Compare commits
20 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| e8a2a3ff1b | |||
| cbc9d8d45b | |||
| d52e6ae67d | |||
| b9745a1869 | |||
| af3b61cf74 | |||
| 8666876879 | |||
| b78168307b | |||
| bbd8770205 | |||
| 28bb13dc0c | |||
| 3a24c2c4bd | |||
| 8244ac6eb0 | |||
| 2791d738d6 | |||
| 3fbd054985 | |||
| 8e8830ef92 | |||
| 34931875ad | |||
| 2672509d3f | |||
| ee3a635852 | |||
| a222b1c2fa | |||
| f0556e89f3 | |||
| fe8540c8ba |
1
.serena/.gitignore
vendored
Normal file
1
.serena/.gitignore
vendored
Normal file
@@ -0,0 +1 @@
|
|||||||
|
/cache
|
||||||
67
.serena/project.yml
Normal file
67
.serena/project.yml
Normal file
@@ -0,0 +1,67 @@
|
|||||||
|
# language of the project (csharp, python, rust, java, typescript, go, cpp, or ruby)
|
||||||
|
# * For C, use cpp
|
||||||
|
# * For JavaScript, use typescript
|
||||||
|
# Special requirements:
|
||||||
|
# * csharp: Requires the presence of a .sln file in the project folder.
|
||||||
|
language: typescript
|
||||||
|
|
||||||
|
# whether to use the project's gitignore file to ignore files
|
||||||
|
# Added on 2025-04-07
|
||||||
|
ignore_all_files_in_gitignore: true
|
||||||
|
# list of additional paths to ignore
|
||||||
|
# same syntax as gitignore, so you can use * and **
|
||||||
|
# Was previously called `ignored_dirs`, please update your config if you are using that.
|
||||||
|
# Added (renamed) on 2025-04-07
|
||||||
|
ignored_paths: []
|
||||||
|
|
||||||
|
# whether the project is in read-only mode
|
||||||
|
# If set to true, all editing tools will be disabled and attempts to use them will result in an error
|
||||||
|
# Added on 2025-04-18
|
||||||
|
read_only: false
|
||||||
|
|
||||||
|
# list of tool names to exclude. We recommend not excluding any tools, see the readme for more details.
|
||||||
|
# Below is the complete list of tools for convenience.
|
||||||
|
# To make sure you have the latest list of tools, and to view their descriptions,
|
||||||
|
# execute `uv run scripts/print_tool_overview.py`.
|
||||||
|
#
|
||||||
|
# * `activate_project`: Activates a project by name.
|
||||||
|
# * `check_onboarding_performed`: Checks whether project onboarding was already performed.
|
||||||
|
# * `create_text_file`: Creates/overwrites a file in the project directory.
|
||||||
|
# * `delete_lines`: Deletes a range of lines within a file.
|
||||||
|
# * `delete_memory`: Deletes a memory from Serena's project-specific memory store.
|
||||||
|
# * `execute_shell_command`: Executes a shell command.
|
||||||
|
# * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced.
|
||||||
|
# * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type).
|
||||||
|
# * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type).
|
||||||
|
# * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
|
||||||
|
# * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
|
||||||
|
# * `initial_instructions`: Gets the initial instructions for the current project.
|
||||||
|
# Should only be used in settings where the system prompt cannot be set,
|
||||||
|
# e.g. in clients you have no control over, like Claude Desktop.
|
||||||
|
# * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
|
||||||
|
# * `insert_at_line`: Inserts content at a given line in a file.
|
||||||
|
# * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
|
||||||
|
# * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
|
||||||
|
# * `list_memories`: Lists memories in Serena's project-specific memory store.
|
||||||
|
# * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
|
||||||
|
# * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context).
|
||||||
|
# * `read_file`: Reads a file within the project directory.
|
||||||
|
# * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store.
|
||||||
|
# * `remove_project`: Removes a project from the Serena configuration.
|
||||||
|
# * `replace_lines`: Replaces a range of lines within a file with new content.
|
||||||
|
# * `replace_symbol_body`: Replaces the full definition of a symbol.
|
||||||
|
# * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen.
|
||||||
|
# * `search_for_pattern`: Performs a search for a pattern in the project.
|
||||||
|
# * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase.
|
||||||
|
# * `switch_modes`: Activates modes by providing a list of their names
|
||||||
|
# * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information.
|
||||||
|
# * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task.
|
||||||
|
# * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed.
|
||||||
|
# * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store.
|
||||||
|
excluded_tools: []
|
||||||
|
|
||||||
|
# initial prompt for the project. It will always be given to the LLM upon activating the project
|
||||||
|
# (contrary to the memories, which are loaded on demand).
|
||||||
|
initial_prompt: ""
|
||||||
|
|
||||||
|
project_name: "smartai"
|
||||||
74
changelog.md
74
changelog.md
@@ -1,5 +1,79 @@
|
|||||||
# Changelog
|
# Changelog
|
||||||
|
|
||||||
|
## 2025-10-30 - 0.8.0 - feat(provider.anthropic)
|
||||||
|
Add extended thinking modes to AnthropicProvider and apply thinking budgets to API calls
|
||||||
|
|
||||||
|
- Introduce IAnthropicProviderOptions.extendedThinking to configure thinking modes: 'quick' | 'normal' | 'deep' | 'off'.
|
||||||
|
- Add getThinkingConfig() helper mapping modes to token budgets (quick=2048, normal=8000, deep=16000, off=0).
|
||||||
|
- Apply thinking configuration to Anthropic API calls (chat, chatStream, vision, document, research) and increase max_tokens where appropriate (up to 20000).
|
||||||
|
- Add comprehensive tests (test/test.thinking.anthropic.ts) and update readme.hints.md with usage examples and recommendations.
|
||||||
|
- Add .claude/settings.local.json for local assistant permissions used in development/testing.
|
||||||
|
|
||||||
|
## 2025-10-10 - 0.7.7 - fix(MultiModalModel)
|
||||||
|
Lazy-load SmartPdf and guard document processing across providers; ensure SmartPdf is initialized only when needed
|
||||||
|
|
||||||
|
- Make SmartPdf lazy-loaded: smartpdfInstance is now nullable and no longer started automatically in start()
|
||||||
|
- Add ensureSmartpdfReady() to initialize and start SmartPdf on demand before document processing
|
||||||
|
- Providers updated (OpenAI, Anthropic, Ollama, xAI) to call ensureSmartpdfReady() and use the smartpdfInstance for PDF -> image conversion
|
||||||
|
- stop() now cleans up and nullifies smartpdfInstance to release resources
|
||||||
|
- Avoids starting a browser/process unless document() is actually used (reduces unnecessary resource usage)
|
||||||
|
- Add local Claude permissions file (.claude/settings.local.json) for tooling/configuration
|
||||||
|
|
||||||
|
## 2025-10-09 - 0.7.6 - fix(provider.elevenlabs)
|
||||||
|
Provide default ElevenLabs TTS voice fallback and add local tool/project configs
|
||||||
|
|
||||||
|
- ElevenLabsProvider: fallback to Samara voice id ('19STyYD15bswVz51nqLf') when no voiceId or defaultVoiceId is provided — avoids throwing an error on TTS calls.
|
||||||
|
- ElevenLabsProvider: continue to use 'eleven_v3' as the default model for TTS.
|
||||||
|
- Add .claude/settings.local.json with expanded allowed permissions for local tooling and web search.
|
||||||
|
- Add .serena/project.yml and .serena/.gitignore to include Serena project configuration and ignore cache.
|
||||||
|
|
||||||
|
## 2025-10-08 - 0.7.5 - fix(provider.elevenlabs)
|
||||||
|
Update ElevenLabs default TTS model to eleven_v3 and add local Claude permissions file
|
||||||
|
|
||||||
|
- Changed default ElevenLabs modelId from 'eleven_multilingual_v2' to 'eleven_v3' in ts/provider.elevenlabs.ts to use the newer/default TTS model.
|
||||||
|
- Added .claude/settings.local.json with a permissions allow-list for local Claude tooling and CI tasks.
|
||||||
|
|
||||||
|
## 2025-10-03 - 0.7.4 - fix(provider.anthropic)
|
||||||
|
Use image/png for embedded PDF images in Anthropic provider and add local Claude settings for development permissions
|
||||||
|
|
||||||
|
- AnthropicProvider: change media_type from 'image/jpeg' to 'image/png' when embedding images extracted from PDFs to ensure correct format in Anthropic requests.
|
||||||
|
- Add .claude/settings.local.json with development/testing permissions for local Claude usage (shell commands, webfetch, websearch, test/run tasks).
|
||||||
|
|
||||||
|
## 2025-10-03 - 0.7.3 - fix(tests)
|
||||||
|
Add extensive provider/feature tests and local Claude CI permissions
|
||||||
|
|
||||||
|
- Add many focused test files covering providers and features: OpenAI, Anthropic, Perplexity, Groq, Ollama, Exo, XAI (chat, audio, vision, document, research, image generation, stubs, interfaces, basic)
|
||||||
|
- Introduce .claude/settings.local.json to declare allowed permissions for local Claude/CI actions
|
||||||
|
- Replace older aggregated test files with modular per-feature tests (removed legacy combined tests and split into smaller suites)
|
||||||
|
- No changes to library runtime code — this change adds tests and CI/local agent configuration only
|
||||||
|
|
||||||
|
## 2025-10-03 - 0.7.2 - fix(anthropic)
|
||||||
|
Update Anthropic provider branding to Claude Sonnet 4.5 and add local Claude permissions
|
||||||
|
|
||||||
|
- Docs: Replace 'Claude 3 Opus' with 'Claude Sonnet 4.5' in README provider capabilities matrix.
|
||||||
|
- Config: Add .claude/settings.local.json to define local Claude permissions for tests and development commands.
|
||||||
|
|
||||||
|
## 2025-10-03 - 0.7.1 - fix(docs)
|
||||||
|
Add README image generation docs and .claude local settings
|
||||||
|
|
||||||
|
- Add .claude/settings.local.json with permission allow-list for local assistant tooling and web search
|
||||||
|
- Update README provider capabilities table to include an Images column and reference gpt-image-1
|
||||||
|
- Add Image Generation & Editing section with examples, options, and gpt-image-1 advantages
|
||||||
|
- Mark image generation support as implemented in the roadmap and remove duplicate entry
|
||||||
|
|
||||||
|
## 2025-10-03 - 0.7.0 - feat(providers)
|
||||||
|
Add research API and image generation/editing support; extend providers and tests
|
||||||
|
|
||||||
|
- Introduce ResearchOptions and ResearchResponse to the MultiModalModel interface and implement research() where supported
|
||||||
|
- OpenAiProvider: implement research(), add imageGenerate() and imageEdit() methods (gpt-image-1 / DALL·E support), and expose imageModel option
|
||||||
|
- AnthropicProvider: implement research() and vision handling; explicitly throw for unsupported image generation/editing
|
||||||
|
- PerplexityProvider: implement research() (sonar / sonar-pro support) and expose citation parsing
|
||||||
|
- Add image/document-related interfaces (ImageGenerateOptions, ImageEditOptions, ImageResponse) to abstract API
|
||||||
|
- Add image generation/editing/no-op stubs for other providers (Exo, Groq, Ollama, XAI) that throw informative errors to preserve API compatibility
|
||||||
|
- Add comprehensive OpenAI image generation tests and helper to save test outputs (test/test.image.openai.ts)
|
||||||
|
- Update README with Research & Web Search documentation, capability matrix, and roadmap entry for Research & Web Search API
|
||||||
|
- Add local Claude agent permissions file (.claude/settings.local.json) and various provider type/import updates
|
||||||
|
|
||||||
## 2025-09-28 - 0.6.1 - fix(provider.anthropic)
|
## 2025-09-28 - 0.6.1 - fix(provider.anthropic)
|
||||||
Fix Anthropic research tool identifier and add tests + local Claude permissions
|
Fix Anthropic research tool identifier and add tests + local Claude permissions
|
||||||
|
|
||||||
|
|||||||
17
package.json
17
package.json
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "@push.rocks/smartai",
|
"name": "@push.rocks/smartai",
|
||||||
"version": "0.6.1",
|
"version": "0.8.0",
|
||||||
"private": false,
|
"private": false,
|
||||||
"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.",
|
"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",
|
"main": "dist_ts/index.js",
|
||||||
@@ -15,22 +15,23 @@
|
|||||||
"buildDocs": "(tsdoc)"
|
"buildDocs": "(tsdoc)"
|
||||||
},
|
},
|
||||||
"devDependencies": {
|
"devDependencies": {
|
||||||
"@git.zone/tsbuild": "^2.6.4",
|
"@git.zone/tsbuild": "^2.6.8",
|
||||||
"@git.zone/tsbundle": "^2.5.1",
|
"@git.zone/tsbundle": "^2.5.1",
|
||||||
"@git.zone/tsrun": "^1.3.3",
|
"@git.zone/tsrun": "^1.3.3",
|
||||||
"@git.zone/tstest": "^2.3.2",
|
"@git.zone/tstest": "^2.3.8",
|
||||||
"@push.rocks/qenv": "^6.1.0",
|
"@push.rocks/qenv": "^6.1.3",
|
||||||
"@push.rocks/tapbundle": "^6.0.3",
|
"@push.rocks/tapbundle": "^6.0.3",
|
||||||
"@types/node": "^22.15.17"
|
"@types/node": "^22.15.17",
|
||||||
|
"typescript": "^5.9.3"
|
||||||
},
|
},
|
||||||
"dependencies": {
|
"dependencies": {
|
||||||
"@anthropic-ai/sdk": "^0.59.0",
|
"@anthropic-ai/sdk": "^0.65.0",
|
||||||
"@push.rocks/smartarray": "^1.1.0",
|
"@push.rocks/smartarray": "^1.1.0",
|
||||||
"@push.rocks/smartfile": "^11.2.5",
|
"@push.rocks/smartfile": "^11.2.7",
|
||||||
"@push.rocks/smartpath": "^6.0.0",
|
"@push.rocks/smartpath": "^6.0.0",
|
||||||
"@push.rocks/smartpdf": "^4.1.1",
|
"@push.rocks/smartpdf": "^4.1.1",
|
||||||
"@push.rocks/smartpromise": "^4.2.3",
|
"@push.rocks/smartpromise": "^4.2.3",
|
||||||
"@push.rocks/smartrequest": "^4.2.1",
|
"@push.rocks/smartrequest": "^4.3.1",
|
||||||
"@push.rocks/webstream": "^1.0.10",
|
"@push.rocks/webstream": "^1.0.10",
|
||||||
"openai": "^5.12.2"
|
"openai": "^5.12.2"
|
||||||
},
|
},
|
||||||
|
|||||||
2602
pnpm-lock.yaml
generated
2602
pnpm-lock.yaml
generated
File diff suppressed because it is too large
Load Diff
184
readme.hints.md
184
readme.hints.md
@@ -1 +1,183 @@
|
|||||||
|
# SmartAI Project Hints
|
||||||
|
|
||||||
|
## Anthropic Extended Thinking Feature
|
||||||
|
|
||||||
|
### Overview
|
||||||
|
The Anthropic provider now supports extended thinking by default across all methods. Extended thinking enables Claude to spend more time reasoning about complex problems before generating responses, leading to higher quality answers for difficult questions.
