||||
|
||||
```typescript
|
||||
// Don't wait for the entire response
|
||||
async function streamResponse(userQuery: string) {
|
||||
const stream = await ai.openaiProvider.chatStream(createInputStream(userQuery));
|
||||
|
||||
// Process tokens as they arrive
|
||||
for await (const chunk of stream) {
|
||||
updateUI(chunk); // Immediate feedback
|
||||
await processChunk(chunk); // Parallel processing
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 3. Parallel Multi-Provider Queries
|
||||
|
||||
```typescript
|
||||
// Get the best answer from multiple AIs
|
||||
async function consensusQuery(question: string) {
|
||||
const providers = [
|
||||
ai.openaiProvider.chat({...}),
|
||||
ai.anthropicProvider.chat({...}),
|
||||
ai.perplexityProvider.chat({...})
|
||||
];
|
||||
|
||||
const responses = await Promise.all(providers);
|
||||
return synthesizeResponses(responses);
|
||||
}
|
||||
```
|
||||
|
||||
## 🛠️ Advanced Features
|
||||
|
||||
### Custom Streaming Transformations
|
||||
|
||||
```typescript
|
||||
// Add real-time translation
|
||||
const translationStream = new TransformStream({
|
||||
async transform(chunk, controller) {
|
||||
const translated = await translateChunk(chunk);
|
||||
controller.enqueue(translated);
|
||||
}
|
||||
});
|
||||
|
||||
const responseStream = await ai.openaiProvider.chatStream(input);
|
||||
const translatedStream = responseStream.pipeThrough(translationStream);
|
||||
```
|
||||
|
||||
### Error Handling & Fallbacks
|
||||
|
||||
```typescript
|
||||
class ResilientAI {
|
||||
private providers = ['openai', 'anthropic', 'groq'];
|
||||
|
||||
async query(opts: ChatOptions): Promise<ChatResponse> {
|
||||
for (const provider of this.providers) {
|
||||
try {
|
||||
return await this.ai[`${provider}Provider`].chat(opts);
|
||||
} catch (error) {
|
||||
console.warn(`${provider} failed, trying next...`);
|
||||
continue;
|
||||
}
|
||||
}
|
||||
throw new Error('All providers failed');
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Token Counting & Cost Management
|
||||
|
||||
```typescript
|
||||
// Track usage across providers
|
||||
class UsageTracker {
|
||||
async trackedChat(provider: string, options: ChatOptions) {
|
||||
const start = Date.now();
|
||||
const response = await ai[`${provider}Provider`].chat(options);
|
||||
|
||||
const usage = {
|
||||
provider,
|
||||
duration: Date.now() - start,
|
||||
inputTokens: estimateTokens(options),
|
||||
outputTokens: estimateTokens(response.message)
|
||||
};
|
||||
|
||||
await this.logUsage(usage);
|
||||
return response;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## 📦 Installation & Setup
|
||||
|
||||
### Prerequisites
|
||||
|
||||
- Node.js 16+
|
||||
- TypeScript 4.5+
|
||||
- API keys for your chosen providers
|
||||
|
||||
### Environment Setup
|
||||
|
||||
```bash
|
||||
# Install
|
||||
npm install @push.rocks/smartai
|
||||
|
||||
# Set up environment variables
|
||||
export OPENAI_API_KEY=sk-...
|
||||
export ANTHROPIC_API_KEY=sk-ant-...
|
||||
export PERPLEXITY_API_KEY=pplx-...
|
||||
# ... etc
|
||||
```
|
||||
|
||||
### TypeScript Configuration
|
||||
|
||||
```json
|
||||
{
|
||||
"compilerOptions": {
|
||||
"target": "ES2022",
|
||||
"module": "NodeNext",
|
||||
"lib": ["ES2022"],
|
||||
"strict": true,
|
||||
"esModuleInterop": true,
|
||||
"skipLibCheck": true
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## 🎯 Choosing the Right Provider
|
||||
|
||||
| Use Case | Recommended Provider | Why |
|
||||
|----------|---------------------|-----|
|
||||
| **General Purpose** | OpenAI | Most features, stable, well-documented |
|
||||
| **Complex Reasoning** | Anthropic | Superior logical thinking, safer outputs |
|
||||
| **Research & Facts** | Perplexity | Web-aware, provides citations |
|
||||
| **Speed Critical** | Groq | 10x faster inference, sub-second responses |
|
||||
| **Privacy Critical** | Ollama | 100% local, no data leaves your servers |
|
||||
| **Real-time Data** | XAI | Access to current information |
|
||||
| **Cost Sensitive** | Ollama/Exo | Free (local) or distributed compute |
|
||||
|
||||
## 📈 Roadmap
|
||||
|
||||
- [ ] Streaming function calls
|
||||
- [ ] Image generation support
|
||||
- [ ] Voice input processing
|
||||
- [ ] Fine-tuning integration
|
||||
- [ ] Embedding support
|
||||
- [ ] Agent framework
|
||||
- [ ] More providers (Cohere, AI21, etc.)
|
||||
|
||||
## License and Legal Information
|
||||
|
||||
This repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository.
|
||||
|
||||
**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
|
||||
|
||||
### Trademarks
|
||||
|
||||
This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.
|
||||
|
||||
### Company Information
|
||||
|
||||
Task Venture Capital GmbH
|
||||
Registered at District court Bremen HRB 35230 HB, Germany
|
||||
|
||||
For any legal inquiries or if you require further information, please contact us via email at hello@task.vc.
|
||||
|
||||
By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.
|
||||
106
test/test.ts
106
test/test.ts
@@ -1,8 +1,102 @@
|
||||
import { expect, expectAsync, tap } from '@push.rocks/tapbundle';
|
||||
import * as smartai from '../ts/index.js'
|
||||
import { expect, tap } from '@push.rocks/tapbundle';
|
||||
import * as qenv from '@push.rocks/qenv';
|
||||
import * as smartrequest from '@push.rocks/smartrequest';
|
||||
import * as smartfile from '@push.rocks/smartfile';
|
||||
|
||||
tap.test('first test', async () => {
|
||||
console.log(smartai)
|
||||
})
|
||||
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||
|
||||
tap.start()
|
||||
import * as smartai from '../ts/index.js';
|
||||
|
||||
let testSmartai: smartai.SmartAi;
|
||||
|
||||
tap.test('should create a smartai instance', async () => {
|
||||
testSmartai = new smartai.SmartAi({
|
||||
openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
|
||||
});
|
||||
await testSmartai.start();
|
||||
});
|
||||
|
||||
tap.test('should create chat response with openai', async () => {
|
||||
const userMessage = 'How are you?';
|
||||
const response = await testSmartai.openaiProvider.chat({
|
||||
systemMessage: 'Hello',
|
||||
userMessage: userMessage,
|
||||
messageHistory: [],
|
||||
});
|
||||
console.log(`userMessage: ${userMessage}`);
|
||||
console.log(response.message);
|
||||
});
|
||||
|
||||
tap.test('should document a pdf', async () => {
|
||||
const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
|
||||
const pdfResponse = await smartrequest.SmartRequest.create()
|
||||
.url(pdfUrl)
|
||||
.get();
|
||||
const result = await testSmartai.openaiProvider.document({
|
||||
systemMessage: 'Classify the document. Only the following answers are allowed: "invoice", "bank account statement", "contract", "other". The answer should only contain the keyword for machine use.',
|
||||
userMessage: "Classify the document.",
|
||||
messageHistory: [],
|
||||
pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
|
||||
});
|
||||
console.log(result);
|
||||
});
|
||||
|
||||
tap.test('should recognize companies in a pdf', async () => {
|
||||
const pdfBuffer = await smartfile.fs.toBuffer('./.nogit/demo_without_textlayer.pdf');
|
||||
const result = await testSmartai.openaiProvider.document({
|
||||
systemMessage: `
|
||||
summarize the document.