|
||||||
|
|
||||||
|
### Configuration
|
||||||
|
|
||||||
|
Extended thinking is configured at the provider level during instantiation:
|
||||||
|
|
||||||
|
```typescript
|
||||||
|
import * as smartai from '@push.rocks/smartai';
|
||||||
|
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: 'your-token-here',
|
||||||
|
extendedThinking: 'normal', // Options: 'quick' | 'normal' | 'deep' | 'off'
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
### Thinking Modes
|
||||||
|
|
||||||
|
The `extendedThinking` parameter accepts four modes:
|
||||||
|
|
||||||
|
| Mode | Budget Tokens | Use Case |
|
||||||
|
|------|---------------|----------|
|
||||||
|
| `'quick'` | 2,048 | Lightweight reasoning for simple queries |
|
||||||
|
| `'normal'` | 8,000 | **Default** - Balanced reasoning for most tasks |
|
||||||
|
| `'deep'` | 16,000 | Complex reasoning for difficult problems |
|
||||||
|
| `'off'` | 0 | Disable extended thinking |
|
||||||
|
|
||||||
|
**Default Behavior**: If `extendedThinking` is not specified, it defaults to `'normal'` mode (8,000 tokens).
|
||||||
|
|
||||||
|
### Supported Methods
|
||||||
|
|
||||||
|
Extended thinking is automatically applied to all Anthropic provider methods:
|
||||||
|
- `chat()` - Synchronous chat
|
||||||
|
- `chatStream()` - Streaming chat
|
||||||
|
- `vision()` - Image analysis
|
||||||
|
- `document()` - PDF document processing
|
||||||
|
- `research()` - Web research with citations
|
||||||
|
|
||||||
|
### Token Budget Constraints
|
||||||
|
|
||||||
|
**Important**: The thinking budget must be less than `max_tokens` for the API call. The current `max_tokens` values are:
|
||||||
|
|
||||||
|
- `chatStream()`: 20,000 tokens (sufficient for all modes ✓)
|
||||||
|
- `chat()`: 20,000 tokens (sufficient for all modes ✓)
|
||||||
|
- `vision()`: 10,000 tokens (sufficient for all modes ✓)
|
||||||
|
- `document()`: 20,000 tokens (sufficient for all modes ✓)
|
||||||
|
- `research()`: 20,000 tokens for all searchDepth levels (sufficient ✓)
|
||||||
|
|
||||||
|
### Performance and Cost Implications
|
||||||
|
|
||||||
|
**Token Usage**:
|
||||||
|
- You are charged for the **full thinking tokens** generated, not just the summary
|
||||||
|
- Higher thinking budgets may result in more thorough reasoning but increased costs
|
||||||
|
- The budget is a **target**, not a strict limit - actual usage may vary
|
||||||
|
|
||||||
|
**Response Quality**:
|
||||||
|
- `'quick'`: Fast responses, basic reasoning
|
||||||
|
- `'normal'`: Good balance between quality and speed (recommended for most use cases)
|
||||||
|
- `'deep'`: Highest quality reasoning for complex problems, slower responses
|
||||||
|
|
||||||
|
**Recommendations**:
|
||||||
|
- Start with `'normal'` (default) for general usage
|
||||||
|
- Use `'deep'` for complex analytical tasks, philosophy, mathematics, or research
|
||||||
|
- Use `'quick'` for simple factual queries where deep reasoning isn't needed
|
||||||
|
- Use `'off'` only if you want traditional Claude behavior without extended thinking
|
||||||
|
|
||||||
|
### Usage Examples
|
||||||
|
|
||||||
|
#### Example 1: Default (Normal Mode)
|
||||||
|
```typescript
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: process.env.ANTHROPIC_TOKEN,
|
||||||
|
// extendedThinking defaults to 'normal'
|
||||||
|
});
|
||||||
|
|
||||||
|
await provider.start();
|
||||||
|
|
||||||
|
const response = await provider.chat({
|
||||||
|
systemMessage: 'You are a helpful assistant.',
|
||||||
|
userMessage: 'Explain the implications of quantum computing.',
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
#### Example 2: Deep Thinking for Complex Analysis
|
||||||
|
```typescript
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: process.env.ANTHROPIC_TOKEN,
|
||||||
|
extendedThinking: 'deep', // 16,000 token budget
|
||||||
|
});
|
||||||
|
|
||||||
|
await provider.start();
|
||||||
|
|
||||||
|
const response = await provider.chat({
|
||||||
|
systemMessage: 'You are a philosopher and ethicist.',
|
||||||
|
userMessage: 'Analyze the trolley problem from multiple ethical frameworks.',
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
#### Example 3: Quick Mode for Simple Queries
|
||||||
|
```typescript
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: process.env.ANTHROPIC_TOKEN,
|
||||||
|
extendedThinking: 'quick', // 2,048 token budget
|
||||||
|
});
|
||||||
|
|
||||||
|
await provider.start();
|
||||||
|
|
||||||
|
const response = await provider.chat({
|
||||||
|
systemMessage: 'You are a helpful assistant.',
|
||||||
|
userMessage: 'What is the capital of France?',
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
#### Example 4: Disable Thinking
|
||||||
|
```typescript
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: process.env.ANTHROPIC_TOKEN,
|
||||||
|
extendedThinking: 'off', // No extended thinking
|
||||||
|
});
|
||||||
|
|
||||||
|
await provider.start();
|
||||||
|
|
||||||
|
const response = await provider.chat({
|
||||||
|
systemMessage: 'You are a helpful assistant.',
|
||||||
|
userMessage: 'Tell me a joke.',
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
#### Example 5: Extended Thinking with Vision
|
||||||
|
```typescript
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: process.env.ANTHROPIC_TOKEN,
|
||||||
|
extendedThinking: 'normal',
|
||||||
|
});
|
||||||
|
|
||||||
|
await provider.start();
|
||||||
|
|
||||||
|
const imageBuffer = await fs.promises.readFile('./image.jpg');
|
||||||
|
const analysis = await provider.vision({
|
||||||
|
image: imageBuffer,
|
||||||
|
prompt: 'Analyze this image in detail and explain what you see.',
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
### Testing
|
||||||
|
|
||||||
|
Comprehensive tests for extended thinking are available in:
|
||||||
|
- `test/test.thinking.anthropic.ts` - Tests all thinking modes
|
||||||
|
|
||||||
|
Run tests with:
|
||||||
|
```bash
|
||||||
|
pnpm test
|
||||||
|
```
|
||||||
|
|
||||||
|
Run specific thinking tests:
|
||||||
|
```bash
|
||||||
|
npx tstest test/test.thinking.anthropic.ts --verbose
|
||||||
|
```
|
||||||
|
|
||||||
|
### API Reference
|
||||||
|
|
||||||
|
According to Anthropic's documentation:
|
||||||
|
- Extended thinking is supported on Claude Sonnet 4.5, 4, 3.7, Haiku 4.5, and Opus 4.1, 4
|
||||||
|
- The current model used is `claude-sonnet-4-5-20250929`
|
||||||
|
- Minimum thinking budget is 1,024 tokens
|
||||||
|
- Thinking budget must be less than `max_tokens`
|
||||||
|
|
||||||
|
### Implementation Details
|
||||||
|
|
||||||
|
The extended thinking feature is implemented via:
|
||||||
|
1. **Interface**: `IAnthropicProviderOptions.extendedThinking` property
|
||||||
|
2. **Helper Method**: `getThinkingConfig()` private method that maps modes to token budgets
|
||||||
|
3. **API Parameter**: Adds `thinking: { type: 'enabled', budget_tokens: number }` to all API calls
|
||||||
|
|
||||||
|
The thinking configuration is applied automatically to all API calls when the provider is instantiated.
|
||||||
|
|||||||
175
readme.md
175
readme.md
@@ -5,7 +5,7 @@
|
|||||||
[](https://www.typescriptlang.org/)
|
[](https://www.typescriptlang.org/)
|
||||||
[](https://opensource.org/licenses/MIT)
|
[](https://opensource.org/licenses/MIT)
|
||||||
|
|
||||||
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.
|
SmartAI unifies the world's leading AI providers - OpenAI, Anthropic, Perplexity, Ollama, Groq, XAI, Exo, and ElevenLabs - under a single, elegant TypeScript interface. Build AI applications at lightning speed without vendor lock-in.
|
||||||
|
|
||||||
## 🎯 Why SmartAI?
|
## 🎯 Why SmartAI?
|
||||||
|
|
||||||
@@ -28,7 +28,11 @@ import { SmartAi } from '@push.rocks/smartai';
|
|||||||
// Initialize with your favorite providers
|
// Initialize with your favorite providers
|
||||||
const ai = new SmartAi({
|
const ai = new SmartAi({
|
||||||
openaiToken: 'sk-...',
|
openaiToken: 'sk-...',
|
||||||
anthropicToken: 'sk-ant-...'
|
anthropicToken: 'sk-ant-...',
|
||||||
|
elevenlabsToken: 'sk-...',
|
||||||
|
elevenlabs: {
|
||||||
|
defaultVoiceId: '19STyYD15bswVz51nqLf' // Optional: Samara voice
|
||||||
|
}
|
||||||
});
|
});
|
||||||
|
|
||||||
await ai.start();
|
await ai.start();
|
||||||
@@ -45,15 +49,16 @@ const response = await ai.openaiProvider.chat({
|
|||||||
|
|
||||||
Choose the right provider for your use case:
|
Choose the right provider for your use case:
|
||||||
|
|
||||||
| Provider | Chat | Streaming | TTS | Vision | Documents | Highlights |
|
| Provider | Chat | Streaming | TTS | Vision | Documents | Research | Images | Highlights |
|
||||||
|----------|:----:|:---------:|:---:|:------:|:---------:|------------|
|
|----------|:----:|:---------:|:---:|:------:|:---------:|:--------:|:------:|------------|
|
||||||
| **OpenAI** | ✅ | ✅ | ✅ | ✅ | ✅ | • GPT-4, DALL-E 3<br>• Industry standard<br>• Most features |
|
| **OpenAI** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | • gpt-image-1<br>• DALL-E 3<br>• Deep research API |
|
||||||
| **Anthropic** | ✅ | ✅ | ❌ | ✅ | ✅ | • Claude 3 Opus<br>• Superior reasoning<br>• 200k context |
|
| **Anthropic** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | • Claude Sonnet 4.5<br>• Superior reasoning<br>• Web search API |
|
||||||
| **Ollama** | ✅ | ✅ | ❌ | ✅ | ✅ | • 100% local<br>• Privacy-first<br>• No API costs |
|
| **ElevenLabs** | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | • Premium TTS<br>• 70+ languages<br>• Natural voices |
|
||||||
| **XAI** | ✅ | ✅ | ❌ | ❌ | ✅ | • Grok models<br>• Real-time data<br>• Uncensored |
|
| **Ollama** | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | • 100% local<br>• Privacy-first<br>• No API costs |
|
||||||
| **Perplexity** | ✅ | ✅ | ❌ | ❌ | ❌ | • Web-aware<br>• Research-focused<br>• Citations |
|
| **XAI** | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | • Grok models<br>• Real-time data<br>• Uncensored |
|
||||||
| **Groq** | ✅ | ✅ | ❌ | ❌ | ❌ | • 10x faster<br>• LPU inference<br>• Low latency |
|
| **Perplexity** | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | • Web-aware<br>• Research-focused<br>• Sonar Pro models |
|
||||||
| **Exo** | ✅ | ✅ | ❌ | ❌ | ❌ | • Distributed<br>• P2P compute<br>• Decentralized |
|
| **Groq** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | • 10x faster<br>• LPU inference<br>• Low latency |
|
||||||
|
| **Exo** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | • Distributed<br>• P2P compute<br>• Decentralized |
|
||||||
|
|
||||||
## 🎮 Core Features
|
## 🎮 Core Features
|
||||||
|
|
||||||
@@ -105,13 +110,27 @@ while (true) {
|
|||||||
|
|
||||||
### 🎙️ Text-to-Speech
|
### 🎙️ Text-to-Speech
|
||||||
|
|
||||||
Generate natural voices with OpenAI:
|
Generate natural voices with OpenAI or ElevenLabs:
|
||||||
|
|
||||||
```typescript
|
```typescript
|
||||||
|
// OpenAI TTS
|
||||||
const audioStream = await ai.openaiProvider.audio({
|
const audioStream = await ai.openaiProvider.audio({
|
||||||
message: 'Welcome to the future of AI development!'
|
message: 'Welcome to the future of AI development!'
|
||||||
});
|
});
|
||||||
|
|
||||||
|
// ElevenLabs TTS - Premium quality, natural voices (uses v3 by default)
|
||||||
|
const elevenLabsAudio = await ai.elevenlabsProvider.audio({
|
||||||
|
message: 'Experience the most lifelike text to speech technology.',
|
||||||
|
voiceId: '19STyYD15bswVz51nqLf', // Optional: Samara voice
|
||||||
|
modelId: 'eleven_v3', // Optional: defaults to eleven_v3 (70+ languages, most expressive)
|
||||||
|
voiceSettings: { // Optional: fine-tune voice characteristics
|
||||||
|
stability: 0.5, // 0-1: Speech consistency
|
||||||
|
similarity_boost: 0.8, // 0-1: Voice similarity to original
|
||||||
|
style: 0.0, // 0-1: Expressiveness (higher = more expressive)
|
||||||
|
use_speaker_boost: true // Enhanced clarity
|
||||||
|
}
|
||||||
|
});
|
||||||
|
|
||||||
// Stream directly to speakers
|
// Stream directly to speakers
|
||||||
audioStream.pipe(speakerOutput);
|
audioStream.pipe(speakerOutput);
|
||||||
|
|
||||||
@@ -171,6 +190,132 @@ const taxAnalysis = await ai.anthropicProvider.document({
|
|||||||
});
|
});
|
||||||
```
|
```
|
||||||
|
|
||||||
|
### 🔬 Research & Web Search
|
||||||
|
|
||||||
|
Perform deep research with web search capabilities across multiple providers:
|
||||||
|
|
||||||
|
```typescript
|
||||||
|
// OpenAI Deep Research - Comprehensive analysis
|
||||||
|
const deepResearch = await ai.openaiProvider.research({
|
||||||
|
query: 'What are the latest developments in quantum computing?',
|
||||||
|
searchDepth: 'deep',
|
||||||
|
includeWebSearch: true
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(deepResearch.answer);
|
||||||
|
console.log('Sources:', deepResearch.sources);
|
||||||
|
|
||||||
|
// Anthropic Web Search - Domain-filtered research
|
||||||
|
const anthropic = new AnthropicProvider({
|
||||||
|
anthropicToken: 'sk-ant-...',
|
||||||
|
enableWebSearch: true,
|
||||||
|
searchDomainAllowList: ['nature.com', 'science.org']
|
||||||
|
});
|
||||||
|
|
||||||
|
const scientificResearch = await anthropic.research({
|
||||||
|
query: 'Latest breakthroughs in CRISPR gene editing',
|
||||||
|
searchDepth: 'advanced'
|
||||||
|
});
|
||||||
|
|
||||||
|
// Perplexity - Research-focused with citations
|
||||||
|
const perplexityResearch = await ai.perplexityProvider.research({
|
||||||
|
query: 'Current state of autonomous vehicle technology',
|
||||||
|
searchDepth: 'deep' // Uses Sonar Pro model
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
**Research Options:**
|
||||||
|
- `searchDepth`: 'basic' | 'advanced' | 'deep'
|
||||||
|
- `maxSources`: Number of sources to include
|
||||||
|
- `includeWebSearch`: Enable web search (OpenAI)
|
||||||
|
- `background`: Run as background task (OpenAI)
|
||||||
|
|
||||||
|
**Supported Providers:**
|
||||||
|
- **OpenAI**: Deep Research API with specialized models (`o3-deep-research-2025-06-26`, `o4-mini-deep-research-2025-06-26`)
|
||||||
|
- **Anthropic**: Web Search API with domain filtering
|
||||||
|
- **Perplexity**: Sonar and Sonar Pro models with built-in citations
|
||||||
|
|
||||||
|
### 🎨 Image Generation & Editing
|
||||||
|
|
||||||
|
Generate and edit images with OpenAI's cutting-edge models:
|
||||||
|
|
||||||
|
```typescript
|
||||||
|
// Basic image generation with gpt-image-1
|
||||||
|
const image = await ai.openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A futuristic robot assistant in a modern office, digital art',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
// Save the generated image
|
||||||
|
const imageBuffer = Buffer.from(image.images[0].b64_json!, 'base64');
|
||||||
|
fs.writeFileSync('robot.png', imageBuffer);
|
||||||
|
|
||||||
|
// Advanced: Transparent background with custom format
|
||||||
|
const logo = await ai.openaiProvider.imageGenerate({
|
||||||
|
prompt: 'Minimalist mountain peak logo, geometric design',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1024x1024',
|
||||||
|
background: 'transparent',
|
||||||
|
outputFormat: 'png'
|
||||||
|
});
|
||||||
|
|
||||||
|
// WebP with compression for web use
|
||||||
|
const webImage = await ai.openaiProvider.imageGenerate({
|
||||||
|
prompt: 'Product showcase: sleek smartphone on marble surface',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1536x1024',
|
||||||
|
outputFormat: 'webp',
|
||||||
|
outputCompression: 85
|
||||||
|
});
|
||||||
|
|
||||||
|
// Superior text rendering (gpt-image-1's strength)
|
||||||
|
const signage = await ai.openaiProvider.imageGenerate({
|
||||||
|
prompt: 'Vintage cafe sign saying "COFFEE & CODE" in hand-lettered typography',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
// Generate multiple variations at once
|
||||||
|
const variations = await ai.openaiProvider.imageGenerate({
|
||||||
|
prompt: 'Abstract geometric pattern, colorful minimalist art',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
n: 3,
|
||||||
|
quality: 'medium',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
// Edit an existing image
|
||||||
|
const editedImage = await ai.openaiProvider.imageEdit({
|
||||||
|
image: originalImageBuffer,
|
||||||
|
prompt: 'Add sunglasses and change the background to a beach sunset',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high'
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
**Image Generation Options:**
|
||||||
|
- `model`: 'gpt-image-1' | 'dall-e-3' | 'dall-e-2'
|
||||||
|
- `quality`: 'low' | 'medium' | 'high' | 'auto'
|
||||||
|
- `size`: Multiple aspect ratios up to 4096×4096
|
||||||
|
- `background`: 'transparent' | 'opaque' | 'auto'
|
||||||
|
- `outputFormat`: 'png' | 'jpeg' | 'webp'
|
||||||
|
- `outputCompression`: 0-100 for webp/jpeg
|
||||||
|
- `moderation`: 'low' | 'auto'
|
||||||
|
- `n`: Number of images (1-10)
|
||||||
|
|
||||||
|
**gpt-image-1 Advantages:**
|
||||||
|
- Superior text rendering in images
|
||||||
|
- Up to 4096×4096 resolution
|
||||||
|
- Transparent background support
|
||||||
|
- Advanced output formats (WebP with compression)
|
||||||
|
- Better prompt understanding
|
||||||
|
- Streaming support for progressive rendering
|
||||||
|
|
||||||
### 🔄 Persistent Conversations
|
### 🔄 Persistent Conversations
|
||||||
|
|
||||||
Maintain context across interactions:
|
Maintain context across interactions:
|
||||||
@@ -422,6 +567,7 @@ npm install @push.rocks/smartai
|
|||||||
export OPENAI_API_KEY=sk-...
|
export OPENAI_API_KEY=sk-...
|
||||||
export ANTHROPIC_API_KEY=sk-ant-...
|
export ANTHROPIC_API_KEY=sk-ant-...
|
||||||
export PERPLEXITY_API_KEY=pplx-...
|
export PERPLEXITY_API_KEY=pplx-...
|
||||||
|
export ELEVENLABS_API_KEY=sk-...
|
||||||
# ... etc
|
# ... etc
|
||||||
```
|
```
|
||||||
|
|
||||||
@@ -447,6 +593,8 @@ export PERPLEXITY_API_KEY=pplx-...
|
|||||||
| **General Purpose** | OpenAI | Most features, stable, well-documented |
|
| **General Purpose** | OpenAI | Most features, stable, well-documented |
|
||||||
| **Complex Reasoning** | Anthropic | Superior logical thinking, safer outputs |
|
| **Complex Reasoning** | Anthropic | Superior logical thinking, safer outputs |
|
||||||
| **Research & Facts** | Perplexity | Web-aware, provides citations |
|
| **Research & Facts** | Perplexity | Web-aware, provides citations |
|
||||||
|
| **Deep Research** | OpenAI | Deep Research API with comprehensive analysis |
|
||||||
|
| **Premium TTS** | ElevenLabs | Most natural voices, 70+ languages, superior quality (v3) |
|
||||||
| **Speed Critical** | Groq | 10x faster inference, sub-second responses |
|
| **Speed Critical** | Groq | 10x faster inference, sub-second responses |
|
||||||
| **Privacy Critical** | Ollama | 100% local, no data leaves your servers |
|
| **Privacy Critical** | Ollama | 100% local, no data leaves your servers |
|
||||||
| **Real-time Data** | XAI | Access to current information |
|
| **Real-time Data** | XAI | Access to current information |
|
||||||
@@ -454,8 +602,9 @@ export PERPLEXITY_API_KEY=pplx-...
|
|||||||
|
|
||||||
## 📈 Roadmap
|
## 📈 Roadmap
|
||||||
|
|
||||||
|
- [x] Research & Web Search API
|
||||||
|
- [x] Image generation support (gpt-image-1, DALL-E 3, DALL-E 2)
|
||||||
- [ ] Streaming function calls
|
- [ ] Streaming function calls
|
||||||
- [ ] Image generation support
|
|
||||||
- [ ] Voice input processing
|
- [ ] Voice input processing
|
||||||
- [ ] Fine-tuning integration
|
- [ ] Fine-tuning integration
|
||||||
- [ ] Embedding support
|
- [ ] Embedding support
|
||||||
|
|||||||
@@ -1,177 +0,0 @@
|
|||||||
# SmartAI Research API Implementation
|
|
||||||
|
|
||||||
This document describes the new research capabilities added to the SmartAI library, enabling web search and deep research features for OpenAI and Anthropic providers.
|
|
||||||
|
|
||||||
## Features Added
|
|
||||||
|
|
||||||
### 1. Research Method Interface
|
|
||||||
|
|
||||||
Added a new `research()` method to the `MultiModalModel` abstract class with the following interfaces:
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
interface ResearchOptions {
|
|
||||||
query: string;
|
|
||||||
searchDepth?: 'basic' | 'advanced' | 'deep';
|
|
||||||
maxSources?: number;
|
|
||||||
includeWebSearch?: boolean;
|
|
||||||
background?: boolean;
|
|
||||||
}
|
|
||||||
|
|
||||||
interface ResearchResponse {
|
|
||||||
answer: string;
|
|
||||||
sources: Array<{
|
|
||||||
url: string;
|
|
||||||
title: string;
|
|
||||||
snippet: string;
|
|
||||||
}>;
|
|
||||||
searchQueries?: string[];
|
|
||||||
metadata?: any;
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
### 2. OpenAI Provider Research Implementation
|
|
||||||
|
|
||||||
The OpenAI provider now supports:
|
|
||||||
- **Deep Research API** with models:
|
|
||||||
- `o3-deep-research-2025-06-26` (comprehensive analysis)
|
|
||||||
- `o4-mini-deep-research-2025-06-26` (lightweight, faster)
|
|
||||||
- **Web Search** for standard models (gpt-5, o3, o3-pro, o4-mini)
|
|
||||||
- **Background processing** for async deep research tasks
|
|
||||||
|
|
||||||
### 3. Anthropic Provider Research Implementation
|
|
||||||
|
|
||||||
The Anthropic provider now supports:
|
|
||||||
- **Web Search API** with Claude models
|
|
||||||
- **Domain filtering** (allow/block lists)
|
|
||||||
- **Progressive searches** for comprehensive research
|
|
||||||
- **Citation extraction** from responses
|
|
||||||
|
|
||||||
### 4. Perplexity Provider Research Implementation
|
|
||||||
|
|
||||||
The Perplexity provider implements research using:
|
|
||||||
- **Sonar models** for standard searches
|
|
||||||
- **Sonar Pro** for deep research
|
|
||||||
- Built-in citation support
|
|
||||||
|
|
||||||
### 5. Other Providers
|
|
||||||
|
|
||||||
Added research method stubs to:
|
|
||||||
- Groq Provider
|
|
||||||
- Ollama Provider
|
|
||||||
- xAI Provider
|
|
||||||
- Exo Provider
|
|
||||||
|
|
||||||
These providers throw a "not yet supported" error when research is called, maintaining interface compatibility.