|
||||
|
||||
answer in JSON format, adhering to the following schema:
|
||||
\`\`\`typescript
|
||||
type TAnswer = {
|
||||
entitySender: {
|
||||
type: 'official state entity' | 'company' | 'person';
|
||||
name: string;
|
||||
address: string;
|
||||
city: string;
|
||||
country: string;
|
||||
EU: boolean; // whether the entity is within EU
|
||||
};
|
||||
entityReceiver: {
|
||||
type: 'official state entity' | 'company' | 'person';
|
||||
name: string;
|
||||
address: string;
|
||||
city: string;
|
||||
country: string;
|
||||
EU: boolean; // whether the entity is within EU
|
||||
};
|
||||
date: string; // the date of the document as YYYY-MM-DD
|
||||
title: string; // a short title, suitable for a filename
|
||||
}
|
||||
\`\`\`
|
||||
`,
|
||||
userMessage: "Classify the document.",
|
||||
messageHistory: [],
|
||||
pdfDocuments: [pdfBuffer],
|
||||
});
|
||||
console.log(result);
|
||||
});
|
||||
|
||||
tap.test('should create audio response with openai', async () => {
|
||||
// Call the audio method with a sample message.
|
||||
const audioStream = await testSmartai.openaiProvider.audio({
|
||||
message: 'This is a test of audio generation.',
|
||||
});
|
||||
// Read all chunks from the stream.
|
||||
const chunks: Uint8Array[] = [];
|
||||
for await (const chunk of audioStream) {
|
||||
chunks.push(chunk as Uint8Array);
|
||||
}
|
||||
const audioBuffer = Buffer.concat(chunks);
|
||||
await smartfile.fs.toFs(audioBuffer, './.nogit/testoutput.mp3');
|
||||
console.log(`Audio Buffer length: ${audioBuffer.length}`);
|
||||
// Assert that the resulting buffer is not empty.
|
||||
expect(audioBuffer.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
tap.test('should stop the smartai instance', async () => {
|
||||
await testSmartai.stop();
|
||||
});
|
||||
|
||||
export default tap.start();
|
||||
@@ -1,8 +1,8 @@
|
||||
/**
|
||||
* autocreated commitinfo by @pushrocks/commitinfo
|
||||
* autocreated commitinfo by @push.rocks/commitinfo
|
||||
*/
|
||||
export const commitinfo = {
|
||||
name: '@push.rocks/smartai',
|
||||
version: '0.0.6',
|
||||
description: 'a standardaized interface to talk to AI models'
|
||||
version: '0.5.4',
|
||||
description: 'SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.'
|
||||
}
|
||||
|
||||
@@ -1,8 +1,101 @@
|
||||
export abstract class MultiModal {
|
||||
abstract start(): Promise<void>;
|
||||
abstract stop(): Promise<void>;
|
||||
import * as plugins from './plugins.js';
|
||||
|
||||
// Defines a streaming interface for chat interactions.
|
||||
// The implementation will vary based on the specific AI model.
|
||||
abstract chatStream(input: ReadableStream<string>): ReadableStream<string>;
|
||||
/**
|
||||
* Message format for chat interactions
|
||||
*/
|
||||
export interface ChatMessage {
|
||||
role: 'assistant' | 'user' | 'system';
|
||||
content: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Options for chat interactions
|
||||
*/
|
||||
export interface ChatOptions {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
messageHistory: ChatMessage[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Response format for chat interactions
|
||||
*/
|
||||
export interface ChatResponse {
|
||||
role: 'assistant';
|
||||
message: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Abstract base class for multi-modal AI models.
|
||||
* Provides a common interface for different AI providers (OpenAI, Anthropic, Perplexity, Ollama)
|
||||
*/
|
||||
export abstract class MultiModalModel {
|
||||
/**
|
||||
* SmartPdf instance for document processing
|
||||
* Shared across all methods that need PDF functionality
|
||||
*/
|
||||
protected smartpdfInstance: plugins.smartpdf.SmartPdf;
|
||||
|
||||
/**
|
||||
* Initializes the model and any necessary resources
|
||||
* Should be called before using any other methods
|
||||
*/
|
||||
public async start(): Promise<void> {
|
||||
this.smartpdfInstance = new plugins.smartpdf.SmartPdf();
|
||||
await this.smartpdfInstance.start();
|
||||
}
|
||||
|
||||
/**
|
||||
* Cleans up any resources used by the model
|
||||
* Should be called when the model is no longer needed
|
||||
*/
|
||||
public async stop(): Promise<void> {
|
||||
if (this.smartpdfInstance) {
|
||||
await this.smartpdfInstance.stop();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Synchronous chat interaction with the model
|
||||
* @param optionsArg Options containing system message, user message, and message history
|
||||
* @returns Promise resolving to the assistant's response
|
||||
*/
|
||||
public abstract chat(optionsArg: ChatOptions): Promise<ChatResponse>;
|
||||
|
||||
/**
|
||||
* Streaming interface for chat interactions
|
||||
* Allows for real-time responses from the model
|
||||
* @param input Stream of user messages
|
||||
* @returns Stream of model responses
|
||||
*/
|
||||
public abstract chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>>;
|
||||
|
||||
/**
|
||||
* Text-to-speech conversion
|
||||
* @param optionsArg Options containing the message to convert to speech
|
||||
* @returns Promise resolving to a readable stream of audio data
|
||||
* @throws Error if the provider doesn't support audio generation
|
||||
*/
|
||||
public abstract audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream>;
|
||||
|
||||
/**
|
||||
* Vision-language processing
|
||||
* @param optionsArg Options containing the image and prompt for analysis
|
||||
* @returns Promise resolving to the model's description or analysis of the image
|
||||
* @throws Error if the provider doesn't support vision tasks
|
||||
*/
|
||||
public abstract vision(optionsArg: { image: Buffer; prompt: string }): Promise<string>;
|
||||
|
||||
/**
|
||||
* Document analysis and processing
|
||||
* @param optionsArg Options containing system message, user message, PDF documents, and message history
|
||||
* @returns Promise resolving to the model's analysis of the documents
|
||||
* @throws Error if the provider doesn't support document processing
|
||||
*/
|
||||
public abstract document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: ChatMessage[];
|
||||
}): Promise<{ message: any }>;
|
||||
}
|
||||
|
||||
152
ts/classes.conversation.ts
Normal file
152
ts/classes.conversation.ts
Normal file
@@ -0,0 +1,152 @@
|
||||
import type { SmartAi } from "./classes.smartai.js";
|
||||
import { OpenAiProvider } from "./provider.openai.js";
|
||||
|
||||
type TProcessFunction = (input: string) => Promise<string>;
|
||||
|
||||
export interface IConversationOptions {
|
||||
processFunction: TProcessFunction;
|
||||
}
|
||||
|
||||
/**
|
||||
* a conversation
|
||||
*/
|
||||
export class Conversation {
|
||||
// STATIC
|
||||
public static async createWithOpenAi(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.openaiProvider) {
|
||||
throw new Error('OpenAI provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
public static async createWithAnthropic(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.anthropicProvider) {
|
||||
throw new Error('Anthropic provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
public static async createWithPerplexity(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.perplexityProvider) {
|
||||
throw new Error('Perplexity provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
public static async createWithExo(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.exoProvider) {
|
||||