|
|
||||||
|
|
||||||
## Usage Examples
|
|
||||||
|
|
||||||
### Basic Research with OpenAI
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { OpenAiProvider } from '@push.rocks/smartai';
|
|
||||||
|
|
||||||
const openai = new OpenAiProvider({
|
|
||||||
openaiToken: 'your-api-key',
|
|
||||||
researchModel: 'o4-mini-deep-research-2025-06-26'
|
|
||||||
});
|
|
||||||
|
|
||||||
await openai.start();
|
|
||||||
|
|
||||||
const result = await openai.research({
|
|
||||||
query: 'What are the latest developments in quantum computing?',
|
|
||||||
searchDepth: 'basic',
|
|
||||||
includeWebSearch: true
|
|
||||||
});
|
|
||||||
|
|
||||||
console.log(result.answer);
|
|
||||||
console.log('Sources:', result.sources);
|
|
||||||
```
|
|
||||||
|
|
||||||
### Deep Research with OpenAI
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
const deepResult = await openai.research({
|
|
||||||
query: 'Comprehensive analysis of climate change mitigation strategies',
|
|
||||||
searchDepth: 'deep',
|
|
||||||
background: true
|
|
||||||
});
|
|
||||||
```
|
|
||||||
|
|
||||||
### Research with Anthropic
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { AnthropicProvider } from '@push.rocks/smartai';
|
|
||||||
|
|
||||||
const anthropic = new AnthropicProvider({
|
|
||||||
anthropicToken: 'your-api-key',
|
|
||||||
enableWebSearch: true,
|
|
||||||
searchDomainAllowList: ['nature.com', 'science.org']
|
|
||||||
});
|
|
||||||
|
|
||||||
await anthropic.start();
|
|
||||||
|
|
||||||
const result = await anthropic.research({
|
|
||||||
query: 'Latest breakthroughs in CRISPR gene editing',
|
|
||||||
searchDepth: 'advanced'
|
|
||||||
});
|
|
||||||
```
|
|
||||||
|
|
||||||
### Research with Perplexity
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { PerplexityProvider } from '@push.rocks/smartai';
|
|
||||||
|
|
||||||
const perplexity = new PerplexityProvider({
|
|
||||||
perplexityToken: 'your-api-key'
|
|
||||||
});
|
|
||||||
|
|
||||||
const result = await perplexity.research({
|
|
||||||
query: 'Current state of autonomous vehicle technology',
|
|
||||||
searchDepth: 'deep' // Uses Sonar Pro model
|
|
||||||
});
|
|
||||||
```
|
|
||||||
|
|
||||||
## Configuration Options
|
|
||||||
|
|
||||||
### OpenAI Provider
|
|
||||||
- `researchModel`: Specify deep research model (default: `o4-mini-deep-research-2025-06-26`)
|
|
||||||
- `enableWebSearch`: Enable web search for standard models
|
|
||||||
|
|
||||||
### Anthropic Provider
|
|
||||||
- `enableWebSearch`: Enable web search capabilities
|
|
||||||
- `searchDomainAllowList`: Array of allowed domains
|
|
||||||
- `searchDomainBlockList`: Array of blocked domains
|
|
||||||
|
|
||||||
## API Pricing
|
|
||||||
|
|
||||||
- **OpenAI Deep Research**: $10 per 1,000 calls
|
|
||||||
- **Anthropic Web Search**: $10 per 1,000 searches + standard token costs
|
|
||||||
- **Perplexity Sonar**: $5 per 1,000 searches (Sonar Pro)
|
|
||||||
|
|
||||||
## Testing
|
|
||||||
|
|
||||||
Run the test suite:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
pnpm test test/test.research.ts
|
|
||||||
```
|
|
||||||
|
|
||||||
All providers have been tested to ensure:
|
|
||||||
- Research methods are properly exposed
|
|
||||||
- Interfaces are correctly typed
|
|
||||||
- Unsupported providers throw appropriate errors
|
|
||||||
|
|
||||||
## Next Steps
|
|
||||||
|
|
||||||
Future enhancements could include:
|
|
||||||
1. Implementing Google Gemini Grounding API support
|
|
||||||
2. Adding Brave Search API integration
|
|
||||||
3. Implementing retry logic for rate limits
|
|
||||||
4. Adding caching for repeated queries
|
|
||||||
5. Supporting batch research operations
|
|
||||||
|
|
||||||
## Notes
|
|
||||||
|
|
||||||
- The implementation maintains backward compatibility
|
|
||||||
- All existing methods continue to work unchanged
|
|
||||||
- Research capabilities are optional and don't affect existing functionality
|
|
||||||
@@ -1,160 +0,0 @@
|
|||||||
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';
|
|
||||||
|
|
||||||
const testQenv = new qenv.Qenv('./', './.nogit/');
|
|
||||||
|
|
||||||
import * as smartai from '../ts/index.js';
|
|
||||||
|
|
||||||
let anthropicProvider: smartai.AnthropicProvider;
|
|
||||||
|
|
||||||
tap.test('Anthropic: should create and start Anthropic provider', async () => {
|
|
||||||
anthropicProvider = new smartai.AnthropicProvider({
|
|
||||||
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
|
||||||
});
|
|
||||||
await anthropicProvider.start();
|
|
||||||
expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: should create chat response', async () => {
|
|
||||||
const userMessage = 'What is the capital of France? Answer in one word.';
|
|
||||||
const response = await anthropicProvider.chat({
|
|
||||||
systemMessage: 'You are a helpful assistant. Be concise.',
|
|
||||||
userMessage: userMessage,
|
|
||||||
messageHistory: [],
|
|
||||||
});
|
|
||||||
console.log(`Anthropic Chat - User: ${userMessage}`);
|
|
||||||
console.log(`Anthropic Chat - Response: ${response.message}`);
|
|
||||||
|
|
||||||
expect(response.role).toEqual('assistant');
|
|
||||||
expect(response.message).toBeTruthy();
|
|
||||||
expect(response.message.toLowerCase()).toInclude('paris');
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: should handle message history', async () => {
|
|
||||||
const messageHistory: smartai.ChatMessage[] = [
|
|
||||||
{ role: 'user', content: 'My name is Claude Test' },
|
|
||||||
{ role: 'assistant', content: 'Nice to meet you, Claude Test!' }
|
|
||||||
];
|
|
||||||
|
|
||||||
const response = await anthropicProvider.chat({
|
|
||||||
systemMessage: 'You are a helpful assistant with good memory.',
|
|
||||||
userMessage: 'What is my name?',
|
|
||||||
messageHistory: messageHistory,
|
|
||||||
});
|
|
||||||
|
|
||||||
console.log(`Anthropic Memory Test - Response: ${response.message}`);
|
|
||||||
expect(response.message.toLowerCase()).toInclude('claude test');
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: should process vision tasks', async () => {
|
|
||||||
// Create a simple test image (1x1 red pixel JPEG)
|
|
||||||
// This is a valid 1x1 JPEG image
|
|
||||||
const redPixelBase64 = '/9j/4AAQSkZJRgABAQEAYABgAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL/2wBDAQkJCQwLDBgNDRgyIRwhMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjL/wAARCAABAAEDASIAAhEBAxEB/8QAFQABAQAAAAAAAAAAAAAAAAAAAAv/xAAUEAEAAAAAAAAAAAAAAAAAAAAA/8QAFQEBAQAAAAAAAAAAAAAAAAAAAAX/xAAUEQEAAAAAAAAAAAAAAAAAAAAA/9oADAMBAAIRAxEAPwCwAA8A/9k=';
|
|
||||||
const imageBuffer = Buffer.from(redPixelBase64, 'base64');
|
|
||||||
|
|
||||||
const result = await anthropicProvider.vision({
|
|
||||||
image: imageBuffer,
|
|
||||||
prompt: 'What color is this image? Answer with just the color name.'
|
|
||||||
});
|
|
||||||
|
|
||||||
console.log(`Anthropic Vision - Result: ${result}`);
|
|
||||||
expect(result).toBeTruthy();
|
|
||||||
expect(typeof result).toEqual('string');
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: 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 anthropicProvider.document({
|
|
||||||
systemMessage: 'Classify the document. Only the following answers are allowed: "invoice", "bank account statement", "contract", "test document", "other". The answer should only contain the keyword for machine use.',
|
|
||||||
userMessage: 'Classify this document.',
|
|
||||||
messageHistory: [],
|
|
||||||
pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
|
|
||||||
});
|
|
||||||
|
|
||||||
console.log(`Anthropic Document - Result:`, result);
|
|
||||||
expect(result).toBeTruthy();
|
|
||||||
expect(result.message).toBeTruthy();
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: should handle complex document analysis', async () => {
|
|
||||||
// Test with the demo PDF if it exists
|
|
||||||
const pdfPath = './.nogit/demo_without_textlayer.pdf';
|
|
||||||
let pdfBuffer: Uint8Array;
|
|
||||||
|
|
||||||
try {
|
|
||||||
pdfBuffer = await smartfile.fs.toBuffer(pdfPath);
|
|
||||||
} catch (error) {
|
|
||||||
// If the file doesn't exist, use the dummy PDF
|
|
||||||
console.log('Demo PDF not found, using dummy PDF instead');
|
|
||||||
const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
|
|
||||||
const pdfResponse = await smartrequest.SmartRequest.create()
|
|
||||||
.url(pdfUrl)
|
|
||||||
.get();
|
|
||||||
pdfBuffer = Buffer.from(await pdfResponse.arrayBuffer());
|
|
||||||
}
|
|
||||||
|
|
||||||
const result = await anthropicProvider.document({
|
|
||||||
systemMessage: `
|
|
||||||
Analyze this document and provide a JSON response with the following structure:
|
|
||||||
{
|
|
||||||
"documentType": "string",
|
|
||||||
"hasText": boolean,
|
|
||||||
"summary": "string"
|
|
||||||
}
|
|
||||||
`,
|
|
||||||
userMessage: 'Analyze this document.',
|
|
||||||
messageHistory: [],
|
|
||||||
pdfDocuments: [pdfBuffer],
|
|
||||||
});
|
|
||||||
|
|
||||||
console.log(`Anthropic Complex Document Analysis:`, result);
|
|
||||||
expect(result).toBeTruthy();
|
|
||||||
expect(result.message).toBeTruthy();
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: should handle errors gracefully', async () => {
|
|
||||||
// Test with invalid message (empty)
|
|
||||||
let errorCaught = false;
|
|
||||||
|
|
||||||
try {
|
|
||||||
await anthropicProvider.chat({
|
|
||||||
systemMessage: '',
|
|
||||||
userMessage: '',
|
|
||||||
messageHistory: [],
|
|
||||||
});
|
|
||||||
} catch (error) {
|
|
||||||
errorCaught = true;
|
|
||||||
console.log('Expected error caught:', error.message);
|
|
||||||
}
|
|
||||||
|
|
||||||
// Anthropic might handle empty messages, so we don't assert error
|
|
||||||
console.log(`Error handling test - Error caught: ${errorCaught}`);
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: audio should throw not supported error', async () => {
|
|
||||||
let errorCaught = false;
|
|
||||||
|
|
||||||
try {
|
|
||||||
await anthropicProvider.audio({
|
|
||||||
message: 'This should fail'
|
|
||||||
});
|
|
||||||
} catch (error) {
|
|
||||||
errorCaught = true;
|
|
||||||
expect(error.message).toInclude('not yet supported');
|
|
||||||
}
|
|
||||||
|
|
||||||
expect(errorCaught).toBeTrue();
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('Anthropic: should stop the provider', async () => {
|
|
||||||
await anthropicProvider.stop();
|
|
||||||
console.log('Anthropic provider stopped successfully');
|
|
||||||
});
|
|
||||||
|
|
||||||
export default tap.start();
|
|
||||||
54
test/test.audio.elevenlabs.ts
Normal file
54
test/test.audio.elevenlabs.ts
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
import * as smartfile from '@push.rocks/smartfile';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let testSmartai: smartai.SmartAi;
|
||||||
|
|
||||||
|
tap.test('ElevenLabs Audio: should create a smartai instance with ElevenLabs provider', async () => {
|
||||||
|
testSmartai = new smartai.SmartAi({
|
||||||
|
elevenlabsToken: await testQenv.getEnvVarOnDemand('ELEVENLABS_TOKEN'),
|
||||||
|
elevenlabs: {
|
||||||
|
defaultVoiceId: '19STyYD15bswVz51nqLf',
|
||||||
|
},
|
||||||
|
});
|
||||||
|
await testSmartai.start();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('ElevenLabs Audio: should create audio response', async () => {
|
||||||
|
const audioStream = await testSmartai.elevenlabsProvider.audio({
|
||||||
|
message: 'Welcome to SmartAI, the unified interface for the world\'s leading artificial intelligence providers. SmartAI brings together OpenAI, Anthropic, Perplexity, and ElevenLabs under a single elegant TypeScript API. Whether you need text generation, vision analysis, document processing, or premium text-to-speech capabilities, SmartAI provides a consistent and powerful interface for all your AI needs. Build intelligent applications at lightning speed without vendor lock-in.',
|
||||||
|
});
|
||||||
|