throw new Error('Exo provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
public static async createWithOllama(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.ollamaProvider) {
|
||||
throw new Error('Ollama provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
public static async createWithGroq(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.groqProvider) {
|
||||
throw new Error('Groq provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
public static async createWithXai(smartaiRefArg: SmartAi) {
|
||||
if (!smartaiRefArg.xaiProvider) {
|
||||
throw new Error('XAI provider not available');
|
||||
}
|
||||
const conversation = new Conversation(smartaiRefArg, {
|
||||
processFunction: async (input) => {
|
||||
return '' // TODO implement proper streaming
|
||||
}
|
||||
});
|
||||
return conversation;
|
||||
}
|
||||
|
||||
// INSTANCE
|
||||
smartaiRef: SmartAi
|
||||
private systemMessage: string;
|
||||
private processFunction: TProcessFunction;
|
||||
private inputStreamWriter: WritableStreamDefaultWriter<string> | null = null;
|
||||
private outputStreamController: ReadableStreamDefaultController<string> | null = null;
|
||||
|
||||
constructor(smartairefArg: SmartAi, options: IConversationOptions) {
|
||||
this.processFunction = options.processFunction;
|
||||
}
|
||||
|
||||
public async setSystemMessage(systemMessageArg: string) {
|
||||
this.systemMessage = systemMessageArg;
|
||||
}
|
||||
|
||||
private setupOutputStream(): ReadableStream<string> {
|
||||
return new ReadableStream<string>({
|
||||
start: (controller) => {
|
||||
this.outputStreamController = controller;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
private setupInputStream(): WritableStream<string> {
|
||||
const writableStream = new WritableStream<string>({
|
||||
write: async (chunk) => {
|
||||
const processedData = await this.processFunction(chunk);
|
||||
if (this.outputStreamController) {
|
||||
this.outputStreamController.enqueue(processedData);
|
||||
}
|
||||
},
|
||||
close: () => {
|
||||
this.outputStreamController?.close();
|
||||
},
|
||||
abort: (err) => {
|
||||
console.error('Stream aborted', err);
|
||||
this.outputStreamController?.error(err);
|
||||
}
|
||||
});
|
||||
return writableStream;
|
||||
}
|
||||
|
||||
public getInputStreamWriter(): WritableStreamDefaultWriter<string> {
|
||||
if (!this.inputStreamWriter) {
|
||||
const inputStream = this.setupInputStream();
|
||||
this.inputStreamWriter = inputStream.getWriter();
|
||||
}
|
||||
return this.inputStreamWriter;
|
||||
}
|
||||
|
||||
public getOutputStream(): ReadableStream<string> {
|
||||
return this.setupOutputStream();
|
||||
}
|
||||
}
|
||||
141
ts/classes.smartai.ts
Normal file
141
ts/classes.smartai.ts
Normal file
@@ -0,0 +1,141 @@
|
||||
import { Conversation } from './classes.conversation.js';
|
||||
import * as plugins from './plugins.js';
|
||||
import { AnthropicProvider } from './provider.anthropic.js';
|
||||
import { OllamaProvider } from './provider.ollama.js';
|
||||
import { OpenAiProvider } from './provider.openai.js';
|
||||
import { PerplexityProvider } from './provider.perplexity.js';
|
||||
import { ExoProvider } from './provider.exo.js';
|
||||
import { GroqProvider } from './provider.groq.js';
|
||||
import { XAIProvider } from './provider.xai.js';
|
||||
|
||||
|
||||
export interface ISmartAiOptions {
|
||||
openaiToken?: string;
|
||||
anthropicToken?: string;
|
||||
perplexityToken?: string;
|
||||
groqToken?: string;
|
||||
xaiToken?: string;
|
||||
exo?: {
|
||||
baseUrl?: string;
|
||||
apiKey?: string;
|
||||
};
|
||||
ollama?: {
|
||||
baseUrl?: string;
|
||||
model?: string;
|
||||
visionModel?: string;
|
||||
};
|
||||
}
|
||||
|
||||
export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama' | 'exo' | 'groq' | 'xai';
|
||||
|
||||
export class SmartAi {
|
||||
public options: ISmartAiOptions;
|
||||
|
||||
public openaiProvider: OpenAiProvider;
|
||||
public anthropicProvider: AnthropicProvider;
|
||||
public perplexityProvider: PerplexityProvider;
|
||||
public ollamaProvider: OllamaProvider;
|
||||
public exoProvider: ExoProvider;
|
||||
public groqProvider: GroqProvider;
|
||||
public xaiProvider: XAIProvider;
|
||||
|
||||
constructor(optionsArg: ISmartAiOptions) {
|
||||
this.options = optionsArg;
|
||||
}
|
||||
|
||||
public async start() {
|
||||
if (this.options.openaiToken) {
|
||||
this.openaiProvider = new OpenAiProvider({
|
||||
openaiToken: this.options.openaiToken,
|
||||
});
|
||||
await this.openaiProvider.start();
|
||||
}
|
||||
if (this.options.anthropicToken) {
|
||||
this.anthropicProvider = new AnthropicProvider({
|
||||
anthropicToken: this.options.anthropicToken,
|
||||
});
|
||||
await this.anthropicProvider.start();
|
||||
}
|
||||
if (this.options.perplexityToken) {
|
||||
this.perplexityProvider = new PerplexityProvider({
|
||||
perplexityToken: this.options.perplexityToken,
|
||||
});
|
||||
await this.perplexityProvider.start();
|
||||
}
|
||||
if (this.options.groqToken) {
|
||||
this.groqProvider = new GroqProvider({
|
||||
groqToken: this.options.groqToken,
|
||||
});
|
||||
await this.groqProvider.start();
|
||||
}
|
||||
if (this.options.xaiToken) {
|
||||
this.xaiProvider = new XAIProvider({
|
||||
xaiToken: this.options.xaiToken,
|
||||
});
|
||||
await this.xaiProvider.start();
|
||||
}
|
||||
if (this.options.ollama) {
|
||||
this.ollamaProvider = new OllamaProvider({
|
||||
baseUrl: this.options.ollama.baseUrl,
|
||||
model: this.options.ollama.model,
|
||||
visionModel: this.options.ollama.visionModel,
|
||||
});
|
||||
await this.ollamaProvider.start();
|
||||
}
|
||||
if (this.options.exo) {
|
||||
this.exoProvider = new ExoProvider({
|
||||
exoBaseUrl: this.options.exo.baseUrl,
|
||||
apiKey: this.options.exo.apiKey,
|
||||
});
|
||||
await this.exoProvider.start();
|
||||
}
|
||||
}
|
||||
|
||||
public async stop() {
|
||||
if (this.openaiProvider) {
|
||||
await this.openaiProvider.stop();
|
||||
}
|
||||
if (this.anthropicProvider) {
|
||||
await this.anthropicProvider.stop();
|
||||
}
|
||||
if (this.perplexityProvider) {
|
||||
await this.perplexityProvider.stop();
|
||||
}
|
||||
if (this.groqProvider) {
|
||||
await this.groqProvider.stop();
|
||||
}
|
||||
if (this.xaiProvider) {
|
||||
await this.xaiProvider.stop();
|
||||
}
|
||||
if (this.ollamaProvider) {
|
||||
await this.ollamaProvider.stop();
|
||||
}
|
||||
if (this.exoProvider) {
|
||||
await this.exoProvider.stop();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* create a new conversation
|
||||
*/
|
||||
createConversation(provider: TProvider) {
|
||||
switch (provider) {
|
||||
case 'exo':
|
||||
return Conversation.createWithExo(this);
|
||||
case 'openai':
|
||||
return Conversation.createWithOpenAi(this);
|
||||
case 'anthropic':
|
||||
return Conversation.createWithAnthropic(this);
|
||||
case 'perplexity':
|
||||
return Conversation.createWithPerplexity(this);
|
||||
case 'ollama':
|
||||
return Conversation.createWithOllama(this);
|
||||
case 'groq':
|
||||
return Conversation.createWithGroq(this);
|
||||
case 'xai':
|
||||
return Conversation.createWithXai(this);
|
||||
default:
|
||||
throw new Error('Provider not available');
|
||||
}
|
||||
}
|
||||
}
|
||||
15
ts/classes.tts.ts
Normal file
15
ts/classes.tts.ts
Normal file
@@ -0,0 +1,15 @@
|
||||
import type { SmartAi } from './classes.smartai.js';
|
||||
import * as plugins from './plugins.js';
|
||||
|
||||
export class TTS {
|
||||
public static async createWithOpenAi(smartaiRef: SmartAi): Promise<TTS> {
|
||||
return new TTS(smartaiRef);
|
||||
}
|
||||
|
||||
// INSTANCE
|
||||
smartaiRef: SmartAi;
|
||||
|
||||
constructor(smartairefArg: SmartAi) {
|
||||
this.smartaiRef = smartairefArg;
|
||||
}
|
||||
}
|
||||
@@ -1,3 +1,3 @@
|
||||
export * from './smartai.classes.smartai.js';
|
||||
export * from './classes.smartai.js';
|
||||
export * from './abstract.classes.multimodal.js';
|
||||
export * from './provider.openai.js';
|
||||
|
||||
0
ts/interfaces.ts
Normal file
0
ts/interfaces.ts
Normal file
@@ -7,20 +7,30 @@ export {
|
||||
|
||||
// @push.rocks scope
|
||||
import * as qenv from '@push.rocks/qenv';
|
||||
import * as smartpath from '@push.rocks/smartpath';
|
||||
import * as smartpromise from '@push.rocks/smartpromise';
|
||||
import * as smartarray from '@push.rocks/smartarray';
|
||||
import * as smartfile from '@push.rocks/smartfile';
|
||||
import * as smartpath from '@push.rocks/smartpath';
|
||||
import * as smartpdf from '@push.rocks/smartpdf';
|
||||
import * as smartpromise from '@push.rocks/smartpromise';
|
||||
import * as smartrequest from '@push.rocks/smartrequest';
|
||||
import * as webstream from '@push.rocks/webstream';
|
||||
|
||||
export {
|
||||
smartarray,
|
||||
qenv,
|
||||
smartpath,
|
||||
smartpromise,
|
||||
smartfile,
|
||||
smartpath,
|
||||
smartpdf,
|
||||
smartpromise,
|
||||
smartrequest,
|
||||
webstream,
|
||||
}
|
||||
|
||||
// third party
|
||||
import * as anthropic from '@anthropic-ai/sdk';
|
||||
import * as openai from 'openai';
|
||||
|
||||
export {
|
||||
anthropic,
|
||||
openai,
|
||||
}
|
||||
|
||||
242
ts/provider.anthropic.ts
Normal file
242
ts/provider.anthropic.ts
Normal file
@@ -0,0 +1,242 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
|
||||
import type { ImageBlockParam, TextBlockParam } from '@anthropic-ai/sdk/resources/messages';
|
||||
|
||||
type ContentBlock = ImageBlockParam | TextBlockParam;
|
||||
|
||||
export interface IAnthropicProviderOptions {
|
||||
anthropicToken: string;
|
||||
}
|
||||
|
||||
export class AnthropicProvider extends MultiModalModel {
|
||||
private options: IAnthropicProviderOptions;
|
||||
public anthropicApiClient: plugins.anthropic.default;
|
||||
|
||||
constructor(optionsArg: IAnthropicProviderOptions) {
|
||||
super();
|
||||
this.options = optionsArg // Ensure the token is stored
|
||||
}
|
||||
|
||||
async start() {
|
||||
await super.start();
|
||||
this.anthropicApiClient = new plugins.anthropic.default({
|
||||
apiKey: this.options.anthropicToken,
|
||||
});
|
||||
}
|
||||
|
||||
async stop() {
|
||||
await super.stop();
|
||||
}
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: { role: string; content: string; } | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
async transform(chunk, controller) {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = {
|
||||
role: message.role || 'user',
|
||||
content: message.content || '',
|
||||
};
|
||||
} catch (e) {
|
||||
console.error('Failed to parse message:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a complete message, send it to Anthropic
|
||||
if (currentMessage) {
|
||||
const stream = await this.anthropicApiClient.messages.create({
|
||||
model: 'claude-3-opus-20240229',
|
||||
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
||||
system: '',
|
||||
stream: true,
|
||||
max_tokens: 4000,
|
||||
});
|
||||
|
||||
// Process each chunk from Anthropic
|
||||
for await (const chunk of stream) {
|
||||
const content = chunk.delta?.text;
|
||||
if (content) {
|
||||
controller.enqueue(content);
|
||||
}
|
||||
}
|
||||
|
||||
currentMessage = null;
|
||||
}
|
||||
},
|
||||
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
controller.enqueue(message.content || '');
|
||||
} catch (e) {
|
||||
console.error('Failed to parse remaining buffer:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Connect the input to our transform stream
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
// Implementing the synchronous chat interaction
|
||||
public async chat(optionsArg: ChatOptions): Promise<ChatResponse> {
|
||||
// Convert message history to Anthropic format
|
||||
const messages = optionsArg.messageHistory.map(msg => ({
|
||||
role: msg.role === 'assistant' ? 'assistant' as const : 'user' as const,
|
||||
content: msg.content
|
||||
}));
|
||||
|
||||
const result = await this.anthropicApiClient.messages.create({
|
||||
model: 'claude-3-opus-20240229',
|
||||
system: optionsArg.systemMessage,
|
||||
messages: [
|
||||
...messages,
|
||||
{ role: 'user' as const, content: optionsArg.userMessage }
|
||||
],
|
||||
max_tokens: 4000,
|
||||
});
|
||||
|
||||
// Extract text content from the response
|
||||
let message = '';
|
||||
for (const block of result.content) {
|
||||
if ('text' in block) {
|
||||
message += block.text;
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
role: 'assistant' as const,
|
||||
message,
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
// Anthropic does not provide an audio API, so this method is not implemented.
|
||||
throw new Error('Audio generation is not yet supported by Anthropic.');
|
||||
}
|
||||
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
const base64Image = optionsArg.image.toString('base64');
|
||||
|
||||
const content: ContentBlock[] = [
|
||||
{
|
||||
type: 'text',
|
||||
text: optionsArg.prompt
|
||||
},
|
||||
{
|
||||
type: 'image',
|
||||
source: {
|
||||
type: 'base64',
|
||||
media_type: 'image/jpeg',
|
||||
data: base64Image
|
||||
}
|
||||
}
|
||||
];
|
||||
|
||||
const result = await this.anthropicApiClient.messages.create({
|
||||
model: 'claude-3-opus-20240229',
|
||||
messages: [{
|
||||
role: 'user',
|
||||
content
|
||||
}],
|
||||
max_tokens: 1024
|
||||
});
|
||||
|
||||
// Extract text content from the response
|
||||
let message = '';
|
||||
for (const block of result.content) {
|
||||
if ('text' in block) {
|
||||
message += block.text;
|
||||
}
|
||||
}
|
||||
return message;
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: ChatMessage[];
|
||||
}): Promise<{ message: any }> {
|
||||
// Convert PDF documents to images using SmartPDF
|
||||
let documentImageBytesArray: Uint8Array[] = [];
|
||||
|
||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
||||
documentImageBytesArray = documentImageBytesArray.concat(documentImageArray);
|
||||
}
|
||||
|
||||
// Convert message history to Anthropic format
|
||||
const messages = optionsArg.messageHistory.map(msg => ({
|
||||
role: msg.role === 'assistant' ? 'assistant' as const : 'user' as const,
|
||||
content: msg.content
|
||||
}));
|
||||
|
||||
// Create content array with text and images
|
||||
const content: ContentBlock[] = [
|
||||
{
|
||||
type: 'text',
|
||||
text: optionsArg.userMessage
|
||||
}
|
||||
];
|
||||
|
||||
// Add each document page as an image
|
||||
for (const imageBytes of documentImageBytesArray) {
|
||||
content.push({
|
||||
type: 'image',
|
||||
source: {
|
||||
type: 'base64',
|
||||
media_type: 'image/jpeg',
|
||||
data: Buffer.from(imageBytes).toString('base64')
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
const result = await this.anthropicApiClient.messages.create({
|
||||
model: 'claude-3-opus-20240229',
|
||||
system: optionsArg.systemMessage,
|
||||
messages: [
|
||||
...messages,
|
||||
{ role: 'user', content }
|
||||
],
|
||||
max_tokens: 4096
|
||||