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_elevenlabs.mp3');
|
||||||
|
console.log(`Audio Buffer length: ${audioBuffer.length}`);
|
||||||
|
expect(audioBuffer.length).toBeGreaterThan(0);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('ElevenLabs Audio: should create audio with custom voice', async () => {
|
||||||
|
const audioStream = await testSmartai.elevenlabsProvider.audio({
|
||||||
|
message: 'Testing with a different voice.',
|
||||||
|
voiceId: 'JBFqnCBsd6RMkjVDRZzb',
|
||||||
|
});
|
||||||
|
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_elevenlabs_custom.mp3');
|
||||||
|
console.log(`Audio Buffer length (custom voice): ${audioBuffer.length}`);
|
||||||
|
expect(audioBuffer.length).toBeGreaterThan(0);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('ElevenLabs Audio: should stop the smartai instance', async () => {
|
||||||
|
await testSmartai.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
39
test/test.audio.openai.ts
Normal file
39
test/test.audio.openai.ts
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
import * as smartfile from '@push.rocks/smartfile';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let testSmartai: smartai.SmartAi;
|
||||||
|
|
||||||
|
tap.test('OpenAI Audio: should create a smartai instance with OpenAI provider', async () => {
|
||||||
|
testSmartai = new smartai.SmartAi({
|
||||||
|
openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
|
||||||
|
});
|
||||||
|
await testSmartai.start();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Audio: should create audio response', 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('OpenAI Audio: should stop the smartai instance', async () => {
|
||||||
|
await testSmartai.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
36
test/test.audio.stubs.ts
Normal file
36
test/test.audio.stubs.ts
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let anthropicProvider: smartai.AnthropicProvider;
|
||||||
|
|
||||||
|
tap.test('Audio Stubs: should create Anthropic provider', async () => {
|
||||||
|
anthropicProvider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
});
|
||||||
|
await anthropicProvider.start();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Audio Stubs: Anthropic audio should throw not supported error', async () => {
|
||||||
|
let errorCaught = false;
|
||||||
|
|
||||||
|
try {
|
||||||
|
await anthropicProvider.audio({
|
||||||
|
message: 'This should fail'
|
||||||
|
});
|
||||||
|
} catch (error) {
|
||||||
|
errorCaught = true;
|
||||||
|
expect(error.message).toInclude('not yet supported');
|
||||||
|
}
|
||||||
|
|
||||||
|
expect(errorCaught).toBeTrue();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Audio Stubs: should stop Anthropic provider', async () => {
|
||||||
|
await anthropicProvider.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
72
test/test.chat.anthropic.ts
Normal file
72
test/test.chat.anthropic.ts
Normal file
@@ -0,0 +1,72 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let anthropicProvider: smartai.AnthropicProvider;
|
||||||
|
|
||||||
|
tap.test('Anthropic Chat: should create and start Anthropic provider', async () => {
|
||||||
|
anthropicProvider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
});
|
||||||
|
await anthropicProvider.start();
|
||||||
|
expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Chat: should create chat response', async () => {
|
||||||
|
const userMessage = 'What is the capital of France? Answer in one word.';
|
||||||
|
const response = await anthropicProvider.chat({
|
||||||
|
systemMessage: 'You are a helpful assistant. Be concise.',
|
||||||
|
userMessage: userMessage,
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
console.log(`Anthropic Chat - User: ${userMessage}`);
|
||||||
|
console.log(`Anthropic Chat - Response: ${response.message}`);
|
||||||
|
|
||||||
|
expect(response.role).toEqual('assistant');
|
||||||
|
expect(response.message).toBeTruthy();
|
||||||
|
expect(response.message.toLowerCase()).toInclude('paris');
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Chat: should handle message history', async () => {
|
||||||
|
const messageHistory: smartai.ChatMessage[] = [
|
||||||
|
{ role: 'user', content: 'My name is Claude Test' },
|
||||||
|
{ role: 'assistant', content: 'Nice to meet you, Claude Test!' }
|
||||||
|
];
|
||||||
|
|
||||||
|
const response = await anthropicProvider.chat({
|
||||||
|
systemMessage: 'You are a helpful assistant with good memory.',
|
||||||
|
userMessage: 'What is my name?',
|
||||||
|
messageHistory: messageHistory,
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Anthropic Memory Test - Response: ${response.message}`);
|
||||||
|
expect(response.message.toLowerCase()).toInclude('claude test');
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Chat: should handle errors gracefully', async () => {
|
||||||
|
// Test with invalid message (empty)
|
||||||
|
let errorCaught = false;
|
||||||
|
|
||||||
|
try {
|
||||||
|
await anthropicProvider.chat({
|
||||||
|
systemMessage: '',
|
||||||
|
userMessage: '',
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
} catch (error) {
|
||||||
|
errorCaught = true;
|
||||||
|
console.log('Expected error caught:', error.message);
|
||||||
|
}
|
||||||
|
|
||||||
|
// Anthropic might handle empty messages, so we don't assert error
|
||||||
|
console.log(`Error handling test - Error caught: ${errorCaught}`);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Chat: should stop the provider', async () => {
|
||||||
|
await anthropicProvider.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
34
test/test.chat.openai.ts
Normal file
34
test/test.chat.openai.ts
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let testSmartai: smartai.SmartAi;
|
||||||
|
|
||||||
|
tap.test('OpenAI Chat: should create a smartai instance with OpenAI provider', async () => {
|
||||||
|
testSmartai = new smartai.SmartAi({
|
||||||
|
openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
|
||||||
|
});
|
||||||
|
await testSmartai.start();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Chat: should create chat response', 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);
|
||||||
|
expect(response.role).toEqual('assistant');
|
||||||
|
expect(response.message).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Chat: should stop the smartai instance', async () => {
|
||||||
|
await testSmartai.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
78
test/test.document.anthropic.ts
Normal file
78
test/test.document.anthropic.ts
Normal file
@@ -0,0 +1,78 @@
|
|||||||
|
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';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let anthropicProvider: smartai.AnthropicProvider;
|
||||||
|
|
||||||
|
tap.test('Anthropic Document: should create and start Anthropic provider', async () => {
|
||||||
|
anthropicProvider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
});
|
||||||
|
await anthropicProvider.start();
|
||||||
|
expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Document: 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 anthropicProvider.document({
|
||||||
|
systemMessage: 'Classify the document. Only the following answers are allowed: "invoice", "bank account statement", "contract", "test document", "other". The answer should only contain the keyword for machine use.',
|
||||||
|
userMessage: 'Classify this document.',
|
||||||
|
messageHistory: [],
|
||||||
|
pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Anthropic Document - Result:`, result);
|
||||||
|
expect(result).toBeTruthy();
|
||||||
|
expect(result.message).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Document: should handle complex document analysis', async () => {
|
||||||
|
// Test with the demo PDF if it exists
|
||||||
|
const pdfPath = './.nogit/demo_without_textlayer.pdf';
|
||||||
|
let pdfBuffer: Uint8Array;
|
||||||
|
|
||||||
|
try {
|
||||||
|
pdfBuffer = await smartfile.fs.toBuffer(pdfPath);
|
||||||
|
} catch (error) {
|
||||||
|
// If the file doesn't exist, use the dummy PDF
|
||||||
|
console.log('Demo PDF not found, using dummy PDF instead');
|
||||||
|
const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
|
||||||
|
const pdfResponse = await smartrequest.SmartRequest.create()
|
||||||
|
.url(pdfUrl)
|
||||||
|
.get();
|
||||||
|
pdfBuffer = Buffer.from(await pdfResponse.arrayBuffer());
|
||||||
|
}
|
||||||
|
|
||||||
|
const result = await anthropicProvider.document({
|
||||||
|
systemMessage: `
|
||||||
|
Analyze this document and provide a JSON response with the following structure:
|
||||||
|
{
|
||||||
|
"documentType": "string",
|
||||||
|
"hasText": boolean,
|
||||||
|
"summary": "string"
|
||||||
|
}
|
||||||
|
`,
|
||||||
|
userMessage: 'Analyze this document.',
|
||||||
|
messageHistory: [],
|
||||||
|
pdfDocuments: [pdfBuffer],
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Anthropic Complex Document Analysis:`, result);
|
||||||
|
expect(result).toBeTruthy();
|
||||||
|
expect(result.message).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Document: should stop the provider', async () => {
|
||||||
|
await anthropicProvider.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
@@ -9,25 +9,14 @@ import * as smartai from '../ts/index.js';
|
|||||||
|
|
||||||
let testSmartai: smartai.SmartAi;
|
let testSmartai: smartai.SmartAi;
|
||||||
|
|
||||||
tap.test('OpenAI: should create a smartai instance with OpenAI provider', async () => {
|
tap.test('OpenAI Document: should create a smartai instance with OpenAI provider', async () => {
|
||||||
testSmartai = new smartai.SmartAi({
|
testSmartai = new smartai.SmartAi({
|
||||||
openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
|
openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
|
||||||
});
|
});
|
||||||
await testSmartai.start();
|
await testSmartai.start();
|
||||||
});
|
});
|
||||||
|
|
||||||
tap.test('OpenAI: should create chat response', async () => {
|
tap.test('OpenAI Document: should document a pdf', 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('OpenAI: should document a pdf', async () => {
|
|
||||||
const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
|
const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
|
||||||
const pdfResponse = await smartrequest.SmartRequest.create()
|
const pdfResponse = await smartrequest.SmartRequest.create()
|
||||||
.url(pdfUrl)
|
.url(pdfUrl)
|
||||||
@@ -39,9 +28,10 @@ tap.test('OpenAI: should document a pdf', async () => {
|
|||||||
pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
|
pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
|
||||||
});
|
});
|
||||||
console.log(result);
|
console.log(result);
|
||||||
|
expect(result.message).toBeTruthy();
|
||||||
});
|
});
|
||||||
|
|
||||||
tap.test('OpenAI: should recognize companies in a pdf', async () => {
|
tap.test('OpenAI Document: should recognize companies in a pdf', async () => {
|
||||||
const pdfBuffer = await smartfile.fs.toBuffer('./.nogit/demo_without_textlayer.pdf');
|
const pdfBuffer = await smartfile.fs.toBuffer('./.nogit/demo_without_textlayer.pdf');
|
||||||
const result = await testSmartai.openaiProvider.document({
|
const result = await testSmartai.openaiProvider.document({
|
||||||
systemMessage: `
|
systemMessage: `
|
||||||
@@ -76,27 +66,11 @@ tap.test('OpenAI: should recognize companies in a pdf', async () => {
|
|||||||
pdfDocuments: [pdfBuffer],
|
pdfDocuments: [pdfBuffer],
|
||||||
});
|
});
|
||||||
console.log(result);
|
console.log(result);
|
||||||
|
expect(result.message).toBeTruthy();
|
||||||
});
|
});
|
||||||
|
|
||||||
tap.test('OpenAI: should create audio response', async () => {
|
tap.test('OpenAI Document: should stop the smartai instance', 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: ${audioBuffer.length}`);
|
|
||||||
// Assert that the resulting buffer is not empty.