});
|
||||
|
||||
// Extract text content from the response
|
||||
let message = '';
|
||||
for (const block of result.content) {
|
||||
if ('text' in block) {
|
||||
message += block.text;
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: message
|
||||
}
|
||||
};
|
||||
}
|
||||
}
|
||||
128
ts/provider.exo.ts
Normal file
128
ts/provider.exo.ts
Normal file
@@ -0,0 +1,128 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
|
||||
import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
|
||||
|
||||
export interface IExoProviderOptions {
|
||||
exoBaseUrl?: string;
|
||||
apiKey?: string;
|
||||
}
|
||||
|
||||
export class ExoProvider extends MultiModalModel {
|
||||
private options: IExoProviderOptions;
|
||||
public openAiApiClient: plugins.openai.default;
|
||||
|
||||
constructor(optionsArg: IExoProviderOptions = {}) {
|
||||
super();
|
||||
this.options = {
|
||||
exoBaseUrl: 'http://localhost:8080/v1', // Default Exo API endpoint
|
||||
...optionsArg
|
||||
};
|
||||
}
|
||||
|
||||
public async start() {
|
||||
this.openAiApiClient = new plugins.openai.default({
|
||||
apiKey: this.options.apiKey || 'not-needed', // Exo might not require an API key for local deployment
|
||||
baseURL: this.options.exoBaseUrl,
|
||||
});
|
||||
}
|
||||
|
||||
public async stop() {}
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: { role: string; content: string; } | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
transform: async (chunk, controller) => {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = message;
|
||||
|
||||
// Process the message based on its type
|
||||
if (message.type === 'message') {
|
||||
const response = await this.chat({
|
||||
systemMessage: '',
|
||||
userMessage: message.content,
|
||||
messageHistory: [{ role: message.role as 'user' | 'assistant' | 'system', content: message.content }]
|
||||
});
|
||||
|
||||
controller.enqueue(JSON.stringify(response) + '\n');
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Error processing message:', error);
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
currentMessage = message;
|
||||
} catch (error) {
|
||||
console.error('Error processing remaining buffer:', error);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
public async chat(options: ChatOptions): Promise<ChatResponse> {
|
||||
const messages: ChatCompletionMessageParam[] = [
|
||||
{ role: 'system', content: options.systemMessage },
|
||||
...options.messageHistory,
|
||||
{ role: 'user', content: options.userMessage }
|
||||
];
|
||||
|
||||
try {
|
||||
const response = await this.openAiApiClient.chat.completions.create({
|
||||
model: 'local-model', // Exo uses local models
|
||||
messages: messages,
|
||||
stream: false
|
||||
});
|
||||
|
||||
return {
|
||||
role: 'assistant',
|
||||
message: response.choices[0]?.message?.content || ''
|
||||
};
|
||||
} catch (error) {
|
||||
console.error('Error in chat completion:', error);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
throw new Error('Audio generation is not supported by Exo provider');
|
||||
}
|
||||
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
throw new Error('Vision processing is not supported by Exo provider');
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: ChatMessage[];
|
||||
}): Promise<{ message: any }> {
|
||||
throw new Error('Document processing is not supported by Exo provider');
|
||||
}
|
||||
}
|
||||
192
ts/provider.groq.ts
Normal file
192
ts/provider.groq.ts
Normal file
@@ -0,0 +1,192 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
|
||||
|
||||
export interface IGroqProviderOptions {
|
||||
groqToken: string;
|
||||
model?: string;
|
||||
}
|
||||
|
||||
export class GroqProvider extends MultiModalModel {
|
||||
private options: IGroqProviderOptions;
|
||||
private baseUrl = 'https://api.groq.com/v1';
|
||||
|
||||
constructor(optionsArg: IGroqProviderOptions) {
|
||||
super();
|
||||
this.options = {
|
||||
...optionsArg,
|
||||
model: optionsArg.model || 'llama-3.3-70b-versatile', // Default model
|
||||
};
|
||||
}
|
||||
|
||||
async start() {}
|
||||
|
||||
async stop() {}
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: { role: string; content: string; } | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
transform: async (chunk, controller) => {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = {
|
||||
role: message.role || 'user',
|
||||
content: message.content || '',
|
||||
};
|
||||
} catch (e) {
|
||||
console.error('Failed to parse message:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a complete message, send it to Groq
|
||||
if (currentMessage) {
|
||||
const response = await fetch(`${this.baseUrl}/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Authorization': `Bearer ${this.options.groqToken}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.options.model,
|
||||
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
||||
stream: true,
|
||||
}),
|
||||
});
|
||||
|
||||
// Process each chunk from Groq
|
||||
const reader = response.body?.getReader();
|
||||
if (reader) {
|
||||
try {
|
||||
while (true) {
|
||||
const { done, value } = await reader.read();
|
||||
if (done) break;
|
||||
|
||||
const chunk = new TextDecoder().decode(value);
|
||||
const lines = chunk.split('\n');
|
||||
|
||||
for (const line of lines) {
|
||||
if (line.startsWith('data: ')) {
|
||||
const data = line.slice(6);
|
||||
if (data === '[DONE]') break;
|
||||
|
||||
try {
|
||||
const parsed = JSON.parse(data);
|
||||
const content = parsed.choices[0]?.delta?.content;
|
||||
if (content) {
|
||||
controller.enqueue(content);
|
||||
}
|
||||
} catch (e) {
|
||||
console.error('Failed to parse SSE data:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
reader.releaseLock();
|
||||
}
|
||||
}
|
||||
|
||||
currentMessage = null;
|
||||
}
|
||||
},
|
||||
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
controller.enqueue(message.content || '');
|
||||
} catch (e) {
|
||||
console.error('Failed to parse remaining buffer:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Connect the input to our transform stream
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
// Implementing the synchronous chat interaction
|
||||
public async chat(optionsArg: ChatOptions): Promise<ChatResponse> {
|
||||
const messages = [
|
||||
// System message
|
||||
{
|
||||
role: 'system',
|
||||
content: optionsArg.systemMessage,
|
||||
},
|
||||
// Message history
|
||||
...optionsArg.messageHistory.map(msg => ({
|
||||
role: msg.role,
|
||||
content: msg.content,
|
||||
})),
|
||||
// User message
|
||||
{
|
||||
role: 'user',
|
||||
content: optionsArg.userMessage,
|
||||
},
|
||||
];
|
||||
|
||||
const response = await fetch(`${this.baseUrl}/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Authorization': `Bearer ${this.options.groqToken}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.options.model,
|
||||
messages,
|
||||
temperature: 0.7,
|
||||
max_completion_tokens: 1024,
|
||||
stream: false,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
const error = await response.json();
|
||||
throw new Error(`Groq API error: ${error.message || response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
|
||||
return {
|
||||
role: 'assistant',
|
||||
message: result.choices[0].message.content,
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
// Groq does not provide an audio API, so this method is not implemented.