|
|
||||||
expect(audioBuffer.length).toBeGreaterThan(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
tap.test('OpenAI: should stop the smartai instance', async () => {
|
|
||||||
await testSmartai.stop();
|
await testSmartai.stop();
|
||||||
});
|
});
|
||||||
|
|
||||||
export default tap.start();
|
export default tap.start();
|
||||||
203
test/test.image.openai.ts
Normal file
203
test/test.image.openai.ts
Normal file
@@ -0,0 +1,203 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
import * as path from 'path';
|
||||||
|
import { promises as fs } from 'fs';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
let openaiProvider: smartai.OpenAiProvider;
|
||||||
|
|
||||||
|
// Helper function to save image results
|
||||||
|
async function saveImageResult(testName: string, result: any) {
|
||||||
|
const sanitizedName = testName.replace(/[^a-z0-9]/gi, '_').toLowerCase();
|
||||||
|
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
|
||||||
|
const filename = `openai_${sanitizedName}_${timestamp}.json`;
|
||||||
|
const filepath = path.join('.nogit', 'testresults', 'images', filename);
|
||||||
|
|
||||||
|
await fs.mkdir(path.dirname(filepath), { recursive: true });
|
||||||
|
await fs.writeFile(filepath, JSON.stringify(result, null, 2), 'utf-8');
|
||||||
|
|
||||||
|
console.log(` 💾 Saved to: ${filepath}`);
|
||||||
|
|
||||||
|
// Also save the actual image if b64_json is present
|
||||||
|
if (result.images && result.images[0]?.b64_json) {
|
||||||
|
const imageFilename = `openai_${sanitizedName}_${timestamp}.png`;
|
||||||
|
const imageFilepath = path.join('.nogit', 'testresults', 'images', imageFilename);
|
||||||
|
await fs.writeFile(imageFilepath, Buffer.from(result.images[0].b64_json, 'base64'));
|
||||||
|
console.log(` 🖼️ Image saved to: ${imageFilepath}`);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
tap.test('OpenAI Image Generation: should initialize provider', async () => {
|
||||||
|
const openaiToken = await testQenv.getEnvVarOnDemand('OPENAI_TOKEN');
|
||||||
|
expect(openaiToken).toBeTruthy();
|
||||||
|
|
||||||
|
openaiProvider = new smartai.OpenAiProvider({
|
||||||
|
openaiToken,
|
||||||
|
imageModel: 'gpt-image-1'
|
||||||
|
});
|
||||||
|
|
||||||
|
await openaiProvider.start();
|
||||||
|
expect(openaiProvider).toBeInstanceOf(smartai.OpenAiProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: Basic generation with gpt-image-1', async () => {
|
||||||
|
const result = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A cute robot reading a book in a cozy library, digital art style',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'medium',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('Basic gpt-image-1 Generation:');
|
||||||
|
console.log('- Images generated:', result.images.length);
|
||||||
|
console.log('- Model used:', result.metadata?.model);
|
||||||
|
console.log('- Quality:', result.metadata?.quality);
|
||||||
|
console.log('- Size:', result.metadata?.size);
|
||||||
|
console.log('- Tokens used:', result.metadata?.tokensUsed);
|
||||||
|
|
||||||
|
await saveImageResult('basic_generation_gptimage1', result);
|
||||||
|
|
||||||
|
expect(result.images).toBeTruthy();
|
||||||
|
expect(result.images.length).toEqual(1);
|
||||||
|
expect(result.images[0].b64_json).toBeTruthy();
|
||||||
|
expect(result.metadata?.model).toEqual('gpt-image-1');
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: High quality with transparent background', async () => {
|
||||||
|
const result = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A simple geometric logo of a mountain peak, minimal design, clean lines',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1024x1024',
|
||||||
|
background: 'transparent',
|
||||||
|
outputFormat: 'png'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('High Quality Transparent:');
|
||||||
|
console.log('- Quality:', result.metadata?.quality);
|
||||||
|
console.log('- Background: transparent');
|
||||||
|
console.log('- Format:', result.metadata?.outputFormat);
|
||||||
|
console.log('- Tokens used:', result.metadata?.tokensUsed);
|
||||||
|
|
||||||
|
await saveImageResult('high_quality_transparent', result);
|
||||||
|
|
||||||
|
expect(result.images.length).toEqual(1);
|
||||||
|
expect(result.images[0].b64_json).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: WebP format with compression', async () => {
|
||||||
|
const result = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A futuristic cityscape at sunset with flying cars, photorealistic',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1536x1024',
|
||||||
|
outputFormat: 'webp',
|
||||||
|
outputCompression: 85
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('WebP with Compression:');
|
||||||
|
console.log('- Format:', result.metadata?.outputFormat);
|
||||||
|
console.log('- Compression: 85%');
|
||||||
|
console.log('- Size:', result.metadata?.size);
|
||||||
|
|
||||||
|
await saveImageResult('webp_compression', result);
|
||||||
|
|
||||||
|
expect(result.images.length).toEqual(1);
|
||||||
|
expect(result.images[0].b64_json).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: Text rendering with gpt-image-1', async () => {
|
||||||
|
const result = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A vintage cafe sign that says "COFFEE & CODE" in elegant hand-lettered typography, warm colors',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'high',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('Text Rendering:');
|
||||||
|
console.log('- Prompt includes text: "COFFEE & CODE"');
|
||||||
|
console.log('- gpt-image-1 has superior text rendering');
|
||||||
|
console.log('- Tokens used:', result.metadata?.tokensUsed);
|
||||||
|
|
||||||
|
await saveImageResult('text_rendering', result);
|
||||||
|
|
||||||
|
expect(result.images.length).toEqual(1);
|
||||||
|
expect(result.images[0].b64_json).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: Multiple images generation', async () => {
|
||||||
|
const result = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'Abstract colorful geometric patterns, modern minimalist art',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
n: 2,
|
||||||
|
quality: 'medium',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('Multiple Images:');
|
||||||
|
console.log('- Images requested: 2');
|
||||||
|
console.log('- Images generated:', result.images.length);
|
||||||
|
|
||||||
|
await saveImageResult('multiple_images', result);
|
||||||
|
|
||||||
|
expect(result.images.length).toEqual(2);
|
||||||
|
expect(result.images[0].b64_json).toBeTruthy();
|
||||||
|
expect(result.images[1].b64_json).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: Low moderation setting', async () => {
|
||||||
|
const result = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A fantasy battle scene with warriors and dragons',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
moderation: 'low',
|
||||||
|
quality: 'medium'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('Low Moderation:');
|
||||||
|
console.log('- Moderation: low (less restrictive filtering)');
|
||||||
|
console.log('- Tokens used:', result.metadata?.tokensUsed);
|
||||||
|
|
||||||
|
await saveImageResult('low_moderation', result);
|
||||||
|
|
||||||
|
expect(result.images.length).toEqual(1);
|
||||||
|
expect(result.images[0].b64_json).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image Editing: edit with gpt-image-1', async () => {
|
||||||
|
// First, generate a base image
|
||||||
|
const baseResult = await openaiProvider.imageGenerate({
|
||||||
|
prompt: 'A simple white cat sitting on a red cushion',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'low',
|
||||||
|
size: '1024x1024'
|
||||||
|
});
|
||||||
|
|
||||||
|
const baseImageBuffer = Buffer.from(baseResult.images[0].b64_json!, 'base64');
|
||||||
|
|
||||||
|
// Now edit it
|
||||||
|
const editResult = await openaiProvider.imageEdit({
|
||||||
|
image: baseImageBuffer,
|
||||||
|
prompt: 'Change the cat to orange and add stylish sunglasses',
|
||||||
|
model: 'gpt-image-1',
|
||||||
|
quality: 'medium'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('Image Editing:');
|
||||||
|
console.log('- Base image created');
|
||||||
|
console.log('- Edit: change color and add sunglasses');
|
||||||
|
console.log('- Result images:', editResult.images.length);
|
||||||
|
|
||||||
|
await saveImageResult('image_edit', editResult);
|
||||||
|
|
||||||
|
expect(editResult.images.length).toEqual(1);
|
||||||
|
expect(editResult.images[0].b64_json).toBeTruthy();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('OpenAI Image: should clean up provider', async () => {
|
||||||
|
await openaiProvider.stop();
|
||||||
|
console.log('OpenAI image provider stopped successfully');
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
@@ -1,9 +1,24 @@
|
|||||||
import { expect, tap } from '@push.rocks/tapbundle';
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
import * as qenv from '@push.rocks/qenv';
|
import * as qenv from '@push.rocks/qenv';
|
||||||
import * as smartai from '../ts/index.js';
|
import * as smartai from '../ts/index.js';
|
||||||
|
import * as path from 'path';
|
||||||
|
import { promises as fs } from 'fs';
|
||||||
|
|
||||||
const testQenv = new qenv.Qenv('./', './.nogit/');
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
// Helper function to save research results
|
||||||
|
async function saveResearchResult(testName: string, result: any) {
|
||||||
|
const sanitizedName = testName.replace(/[^a-z0-9]/gi, '_').toLowerCase();
|
||||||
|
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
|
||||||
|
const filename = `${sanitizedName}_${timestamp}.json`;
|
||||||
|
const filepath = path.join('.nogit', 'testresults', 'research', filename);
|
||||||
|
|
||||||
|
await fs.mkdir(path.dirname(filepath), { recursive: true });
|
||||||
|
await fs.writeFile(filepath, JSON.stringify(result, null, 2), 'utf-8');
|
||||||
|
|
||||||
|
console.log(` 💾 Saved to: ${filepath}`);
|
||||||
|
}
|
||||||
|
|
||||||
let anthropicProvider: smartai.AnthropicProvider;
|
let anthropicProvider: smartai.AnthropicProvider;
|
||||||
|
|
||||||
tap.test('Anthropic Research: should initialize provider with web search', async () => {
|
tap.test('Anthropic Research: should initialize provider with web search', async () => {
|
||||||
@@ -28,6 +43,8 @@ tap.test('Anthropic Research: should perform basic research query', async () =>
|
|||||||
console.log('- Sources found:', result.sources.length);
|
console.log('- Sources found:', result.sources.length);
|
||||||
console.log('- First 200 chars:', result.answer.substring(0, 200));
|
console.log('- First 200 chars:', result.answer.substring(0, 200));
|
||||||
|
|
||||||
|
await saveResearchResult('basic_research_machine_learning', result);
|
||||||
|
|
||||||
expect(result).toBeTruthy();
|
expect(result).toBeTruthy();
|
||||||
expect(result.answer).toBeTruthy();
|
expect(result.answer).toBeTruthy();
|
||||||
expect(result.answer.toLowerCase()).toInclude('machine learning');
|
expect(result.answer.toLowerCase()).toInclude('machine learning');
|
||||||
@@ -50,6 +67,8 @@ tap.test('Anthropic Research: should perform research with web search', async ()
|
|||||||
console.log('- Search queries:', result.searchQueries);
|
console.log('- Search queries:', result.searchQueries);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
await saveResearchResult('web_search_renewable_energy', result);
|
||||||
|
|
||||||
expect(result.answer).toBeTruthy();
|
expect(result.answer).toBeTruthy();
|
||||||
expect(result.answer.toLowerCase()).toInclude('renewable');
|
expect(result.answer.toLowerCase()).toInclude('renewable');
|
||||||
|
|
||||||
@@ -70,6 +89,8 @@ tap.test('Anthropic Research: should handle deep research queries', async () =>
|
|||||||
console.log('- Answer length:', result.answer.length);
|
console.log('- Answer length:', result.answer.length);
|
||||||
console.log('- Token usage:', result.metadata?.tokensUsed);
|
console.log('- Token usage:', result.metadata?.tokensUsed);
|
||||||
|
|
||||||
|
await saveResearchResult('deep_research_rest_vs_graphql', result);
|
||||||
|
|
||||||
expect(result.answer).toBeTruthy();
|
expect(result.answer).toBeTruthy();
|
||||||
expect(result.answer.length).toBeGreaterThan(300);
|
expect(result.answer.length).toBeGreaterThan(300);
|
||||||
expect(result.answer.toLowerCase()).toInclude('rest');
|
expect(result.answer.toLowerCase()).toInclude('rest');
|
||||||
@@ -87,6 +108,8 @@ tap.test('Anthropic Research: should extract citations from response', async ()
|
|||||||
console.log('- Sources found:', result.sources.length);
|
console.log('- Sources found:', result.sources.length);
|
||||||
console.log('- Answer includes Docker:', result.answer.toLowerCase().includes('docker'));
|
console.log('- Answer includes Docker:', result.answer.toLowerCase().includes('docker'));
|
||||||
|
|
||||||
|
await saveResearchResult('citation_extraction_docker', result);
|
||||||
|
|
||||||
expect(result.answer).toInclude('Docker');
|
expect(result.answer).toInclude('Docker');
|
||||||
|
|
||||||
// Check for URL extraction (both markdown and plain URLs)
|
// Check for URL extraction (both markdown and plain URLs)
|
||||||
@@ -114,6 +137,8 @@ tap.test('Anthropic Research: should use domain filtering when configured', asyn
|
|||||||
console.log('- Answer length:', result.answer.length);
|
console.log('- Answer length:', result.answer.length);
|
||||||
console.log('- Applied domain filters (allow: wikipedia, docs.microsoft)');
|
console.log('- Applied domain filters (allow: wikipedia, docs.microsoft)');
|
||||||
|
|
||||||
|
await saveResearchResult('domain_filtering_javascript', result);
|
||||||
|
|
||||||
expect(result.answer).toBeTruthy();
|
expect(result.answer).toBeTruthy();
|
||||||
expect(result.answer.toLowerCase()).toInclude('javascript');
|
expect(result.answer.toLowerCase()).toInclude('javascript');
|
||||||
|
|
||||||
@@ -156,6 +181,9 @@ tap.test('Anthropic Research: should handle different search depths', async () =
|
|||||||
console.log('- Basic tokens:', basicResult.metadata?.tokensUsed);
|
console.log('- Basic tokens:', basicResult.metadata?.tokensUsed);
|
||||||
console.log('- Advanced tokens:', advancedResult.metadata?.tokensUsed);
|
console.log('- Advanced tokens:', advancedResult.metadata?.tokensUsed);
|
||||||
|
|
||||||
|
await saveResearchResult('search_depth_python_basic', basicResult);
|
||||||
|
await saveResearchResult('search_depth_python_advanced', advancedResult);
|
||||||
|
|
||||||
expect(basicResult.answer).toBeTruthy();
|
expect(basicResult.answer).toBeTruthy();
|
||||||
expect(advancedResult.answer).toBeTruthy();
|
expect(advancedResult.answer).toBeTruthy();
|
||||||
|
|
||||||
@@ -165,6 +193,28 @@ tap.test('Anthropic Research: should handle different search depths', async () =
|
|||||||
expect(advancedResult.answer.toLowerCase()).toInclude('python');
|
expect(advancedResult.answer.toLowerCase()).toInclude('python');
|
||||||
});
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Research: ARM vs. Qualcomm comparison', async () => {
|
||||||
|
const result = await anthropicProvider.research({
|
||||||
|
query: 'Compare ARM and Qualcomm: their technologies, market positions, and recent developments in the mobile and computing sectors',