|
||||
throw new Error('Audio generation is not yet supported by Groq.');
|
||||
}
|
||||
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
throw new Error('Vision tasks are not yet supported by Groq.');
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: ChatMessage[];
|
||||
}): Promise<{ message: any }> {
|
||||
throw new Error('Document processing is not yet supported by Groq.');
|
||||
}
|
||||
}
|
||||
254
ts/provider.ollama.ts
Normal file
254
ts/provider.ollama.ts
Normal file
@@ -0,0 +1,254 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
|
||||
|
||||
export interface IOllamaProviderOptions {
|
||||
baseUrl?: string;
|
||||
model?: string;
|
||||
visionModel?: string; // Model to use for vision tasks (e.g. 'llava')
|
||||
}
|
||||
|
||||
export class OllamaProvider extends MultiModalModel {
|
||||
private options: IOllamaProviderOptions;
|
||||
private baseUrl: string;
|
||||
private model: string;
|
||||
private visionModel: string;
|
||||
|
||||
constructor(optionsArg: IOllamaProviderOptions = {}) {
|
||||
super();
|
||||
this.options = optionsArg;
|
||||
this.baseUrl = optionsArg.baseUrl || 'http://localhost:11434';
|
||||
this.model = optionsArg.model || 'llama2';
|
||||
this.visionModel = optionsArg.visionModel || 'llava';
|
||||
}
|
||||
|
||||
async start() {
|
||||
await super.start();
|
||||
// Verify Ollama is running
|
||||
try {
|
||||
const response = await fetch(`${this.baseUrl}/api/tags`);
|
||||
if (!response.ok) {
|
||||
throw new Error('Failed to connect to Ollama server');
|
||||
}
|
||||
} catch (error) {
|
||||
throw new Error(`Failed to connect to Ollama server at ${this.baseUrl}: ${error.message}`);
|
||||
}
|
||||
}
|
||||
|
||||
async stop() {
|
||||
await super.stop();
|
||||
}
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: { role: string; content: string; } | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
transform: async (chunk, controller) => {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = {
|
||||
role: message.role || 'user',
|
||||
content: message.content || '',
|
||||
};
|
||||
} catch (e) {
|
||||
console.error('Failed to parse message:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a complete message, send it to Ollama
|
||||
if (currentMessage) {
|
||||
const response = await fetch(`${this.baseUrl}/api/chat`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.model,
|
||||
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
||||
stream: true,
|
||||
}),
|
||||
});
|
||||
|
||||
// Process each chunk from Ollama
|
||||
const reader = response.body?.getReader();
|
||||
if (reader) {
|
||||
try {
|
||||
while (true) {
|
||||
const { done, value } = await reader.read();
|
||||
if (done) break;
|
||||
|
||||
const chunk = new TextDecoder().decode(value);
|
||||
const lines = chunk.split('\n');
|
||||
|
||||
for (const line of lines) {
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const parsed = JSON.parse(line);
|
||||
const content = parsed.message?.content;
|
||||
if (content) {
|
||||
controller.enqueue(content);
|
||||
}
|
||||
} catch (e) {
|
||||
console.error('Failed to parse Ollama response:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
reader.releaseLock();
|
||||
}
|
||||
}
|
||||
|
||||
currentMessage = null;
|
||||
}
|
||||
},
|
||||
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
controller.enqueue(message.content || '');
|
||||
} catch (e) {
|
||||
console.error('Failed to parse remaining buffer:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Connect the input to our transform stream
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
// Implementing the synchronous chat interaction
|
||||
public async chat(optionsArg: ChatOptions): Promise<ChatResponse> {
|
||||
// Format messages for Ollama
|
||||
const messages = [
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory,
|
||||
{ role: 'user', content: optionsArg.userMessage }
|
||||
];
|
||||
|
||||
// Make API call to Ollama
|
||||
const response = await fetch(`${this.baseUrl}/api/chat`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.model,
|
||||
messages: messages,
|
||||
stream: false
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Ollama API error: ${response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
|
||||
return {
|
||||
role: 'assistant' as const,
|
||||
message: result.message.content,
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
throw new Error('Audio generation is not supported by Ollama.');
|
||||
}
|
||||
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
const base64Image = optionsArg.image.toString('base64');
|
||||
|
||||
const response = await fetch(`${this.baseUrl}/api/chat`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.visionModel,
|
||||
messages: [{
|
||||
role: 'user',
|
||||
content: optionsArg.prompt,
|
||||
images: [base64Image]
|
||||
}],
|
||||
stream: false
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Ollama API error: ${response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
return result.message.content;
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: ChatMessage[];
|
||||
}): Promise<{ message: any }> {
|
||||
// Convert PDF documents to images using SmartPDF
|
||||
let documentImageBytesArray: Uint8Array[] = [];
|
||||
|
||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
||||
documentImageBytesArray = documentImageBytesArray.concat(documentImageArray);
|
||||
}
|
||||
|
||||
// Convert images to base64
|
||||
const base64Images = documentImageBytesArray.map(bytes => Buffer.from(bytes).toString('base64'));
|
||||
|
||||
// Send request to Ollama with images
|
||||
const response = await fetch(`${this.baseUrl}/api/chat`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.visionModel,
|
||||
messages: [
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory,
|
||||
{
|
||||
role: 'user',
|
||||
content: optionsArg.userMessage,
|
||||
images: base64Images
|
||||
}
|
||||
],
|
||||
stream: false
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Ollama API error: ${response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
return {
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: result.message.content
|
||||
}
|
||||
};
|
||||
}
|
||||
}
|
||||
@@ -1,88 +1,232 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { Readable } from 'stream';
|
||||
|
||||
import { MultiModal } from './abstract.classes.multimodal.js';
|
||||
// Custom type definition for chat completion messages
|
||||
export type TChatCompletionRequestMessage = {
|
||||
role: "system" | "user" | "assistant";
|
||||
content: string;
|
||||
};
|
||||
|
||||
export class OpenAiProvider extends MultiModal {
|
||||
private openAiToken: string;
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
|
||||
export interface IOpenaiProviderOptions {
|
||||
openaiToken: string;
|
||||
chatModel?: string;
|
||||
audioModel?: string;
|
||||
visionModel?: string;
|
||||
// Optionally add more model options (e.g., documentModel) if needed.
|
||||
}
|
||||
|
||||
export class OpenAiProvider extends MultiModalModel {
|
||||
private options: IOpenaiProviderOptions;
|
||||
public openAiApiClient: plugins.openai.default;
|
||||
|
||||
constructor(openaiToken: string) {
|
||||
constructor(optionsArg: IOpenaiProviderOptions) {
|
||||
super();
|
||||
this.openAiToken = openaiToken; // Ensure the token is stored
|
||||
this.options = optionsArg;
|
||||
}
|
||||
|
||||
async start() {
|
||||
public async start() {
|
||||
await super.start();
|
||||
this.openAiApiClient = new plugins.openai.default({
|
||||
apiKey: this.openAiToken,
|
||||
apiKey: this.options.openaiToken,
|
||||
dangerouslyAllowBrowser: true,
|
||||
});
|
||||
}
|
||||
|
||||
async stop() {}
|
||||
|
||||
chatStream(input: ReadableStream<string>): ReadableStream<string> {
|
||||
const decoder = new TextDecoder();
|
||||
let messageHistory: { role: 'assistant' | 'user'; content: string }[] = [];
|
||||
|
||||
return new ReadableStream({
|
||||
async start(controller) {
|
||||
const reader = input.getReader();
|
||||
try {
|
||||
let done, value;
|
||||
while ((({ done, value } = await reader.read()), !done)) {
|
||||
const userMessage = decoder.decode(value, { stream: true });
|
||||
messageHistory.push({ role: 'user', content: userMessage });
|
||||
|
||||
const aiResponse = await this.chat('', userMessage, messageHistory);
|
||||
messageHistory.push({ role: 'assistant', content: aiResponse.message });
|
||||
|
||||
// Directly enqueue the string response instead of encoding it first
|
||||
controller.enqueue(aiResponse.message);
|
||||
public async stop() {
|
||||
await super.stop();
|
||||
}
|
||||
controller.close();
|
||||
} catch (err) {
|
||||
controller.error(err);
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: {
|
||||
role: "function" | "user" | "system" | "assistant" | "tool" | "developer";
|
||||
content: string;
|
||||
} | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
transform: async (chunk, controller) => {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = {
|
||||
role: (message.role || 'user') as "function" | "user" | "system" | "assistant" | "tool" | "developer",
|
||||
content: message.content || '',
|
||||
};
|
||||
} catch (e) {
|
||||
console.error('Failed to parse message:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a complete message, send it to OpenAI
|
||||
if (currentMessage) {
|
||||
const messageToSend = { role: "user" as const, content: currentMessage.content };
|
||||
const chatModel = this.options.chatModel ?? 'o3-mini';
|
||||
const requestParams: any = {
|
||||
model: chatModel,
|
||||
messages: [messageToSend],
|
||||
stream: true,
|
||||
};
|
||||
// Temperature is omitted since the model does not support it.
|
||||
const stream = await this.openAiApiClient.chat.completions.create(requestParams);
|
||||
// Explicitly cast the stream as an async iterable to satisfy TypeScript.