|
||||||
|
searchDepth: 'advanced',
|
||||||
|
includeWebSearch: true,
|
||||||
|
maxSources: 10
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log('ARM vs. Qualcomm Research:');
|
||||||
|
console.log('- Answer length:', result.answer.length);
|
||||||
|
console.log('- Sources found:', result.sources.length);
|
||||||
|
console.log('- First 300 chars:', result.answer.substring(0, 300));
|
||||||
|
|
||||||
|
await saveResearchResult('arm_vs_qualcomm_comparison', result);
|
||||||
|
|
||||||
|
expect(result.answer).toBeTruthy();
|
||||||
|
expect(result.answer.length).toBeGreaterThan(500);
|
||||||
|
expect(result.answer.toLowerCase()).toInclude('arm');
|
||||||
|
expect(result.answer.toLowerCase()).toInclude('qualcomm');
|
||||||
|
expect(result.sources.length).toBeGreaterThan(0);
|
||||||
|
});
|
||||||
|
|
||||||
tap.test('Anthropic Research: should clean up provider', async () => {
|
tap.test('Anthropic Research: should clean up provider', async () => {
|
||||||
await anthropicProvider.stop();
|
await anthropicProvider.stop();
|
||||||
console.log('Anthropic research provider stopped successfully');
|
console.log('Anthropic research provider stopped successfully');
|
||||||
|
|||||||
@@ -1,9 +1,24 @@
|
|||||||
import { expect, tap } from '@push.rocks/tapbundle';
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
import * as qenv from '@push.rocks/qenv';
|
import * as qenv from '@push.rocks/qenv';
|
||||||
import * as smartai from '../ts/index.js';
|
import * as smartai from '../ts/index.js';
|
||||||
|
import * as path from 'path';
|
||||||
|
import { promises as fs } from 'fs';
|
||||||
|
|
||||||
const testQenv = new qenv.Qenv('./', './.nogit/');
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
// Helper function to save research results
|
||||||
|
async function saveResearchResult(testName: string, result: any) {
|
||||||
|
const sanitizedName = testName.replace(/[^a-z0-9]/gi, '_').toLowerCase();
|
||||||
|
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
|
||||||
|
const filename = `openai_${sanitizedName}_${timestamp}.json`;
|
||||||
|
const filepath = path.join('.nogit', 'testresults', 'research', filename);
|
||||||
|
|
||||||
|
await fs.mkdir(path.dirname(filepath), { recursive: true });
|
||||||
|
await fs.writeFile(filepath, JSON.stringify(result, null, 2), 'utf-8');
|
||||||
|
|
||||||
|
console.log(` 💾 Saved to: ${filepath}`);
|
||||||
|
}
|
||||||
|
|
||||||
let openaiProvider: smartai.OpenAiProvider;
|
let openaiProvider: smartai.OpenAiProvider;
|
||||||
|
|
||||||
tap.test('OpenAI Research: should initialize provider with research capabilities', async () => {
|
tap.test('OpenAI Research: should initialize provider with research capabilities', async () => {
|
||||||
@@ -29,6 +44,8 @@ tap.test('OpenAI Research: should perform basic research query', async () => {
|
|||||||
console.log('- Sources found:', result.sources.length);
|
console.log('- Sources found:', result.sources.length);
|
||||||
console.log('- First 200 chars:', result.answer.substring(0, 200));
|
console.log('- First 200 chars:', result.answer.substring(0, 200));
|
||||||
|
|
||||||
|
await saveResearchResult('basic_research_typescript', result);
|
||||||
|
|
||||||
expect(result).toBeTruthy();
|
expect(result).toBeTruthy();
|
||||||
expect(result.answer).toBeTruthy();
|
expect(result.answer).toBeTruthy();
|
||||||
expect(result.answer.toLowerCase()).toInclude('typescript');
|
expect(result.answer.toLowerCase()).toInclude('typescript');
|
||||||
@@ -52,6 +69,8 @@ tap.test('OpenAI Research: should perform research with web search enabled', asy
|
|||||||
console.log('- Search queries used:', result.searchQueries);
|
console.log('- Search queries used:', result.searchQueries);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
await saveResearchResult('web_search_ecmascript', result);
|
||||||
|
|
||||||
expect(result.answer).toBeTruthy();
|
expect(result.answer).toBeTruthy();
|
||||||
expect(result.answer.toLowerCase()).toInclude('ecmascript');
|
expect(result.answer.toLowerCase()).toInclude('ecmascript');
|
||||||
|
|
||||||
@@ -98,6 +117,8 @@ tap.test('OpenAI Research: should extract sources from markdown links', async ()
|
|||||||
console.log('OpenAI Source Extraction:');
|
console.log('OpenAI Source Extraction:');
|
||||||
console.log('- Sources found:', result.sources.length);
|
console.log('- Sources found:', result.sources.length);
|
||||||
|
|
||||||
|
await saveResearchResult('source_extraction_nodejs', result);
|
||||||
|
|
||||||
if (result.sources.length > 0) {
|
if (result.sources.length > 0) {
|
||||||
console.log('- Example source:', result.sources[0]);
|
console.log('- Example source:', result.sources[0]);
|
||||||
expect(result.sources[0].url).toBeTruthy();
|
expect(result.sources[0].url).toBeTruthy();
|
||||||
|
|||||||
151
test/test.thinking.anthropic.ts
Normal file
151
test/test.thinking.anthropic.ts
Normal file
@@ -0,0 +1,151 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let anthropicProviderQuick: smartai.AnthropicProvider;
|
||||||
|
let anthropicProviderNormal: smartai.AnthropicProvider;
|
||||||
|
let anthropicProviderDeep: smartai.AnthropicProvider;
|
||||||
|
let anthropicProviderOff: smartai.AnthropicProvider;
|
||||||
|
|
||||||
|
// Test 'quick' mode
|
||||||
|
tap.test('Extended Thinking: should create Anthropic provider with quick mode', async () => {
|
||||||
|
anthropicProviderQuick = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
extendedThinking: 'quick',
|
||||||
|
});
|
||||||
|
await anthropicProviderQuick.start();
|
||||||
|
expect(anthropicProviderQuick).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should chat with quick mode (2048 tokens)', async () => {
|
||||||
|
const userMessage = 'Explain quantum entanglement in simple terms.';
|
||||||
|
const response = await anthropicProviderQuick.chat({
|
||||||
|
systemMessage: 'You are a helpful physics teacher.',
|
||||||
|
userMessage: userMessage,
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
console.log(`Quick Mode - User: ${userMessage}`);
|
||||||
|
console.log(`Quick Mode - Response length: ${response.message.length} chars`);
|
||||||
|
expect(response.role).toEqual('assistant');
|
||||||
|
expect(response.message).toBeTruthy();
|
||||||
|
expect(response.message.toLowerCase()).toInclude('quantum');
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should stop quick mode provider', async () => {
|
||||||
|
await anthropicProviderQuick.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
// Test 'normal' mode (default)
|
||||||
|
tap.test('Extended Thinking: should create Anthropic provider with normal mode (default)', async () => {
|
||||||
|
anthropicProviderNormal = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
// extendedThinking not specified, should default to 'normal'
|
||||||
|
});
|
||||||
|
await anthropicProviderNormal.start();
|
||||||
|
expect(anthropicProviderNormal).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should chat with normal mode (8000 tokens default)', async () => {
|
||||||
|
const userMessage = 'What are the implications of the P vs NP problem?';
|
||||||
|
const response = await anthropicProviderNormal.chat({
|
||||||
|
systemMessage: 'You are a helpful computer science expert.',
|
||||||
|
userMessage: userMessage,
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
console.log(`Normal Mode - User: ${userMessage}`);
|
||||||
|
console.log(`Normal Mode - Response length: ${response.message.length} chars`);
|
||||||
|
expect(response.role).toEqual('assistant');
|
||||||
|
expect(response.message).toBeTruthy();
|
||||||
|
expect(response.message.length).toBeGreaterThan(50);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should stop normal mode provider', async () => {
|
||||||
|
await anthropicProviderNormal.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
// Test 'deep' mode
|
||||||
|
tap.test('Extended Thinking: should create Anthropic provider with deep mode', async () => {
|
||||||
|
anthropicProviderDeep = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
extendedThinking: 'deep',
|
||||||
|
});
|
||||||
|
await anthropicProviderDeep.start();
|
||||||
|
expect(anthropicProviderDeep).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should chat with deep mode (16000 tokens)', async () => {
|
||||||
|
const userMessage = 'Analyze the philosophical implications of artificial consciousness.';
|
||||||
|
const response = await anthropicProviderDeep.chat({
|
||||||
|
systemMessage: 'You are a philosopher and cognitive scientist.',
|
||||||
|
userMessage: userMessage,
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
console.log(`Deep Mode - User: ${userMessage}`);
|
||||||
|
console.log(`Deep Mode - Response length: ${response.message.length} chars`);
|
||||||
|
expect(response.role).toEqual('assistant');
|
||||||
|
expect(response.message).toBeTruthy();
|
||||||
|
expect(response.message.length).toBeGreaterThan(100);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should stop deep mode provider', async () => {
|
||||||
|
await anthropicProviderDeep.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
// Test 'off' mode
|
||||||
|
tap.test('Extended Thinking: should create Anthropic provider with thinking disabled', async () => {
|
||||||
|
anthropicProviderOff = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
extendedThinking: 'off',
|
||||||
|
});
|
||||||
|
await anthropicProviderOff.start();
|
||||||
|
expect(anthropicProviderOff).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should chat with thinking disabled', async () => {
|
||||||
|
const userMessage = 'What is 2 + 2?';
|
||||||
|
const response = await anthropicProviderOff.chat({
|
||||||
|
systemMessage: 'You are a helpful assistant.',
|
||||||
|
userMessage: userMessage,
|
||||||
|
messageHistory: [],
|
||||||
|
});
|
||||||
|
console.log(`Thinking Off - User: ${userMessage}`);
|
||||||
|
console.log(`Thinking Off - Response: ${response.message}`);
|
||||||
|
expect(response.role).toEqual('assistant');
|
||||||
|
expect(response.message).toBeTruthy();
|
||||||
|
expect(response.message).toInclude('4');
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Extended Thinking: should stop off mode provider', async () => {
|
||||||
|
await anthropicProviderOff.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
// Test with vision method
|
||||||
|
tap.test('Extended Thinking: should work with vision method', async () => {
|
||||||
|
const provider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
extendedThinking: 'normal',
|
||||||
|
});
|
||||||
|
await provider.start();
|
||||||
|
|
||||||
|
// Create a simple test image (1x1 red pixel PNG)
|
||||||
|
const redPixelPng = Buffer.from(
|
||||||
|
'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8DwHwAFBQIAX8jx0gAAAABJRU5ErkJggg==',
|
||||||
|
'base64'
|
||||||
|
);
|
||||||
|
|
||||||
|
const response = await provider.vision({
|
||||||
|
image: redPixelPng,
|
||||||
|
prompt: 'What color is this image?',
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Vision with Thinking - Response: ${response}`);
|
||||||
|
expect(response).toBeTruthy();
|
||||||
|
expect(response.toLowerCase()).toInclude('red');
|
||||||
|
|
||||||
|
await provider.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
95
test/test.vision.anthropic.ts
Normal file
95
test/test.vision.anthropic.ts
Normal file
@@ -0,0 +1,95 @@
|
|||||||
|
import { expect, tap } from '@push.rocks/tapbundle';
|
||||||
|
import * as qenv from '@push.rocks/qenv';
|
||||||
|
import * as smartfile from '@push.rocks/smartfile';
|
||||||
|
|
||||||
|
const testQenv = new qenv.Qenv('./', './.nogit/');
|
||||||
|
|
||||||
|
import * as smartai from '../ts/index.js';
|
||||||
|
|
||||||
|
let anthropicProvider: smartai.AnthropicProvider;
|
||||||
|
|
||||||
|
tap.test('Anthropic Vision: should create and start Anthropic provider', async () => {
|
||||||
|
anthropicProvider = new smartai.AnthropicProvider({
|
||||||
|
anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
|
||||||
|
});
|
||||||
|
await anthropicProvider.start();
|
||||||
|
expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Vision: should analyze coffee image with latte art', async () => {
|
||||||
|
// Test 1: Coffee image from Unsplash by Dani
|
||||||
|
const imagePath = './test/testimages/coffee-dani/coffee.jpg';
|
||||||
|
console.log(`Loading coffee image from: ${imagePath}`);
|
||||||
|
|
||||||
|
const imageBuffer = await smartfile.fs.toBuffer(imagePath);
|
||||||
|
console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
|
||||||
|
|
||||||
|
const result = await anthropicProvider.vision({
|
||||||
|
image: imageBuffer,
|
||||||
|
prompt: 'Describe this coffee image. What do you see in terms of the cup, foam pattern, and overall composition?'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Anthropic Vision (Coffee) - Result: ${result}`);
|
||||||
|
expect(result).toBeTruthy();
|
||||||
|
expect(typeof result).toEqual('string');
|
||||||
|
expect(result.toLowerCase()).toInclude('coffee');
|
||||||
|
// The image has a heart pattern in the latte art
|
||||||
|
const mentionsLatte = result.toLowerCase().includes('heart') ||
|
||||||
|
result.toLowerCase().includes('latte') ||
|
||||||
|
result.toLowerCase().includes('foam');
|
||||||
|
expect(mentionsLatte).toBeTrue();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Vision: should analyze laptop/workspace image', async () => {
|
||||||
|
// Test 2: Laptop image from Unsplash by Nicolas Bichon
|
||||||
|
const imagePath = './test/testimages/laptop-nicolas/laptop.jpg';
|
||||||
|
console.log(`Loading laptop image from: ${imagePath}`);
|
||||||
|
|
||||||
|
const imageBuffer = await smartfile.fs.toBuffer(imagePath);
|
||||||
|
console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
|
||||||
|
|
||||||
|
const result = await anthropicProvider.vision({
|
||||||
|
image: imageBuffer,
|
||||||
|
prompt: 'Describe the technology and workspace setup in this image. What devices and equipment can you see?'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Anthropic Vision (Laptop) - Result: ${result}`);
|
||||||
|
expect(result).toBeTruthy();
|
||||||
|
expect(typeof result).toEqual('string');
|
||||||
|
// Should mention laptop, computer, keyboard, or desk
|
||||||
|
const mentionsTech = result.toLowerCase().includes('laptop') ||
|
||||||
|
result.toLowerCase().includes('computer') ||
|
||||||
|
result.toLowerCase().includes('keyboard') ||
|
||||||
|
result.toLowerCase().includes('desk');
|
||||||
|
expect(mentionsTech).toBeTrue();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Vision: should analyze receipt/document image', async () => {
|
||||||
|
// Test 3: Receipt image from Unsplash by Annie Spratt
|
||||||
|
const imagePath = './test/testimages/receipt-annie/receipt.jpg';
|
||||||
|
console.log(`Loading receipt image from: ${imagePath}`);
|
||||||
|
|
||||||
|
const imageBuffer = await smartfile.fs.toBuffer(imagePath);
|
||||||
|
console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
|
||||||
|
|
||||||
|
const result = await anthropicProvider.vision({
|
||||||
|
image: imageBuffer,
|
||||||
|
prompt: 'What type of document is this? Can you identify any text or numbers visible in the image?'