|
||||
const streamAsyncIterable = stream as unknown as AsyncIterableIterator<any>;
|
||||
// Process each chunk from OpenAI
|
||||
for await (const chunk of streamAsyncIterable) {
|
||||
const content = chunk.choices[0]?.delta?.content;
|
||||
if (content) {
|
||||
controller.enqueue(content);
|
||||
}
|
||||
}
|
||||
currentMessage = null;
|
||||
}
|
||||
},
|
||||
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
controller.enqueue(message.content || '');
|
||||
} catch (e) {
|
||||
console.error('Failed to parse remaining buffer:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Connect the input to our transform stream
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
// Implementing the synchronous chat interaction
|
||||
public async chat(
|
||||
systemMessage: string,
|
||||
userMessage: string,
|
||||
public async chat(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
messageHistory: {
|
||||
role: 'assistant' | 'user';
|
||||
content: string;
|
||||
}[]
|
||||
) {
|
||||
const result = await this.openAiApiClient.chat.completions.create({
|
||||
model: 'gpt-3.5-turbo-16k-0613',
|
||||
}[];
|
||||
}) {
|
||||
const chatModel = this.options.chatModel ?? 'o3-mini';
|
||||
const requestParams: any = {
|
||||
model: chatModel,
|
||||
messages: [
|
||||
{ role: 'system', content: systemMessage },
|
||||
...messageHistory,
|
||||
{ role: 'user', content: userMessage },
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory,
|
||||
{ role: 'user', content: optionsArg.userMessage },
|
||||
],
|
||||
};
|
||||
// Temperature parameter removed to avoid unsupported error.
|
||||
const result = await this.openAiApiClient.chat.completions.create(requestParams);
|
||||
return {
|
||||
role: result.choices[0].message.role as 'assistant',
|
||||
message: result.choices[0].message.content,
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
const done = plugins.smartpromise.defer<NodeJS.ReadableStream>();
|
||||
const result = await this.openAiApiClient.audio.speech.create({
|
||||
model: this.options.audioModel ?? 'tts-1-hd',
|
||||
input: optionsArg.message,
|
||||
voice: 'nova',
|
||||
response_format: 'mp3',
|
||||
speed: 1,
|
||||
});
|
||||
const stream = result.body;
|
||||
const nodeStream = Readable.fromWeb(stream as any);
|
||||
done.resolve(nodeStream);
|
||||
return done.promise;
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: {
|
||||
role: 'assistant' | 'user';
|
||||
content: any;
|
||||
}[];
|
||||
}) {
|
||||
let pdfDocumentImageBytesArray: Uint8Array[] = [];
|
||||
|
||||
// Convert each PDF into one or more image byte arrays.
|
||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
||||
pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
|
||||
}
|
||||
|
||||
console.log(`image smartfile array`);
|
||||
console.log(pdfDocumentImageBytesArray.map((smartfile) => smartfile.length));
|
||||
|
||||
// Filter out any empty buffers to avoid sending invalid image URLs.
|
||||
const validImageBytesArray = pdfDocumentImageBytesArray.filter(imageBytes => imageBytes && imageBytes.length > 0);
|
||||
const imageAttachments = validImageBytesArray.map(imageBytes => ({
|
||||
type: 'image_url',
|
||||
image_url: {
|
||||
url: 'data:image/png;base64,' + Buffer.from(imageBytes).toString('base64'),
|
||||
},
|
||||
}));
|
||||
|
||||
const chatModel = this.options.chatModel ?? 'o4-mini';
|
||||
const requestParams: any = {
|
||||
model: chatModel,
|
||||
messages: [
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory,
|
||||
{
|
||||
role: 'user',
|
||||
content: [
|
||||
{ type: 'text', text: optionsArg.userMessage },
|
||||
...imageAttachments,
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
// Temperature parameter removed.
|
||||
const result = await this.openAiApiClient.chat.completions.create(requestParams);
|
||||
return {
|
||||
message: result.choices[0].message,
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(messageArg: string) {
|
||||
const done = plugins.smartpromise.defer();
|
||||
const result = await this.openAiApiClient.audio.speech.create({
|
||||
model: 'tts-1-hd',
|
||||
input: messageArg,
|
||||
voice: 'nova',
|
||||
response_format: 'mp3',
|
||||
speed: 1,
|
||||
});
|
||||
const stream = result.body.pipe(plugins.smartfile.fsStream.createWriteStream(plugins.path.join(paths.nogitDir, 'output.mp3')));
|
||||
stream.on('finish', () => {
|
||||
done.resolve();
|
||||
});
|
||||
return done.promise;
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
const visionModel = this.options.visionModel ?? '04-mini';
|
||||
const requestParams: any = {
|
||||
model: visionModel,
|
||||
messages: [
|
||||
{
|
||||
role: 'user',
|
||||
content: [
|
||||
{ type: 'text', text: optionsArg.prompt },
|
||||
{
|
||||
type: 'image_url',
|
||||
image_url: {
|
||||
url: `data:image/jpeg;base64,${optionsArg.image.toString('base64')}`
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
max_tokens: 300
|
||||
};
|
||||
const result = await this.openAiApiClient.chat.completions.create(requestParams);
|
||||
return result.choices[0].message.content || '';
|
||||
}
|
||||
}
|
||||
171
ts/provider.perplexity.ts
Normal file
171
ts/provider.perplexity.ts
Normal file
@@ -0,0 +1,171 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
|
||||
|
||||
export interface IPerplexityProviderOptions {
|
||||
perplexityToken: string;
|
||||
}
|
||||
|
||||
export class PerplexityProvider extends MultiModalModel {
|
||||
private options: IPerplexityProviderOptions;
|
||||
|
||||
constructor(optionsArg: IPerplexityProviderOptions) {
|
||||
super();
|
||||
this.options = optionsArg;
|
||||
}
|
||||
|
||||
async start() {
|
||||
// Initialize any necessary clients or resources
|
||||
}
|
||||
|
||||
async stop() {}
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: { role: string; content: string; } | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
async transform(chunk, controller) {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = {
|
||||
role: message.role || 'user',
|
||||
content: message.content || '',
|
||||
};
|
||||
} catch (e) {
|
||||
console.error('Failed to parse message:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a complete message, send it to Perplexity
|
||||
if (currentMessage) {
|
||||
const response = await fetch('https://api.perplexity.ai/chat/completions', {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Authorization': `Bearer ${this.options.perplexityToken}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: 'mixtral-8x7b-instruct',
|
||||
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
||||
stream: true,
|
||||
}),
|
||||
});
|
||||
|
||||
// Process each chunk from Perplexity
|
||||
const reader = response.body?.getReader();
|
||||
if (reader) {
|
||||
try {
|
||||
while (true) {
|
||||
const { done, value } = await reader.read();
|
||||
if (done) break;
|
||||
|
||||
const chunk = new TextDecoder().decode(value);
|
||||
const lines = chunk.split('\n');
|
||||
|
||||
for (const line of lines) {
|
||||
if (line.startsWith('data: ')) {
|
||||
const data = line.slice(6);
|
||||
if (data === '[DONE]') break;
|
||||
|
||||
try {
|
||||
const parsed = JSON.parse(data);
|
||||
const content = parsed.choices[0]?.delta?.content;
|
||||
if (content) {
|
||||
controller.enqueue(content);
|
||||
}
|
||||
} catch (e) {
|
||||
console.error('Failed to parse SSE data:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
reader.releaseLock();
|
||||
}
|
||||
}
|
||||
|
||||
currentMessage = null;
|
||||
}
|
||||
},
|
||||
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
controller.enqueue(message.content || '');
|
||||
} catch (e) {
|
||||
console.error('Failed to parse remaining buffer:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Connect the input to our transform stream
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
// Implementing the synchronous chat interaction
|
||||
public async chat(optionsArg: ChatOptions): Promise<ChatResponse> {
|
||||
// Make API call to Perplexity
|
||||
const response = await fetch('https://api.perplexity.ai/chat/completions', {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Authorization': `Bearer ${this.options.perplexityToken}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: 'mixtral-8x7b-instruct', // Using Mixtral model
|
||||
messages: [
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory,
|
||||
{ role: 'user', content: optionsArg.userMessage }
|
||||
],
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Perplexity API error: ${response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
|
||||
return {
|
||||
role: 'assistant' as const,
|
||||
message: result.choices[0].message.content,
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
throw new Error('Audio generation is not supported by Perplexity.');
|
||||
}
|
||||
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
throw new Error('Vision tasks are not supported by Perplexity.');
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: ChatMessage[];
|
||||
}): Promise<{ message: any }> {
|
||||
throw new Error('Document processing is not supported by Perplexity.');
|
||||
}
|
||||
}
|
||||
184
ts/provider.xai.ts
Normal file
184
ts/provider.xai.ts
Normal file
@@ -0,0 +1,184 @@
|
||||
import * as plugins from './plugins.js';
|
||||
import * as paths from './paths.js';
|
||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||
import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
|
||||
import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
|
||||
|
||||
export interface IXAIProviderOptions {
|
||||
xaiToken: string;
|
||||
}
|
||||
|
||||
export class XAIProvider extends MultiModalModel {
|
||||
private options: IXAIProviderOptions;
|
||||
public openAiApiClient: plugins.openai.default;
|
||||
|
||||
constructor(optionsArg: IXAIProviderOptions) {
|
||||
super();
|
||||
this.options = optionsArg;
|
||||
}
|
||||
|
||||
public async start() {
|
||||
await super.start();
|
||||
this.openAiApiClient = new plugins.openai.default({
|
||||
apiKey: this.options.xaiToken,
|
||||
baseURL: 'https://api.x.ai/v1',
|
||||
});
|
||||
}
|
||||
|
||||
public async stop() {
|
||||
await super.stop();
|
||||
}
|
||||
|
||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||
// Create a TextDecoder to handle incoming chunks
|
||||
const decoder = new TextDecoder();
|
||||
let buffer = '';
|
||||
let currentMessage: { role: string; content: string; } | null = null;
|
||||
|
||||
// Create a TransformStream to process the input
|
||||
const transform = new TransformStream<Uint8Array, string>({
|
||||
async transform(chunk, controller) {
|
||||
buffer += decoder.decode(chunk, { stream: true });
|
||||
|
||||
// Try to parse complete JSON messages from the buffer
|
||||
while (true) {
|
||||
const newlineIndex = buffer.indexOf('\n');
|
||||
if (newlineIndex === -1) break;
|
||||
|
||||
const line = buffer.slice(0, newlineIndex);
|
||||
buffer = buffer.slice(newlineIndex + 1);
|
||||
|
||||
if (line.trim()) {
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
currentMessage = {
|
||||
role: message.role || 'user',
|
||||
content: message.content || '',
|
||||
};
|
||||
} catch (e) {
|
||||
console.error('Failed to parse message:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a complete message, send it to X.AI
|
||||
if (currentMessage) {
|
||||
const stream = await this.openAiApiClient.chat.completions.create({
|
||||
model: 'grok-2-latest',
|
||||
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
||||
stream: true,
|
||||
});
|
||||
|
||||
// Process each chunk from X.AI
|
||||
for await (const chunk of stream) {
|
||||
const content = chunk.choices[0]?.delta?.content;
|
||||
if (content) {
|
||||
controller.enqueue(content);
|
||||
}
|
||||
}
|
||||
|
||||
currentMessage = null;
|
||||
}
|
||||
},
|
||||
|
||||
flush(controller) {
|
||||
if (buffer) {
|
||||
try {
|
||||
const message = JSON.parse(buffer);
|
||||
controller.enqueue(message.content || '');
|
||||
} catch (e) {
|
||||
console.error('Failed to parse remaining buffer:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Connect the input to our transform stream
|
||||
return input.pipeThrough(transform);
|
||||
}
|
||||
|
||||
public async chat(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
messageHistory: { role: string; content: string; }[];
|
||||
}): Promise<{ role: 'assistant'; message: string; }> {
|
||||
// Prepare messages array with system message, history, and user message
|
||||
const messages: ChatCompletionMessageParam[] = [
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory.map(msg => ({
|
||||
role: msg.role as 'system' | 'user' | 'assistant',
|
||||
content: msg.content
|
||||
})),
|
||||
{ role: 'user', content: optionsArg.userMessage }
|
||||
];
|
||||
|
||||
// Call X.AI's chat completion API
|
||||
const completion = await this.openAiApiClient.chat.completions.create({
|
||||
model: 'grok-2-latest',
|
||||
messages: messages,
|
||||
stream: false,
|
||||
});
|
||||
|
||||
// Return the assistant's response
|
||||
return {
|
||||
role: 'assistant',
|
||||
message: completion.choices[0]?.message?.content || ''
|
||||
};
|
||||
}
|
||||
|
||||
public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
|
||||
throw new Error('Audio generation is not supported by X.AI');
|
||||
}
|
||||
|
||||
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||
throw new Error('Vision tasks are not supported by X.AI');
|
||||
}
|
||||
|
||||
public async document(optionsArg: {
|
||||
systemMessage: string;
|
||||
userMessage: string;
|
||||
pdfDocuments: Uint8Array[];
|
||||
messageHistory: { role: string; content: string; }[];
|
||||
}): Promise<{ message: any }> {
|
||||
// First convert PDF documents to images
|
||||
let pdfDocumentImageBytesArray: Uint8Array[] = [];
|
||||
|
||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
||||
pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
|
||||
}
|
||||
|
||||
// Convert images to base64 for inclusion in the message
|
||||
const imageBase64Array = pdfDocumentImageBytesArray.map(bytes =>
|
||||
Buffer.from(bytes).toString('base64')
|
||||
);
|
||||
|
||||
// Combine document images into the user message
|
||||
const enhancedUserMessage = `
|
||||
${optionsArg.userMessage}
|
||||
|
||||
Document contents (as images):
|
||||
${imageBase64Array.map((img, i) => `Image ${i + 1}: <image data>`).join('\n')}
|
||||
`;
|
||||
|
||||
// Use chat completion to analyze the documents
|
||||
const messages: ChatCompletionMessageParam[] = [
|
||||
{ role: 'system', content: optionsArg.systemMessage },
|
||||
...optionsArg.messageHistory.map(msg => ({
|
||||
role: msg.role as 'system' | 'user' | 'assistant',
|
||||
content: msg.content
|
||||
})),
|
||||
{ role: 'user', content: enhancedUserMessage }
|
||||
];
|
||||
|
||||
const completion = await this.openAiApiClient.chat.completions.create({
|
||||
model: 'grok-2-latest',
|
||||
messages: messages,
|
||||
stream: false,
|
||||
});
|
||||
|
||||
return {
|
||||
message: completion.choices[0]?.message?.content || ''
|
||||
};
|
||||
}
|
||||
}
|
||||
@@ -1,53 +0,0 @@
|
||||
type TProcessFunction = (input: string) => Promise<string>;
|
||||
|
||||
interface ISmartAiOptions {
|
||||
processFunction: TProcessFunction;
|
||||
}
|
||||
|
||||
class SmartAi {
|
||||
private processFunction: TProcessFunction;
|
||||
private inputStreamWriter: WritableStreamDefaultWriter<string> | null = null;
|
||||
private outputStreamController: ReadableStreamDefaultController<string> | null = null;
|
||||
|
||||
constructor(options: ISmartAiOptions) {
|
||||
this.processFunction = options.processFunction;
|
||||
}
|
||||
|
||||
private setupOutputStream(): ReadableStream<string> {
|
||||
return new ReadableStream<string>({
|
||||
start: (controller) => {
|
||||
this.outputStreamController = controller;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
private setupInputStream(): WritableStream<string> {
|
||||
return new WritableStream<string>({
|
||||
write: async (chunk) => {
|
||||
const processedData = await this.processFunction(chunk);
|
||||
if (this.outputStreamController) {
|
||||
this.outputStreamController.enqueue(processedData);
|
||||
}
|
||||
},
|
||||
close: () => {
|
||||
this.outputStreamController?.close();
|
||||
},
|
||||
abort: (err) => {
|
||||
console.error('Stream aborted', err);
|
||||
this.outputStreamController?.error(err);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
public getInputStreamWriter(): WritableStreamDefaultWriter<string> {
|
||||
if (!this.inputStreamWriter) {
|
||||
const inputStream = this.setupInputStream();
|
||||
this.inputStreamWriter = inputStream.getWriter();
|
||||
}
|
||||
return this.inputStreamWriter;
|
||||
}
|
||||
|
||||
public getOutputStream(): ReadableStream<string> {
|
||||
return this.setupOutputStream();
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user