|
||||||
|
});
|
||||||
|
|
||||||
|
console.log(`Anthropic Vision (Receipt) - Result: ${result}`);
|
||||||
|
expect(result).toBeTruthy();
|
||||||
|
expect(typeof result).toEqual('string');
|
||||||
|
// Should mention receipt, document, text, or paper
|
||||||
|
const mentionsDocument = result.toLowerCase().includes('receipt') ||
|
||||||
|
result.toLowerCase().includes('document') ||
|
||||||
|
result.toLowerCase().includes('text') ||
|
||||||
|
result.toLowerCase().includes('paper');
|
||||||
|
expect(mentionsDocument).toBeTrue();
|
||||||
|
});
|
||||||
|
|
||||||
|
tap.test('Anthropic Vision: should stop the provider', async () => {
|
||||||
|
await anthropicProvider.stop();
|
||||||
|
});
|
||||||
|
|
||||||
|
export default tap.start();
|
||||||
36
test/testimages/coffee-dani/README.md
Normal file
36
test/testimages/coffee-dani/README.md
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
# Coffee Image Attribution
|
||||||
|
|
||||||
|
## coffee.jpg
|
||||||
|
|
||||||
|
**Photographer:** Dani (@frokz)
|
||||||
|
**Source URL:** https://unsplash.com/photos/cup-of-coffee-on-saucer-ZLqxSzvVr7I
|
||||||
|
**Direct Link:** https://images.unsplash.com/photo-1506372023823-741c83b836fe
|
||||||
|
|
||||||
|
### Metadata
|
||||||
|
- **Title:** Cup of coffee on saucer
|
||||||
|
- **Description:** One of many coffee-moments in my life ;)
|
||||||
|
- **Date Published:** September 25, 2017
|
||||||
|
- **Location:** Stockholm, Sweden
|
||||||
|
- **Tags:** coffee, cafe, heart, coffee cup, cup, barista, latte, mug, saucer, food, sweden, stockholm
|
||||||
|
|
||||||
|
### License
|
||||||
|
**Unsplash License** - Free to use
|
||||||
|
- ✅ Commercial and non-commercial use
|
||||||
|
- ✅ No permission needed
|
||||||
|
- ❌ Cannot be sold without significant modification
|
||||||
|
- ❌ Cannot be used to replicate Unsplash or similar service
|
||||||
|
|
||||||
|
Full license: https://unsplash.com/license
|
||||||
|
|
||||||
|
### Usage in This Project
|
||||||
|
This image is used for testing vision/image processing capabilities in the SmartAI library test suite, specifically for:
|
||||||
|
- Testing coffee/beverage recognition
|
||||||
|
- Latte art pattern detection (heart shape)
|
||||||
|
- Scene/environment analysis
|
||||||
|
- Multi-element image understanding (cup, saucer, table)
|
||||||
|
|
||||||
|
### Download Information
|
||||||
|
- **Downloaded:** September 28, 2025
|
||||||
|
- **Original Filename:** dani-ZLqxSzvVr7I-unsplash.jpg
|
||||||
|
- **Resolution:** High resolution (3.7 MB)
|
||||||
|
- **Format:** JPEG
|
||||||
BIN
test/testimages/coffee-dani/coffee.jpg
Normal file
BIN
test/testimages/coffee-dani/coffee.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 3.7 MiB |
40
test/testimages/laptop-nicolas/README.md
Normal file
40
test/testimages/laptop-nicolas/README.md
Normal file
@@ -0,0 +1,40 @@
|
|||||||
|
# Laptop Image Attribution
|
||||||
|
|
||||||
|
## laptop.jpg
|
||||||
|
|
||||||
|
**Photographer:** Nicolas Bichon (@nicol3a)
|
||||||
|
**Source URL:** https://unsplash.com/photos/a-laptop-computer-sitting-on-top-of-a-wooden-desk-ZhV4iqAXxyA
|
||||||
|
**Direct Link:** https://images.unsplash.com/photo-1704230972797-e0e3aba0fce7
|
||||||
|
|
||||||
|
### Metadata
|
||||||
|
- **Title:** A laptop computer sitting on top of a wooden desk
|
||||||
|
- **Description:** Lifestyle photo I took for my indie app Type, a macOS app to take notes without interrupting your flow. https://usetype.app.
|
||||||
|
- **Date Published:** January 2, 2024
|
||||||
|
- **Camera:** FUJIFILM, X-T20
|
||||||
|
- **Tags:** computer, laptop, mac, keyboard, computer keyboard, computer hardware, furniture, table, electronics, screen, monitor, hardware, display, tabletop, lcd screen, digital display
|
||||||
|
|
||||||
|
### Statistics
|
||||||
|
- **Views:** 183,020
|
||||||
|
- **Downloads:** 757
|
||||||
|
|
||||||
|
### License
|
||||||
|
**Unsplash License** - Free to use
|
||||||
|
- ✅ Commercial and non-commercial use
|
||||||
|
- ✅ No permission needed
|
||||||
|
- ❌ Cannot be sold without significant modification
|
||||||
|
- ❌ Cannot be used to replicate Unsplash or similar service
|
||||||
|
|
||||||
|
Full license: https://unsplash.com/license
|
||||||
|
|
||||||
|
### Usage in This Project
|
||||||
|
This image is used for testing vision/image processing capabilities in the SmartAI library test suite, specifically for:
|
||||||
|
- Testing technology/computer equipment recognition
|
||||||
|
- Workspace/office environment analysis
|
||||||
|
- Object detection (laptop, keyboard, monitor, table)
|
||||||
|
- Scene understanding and context analysis
|
||||||
|
|
||||||
|
### Download Information
|
||||||
|
- **Downloaded:** September 28, 2025
|
||||||
|
- **Original Filename:** nicolas-bichon-ZhV4iqAXxyA-unsplash.jpg
|
||||||
|
- **Resolution:** High resolution (1.8 MB)
|
||||||
|
- **Format:** JPEG
|
||||||
BIN
test/testimages/laptop-nicolas/laptop.jpg
Normal file
BIN
test/testimages/laptop-nicolas/laptop.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.8 MiB |
40
test/testimages/receipt-annie/README.md
Normal file
40
test/testimages/receipt-annie/README.md
Normal file
@@ -0,0 +1,40 @@
|
|||||||
|
# Receipt Image Attribution
|
||||||
|
|
||||||
|
## receipt.jpg
|
||||||
|
|
||||||
|
**Photographer:** Annie Spratt (@anniespratt)
|
||||||
|
**Source URL:** https://unsplash.com/photos/a-receipt-sitting-on-top-of-a-wooden-table-recgFWxDO1Y
|
||||||
|
**Direct Link:** https://images.unsplash.com/photo-1731686602391-7484df33a03c
|
||||||
|
|
||||||
|
### Metadata
|
||||||
|
- **Title:** A receipt sitting on top of a wooden table
|
||||||
|
- **Description:** Download this free HD photo of text, document, invoice, and receipt by Annie Spratt
|
||||||
|
- **Date Published:** November 15, 2024
|
||||||
|
- **Tags:** text, document, invoice, receipt, diaper
|
||||||
|
|
||||||
|
### Statistics
|
||||||
|
- **Views:** 54,593
|
||||||
|
- **Downloads:** 764
|
||||||
|
|
||||||
|
### License
|
||||||
|
**Unsplash License** - Free to use
|
||||||
|
- ✅ Commercial and non-commercial use
|
||||||
|
- ✅ No permission needed
|
||||||
|
- ❌ Cannot be sold without significant modification
|
||||||
|
- ❌ Cannot be used to replicate Unsplash or similar service
|
||||||
|
|
||||||
|
Full license: https://unsplash.com/license
|
||||||
|
|
||||||
|
### Usage in This Project
|
||||||
|
This image is used for testing vision/image processing capabilities in the SmartAI library test suite, specifically for:
|
||||||
|
- Testing text extraction and OCR capabilities
|
||||||
|
- Document recognition and classification
|
||||||
|
- Receipt/invoice analysis
|
||||||
|
- Text-heavy image understanding
|
||||||
|
- Structured data extraction from documents
|
||||||
|
|
||||||
|
### Download Information
|
||||||
|
- **Downloaded:** September 28, 2025
|
||||||
|
- **Original Filename:** annie-spratt-recgFWxDO1Y-unsplash.jpg
|
||||||
|
- **Resolution:** High resolution (3.3 MB)
|
||||||
|
- **Format:** JPEG
|
||||||
BIN
test/testimages/receipt-annie/receipt.jpg
Normal file
BIN
test/testimages/receipt-annie/receipt.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 3.3 MiB |
@@ -3,6 +3,6 @@
|
|||||||
*/
|
*/
|
||||||
export const commitinfo = {
|
export const commitinfo = {
|
||||||
name: '@push.rocks/smartai',
|
name: '@push.rocks/smartai',
|
||||||
version: '0.6.1',
|
version: '0.8.0',
|
||||||
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.'
|
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.'
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -50,6 +50,60 @@ export interface ResearchResponse {
|
|||||||
metadata?: any;
|
metadata?: any;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Options for image generation
|
||||||
|
*/
|
||||||
|
export interface ImageGenerateOptions {
|
||||||
|
prompt: string;
|
||||||
|
model?: 'gpt-image-1' | 'dall-e-3' | 'dall-e-2';
|
||||||
|
quality?: 'low' | 'medium' | 'high' | 'standard' | 'hd' | 'auto';
|
||||||
|
size?: '256x256' | '512x512' | '1024x1024' | '1536x1024' | '1024x1536' | '1792x1024' | '1024x1792' | 'auto';
|
||||||
|
style?: 'vivid' | 'natural';
|
||||||
|
background?: 'transparent' | 'opaque' | 'auto';
|
||||||
|
outputFormat?: 'png' | 'jpeg' | 'webp';
|
||||||
|
outputCompression?: number; // 0-100 for webp/jpeg
|
||||||
|
moderation?: 'low' | 'auto';
|
||||||
|
n?: number; // Number of images to generate
|
||||||
|
stream?: boolean;
|
||||||
|
partialImages?: number; // 0-3 for streaming
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Options for image editing
|
||||||
|
*/
|
||||||
|
export interface ImageEditOptions {
|
||||||
|
image: Buffer;
|
||||||
|
prompt: string;
|
||||||
|
mask?: Buffer;
|
||||||
|
model?: 'gpt-image-1' | 'dall-e-2';
|
||||||
|
quality?: 'low' | 'medium' | 'high' | 'standard' | 'auto';
|
||||||
|
size?: '256x256' | '512x512' | '1024x1024' | '1536x1024' | '1024x1536' | 'auto';
|
||||||
|
background?: 'transparent' | 'opaque' | 'auto';
|
||||||
|
outputFormat?: 'png' | 'jpeg' | 'webp';
|
||||||
|
outputCompression?: number;
|
||||||
|
n?: number;
|
||||||
|
stream?: boolean;
|
||||||
|
partialImages?: number;
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Response format for image operations
|
||||||
|
*/
|
||||||
|
export interface ImageResponse {
|
||||||
|
images: Array<{
|
||||||
|
b64_json?: string;
|
||||||
|
url?: string;
|
||||||
|
revisedPrompt?: string;
|
||||||
|
}>;
|
||||||
|
metadata?: {
|
||||||
|
model: string;
|
||||||
|
quality?: string;
|
||||||
|
size?: string;
|
||||||
|
outputFormat?: string;
|
||||||
|
tokensUsed?: number;
|
||||||
|
};
|
||||||
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Abstract base class for multi-modal AI models.
|
* Abstract base class for multi-modal AI models.
|
||||||
* Provides a common interface for different AI providers (OpenAI, Anthropic, Perplexity, Ollama)
|
* Provides a common interface for different AI providers (OpenAI, Anthropic, Perplexity, Ollama)
|
||||||
@@ -57,19 +111,30 @@ export interface ResearchResponse {
|
|||||||
export abstract class MultiModalModel {
|
export abstract class MultiModalModel {
|
||||||
/**
|
/**
|
||||||
* SmartPdf instance for document processing
|
* SmartPdf instance for document processing
|
||||||
* Shared across all methods that need PDF functionality
|
* Lazy-loaded only when PDF processing is needed to avoid starting browser unnecessarily
|
||||||
*/
|
*/
|
||||||
protected smartpdfInstance: plugins.smartpdf.SmartPdf;
|
protected smartpdfInstance: plugins.smartpdf.SmartPdf | null = null;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Ensures SmartPdf instance is initialized and ready
|
||||||
|
* Call this before using smartpdfInstance in document processing methods
|
||||||
|
*/
|
||||||
|
protected async ensureSmartpdfReady(): Promise<void> {
|
||||||
|
if (!this.smartpdfInstance) {
|
||||||
|
this.smartpdfInstance = new plugins.smartpdf.SmartPdf();
|
||||||
|
await this.smartpdfInstance.start();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Initializes the model and any necessary resources
|
* Initializes the model and any necessary resources
|
||||||
* Should be called before using any other methods
|
* Should be called before using any other methods
|
||||||
*/
|
*/
|
||||||
public async start(): Promise<void> {
|
public async start(): Promise<void> {
|
||||||
this.smartpdfInstance = new plugins.smartpdf.SmartPdf();
|
// SmartPdf is now lazy-loaded only when needed for PDF processing
|
||||||
await this.smartpdfInstance.start();
|
// This avoids starting a browser unless document() method is actually used
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Cleans up any resources used by the model
|
* Cleans up any resources used by the model
|
||||||
* Should be called when the model is no longer needed
|
* Should be called when the model is no longer needed
|
||||||
@@ -77,6 +142,7 @@ export abstract class MultiModalModel {
|
|||||||
public async stop(): Promise<void> {
|
public async stop(): Promise<void> {
|
||||||
if (this.smartpdfInstance) {
|
if (this.smartpdfInstance) {
|
||||||
await this.smartpdfInstance.stop();
|
await this.smartpdfInstance.stop();
|
||||||
|
this.smartpdfInstance = null;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -131,4 +197,20 @@ export abstract class MultiModalModel {
|
|||||||
* @throws Error if the provider doesn't support research capabilities
|
* @throws Error if the provider doesn't support research capabilities
|
||||||
*/
|
*/
|
||||||
public abstract research(optionsArg: ResearchOptions): Promise<ResearchResponse>;
|
public abstract research(optionsArg: ResearchOptions): Promise<ResearchResponse>;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation from text prompts
|
||||||
|
* @param optionsArg Options containing the prompt and generation parameters
|
||||||
|
* @returns Promise resolving to the generated image(s)
|
||||||
|
* @throws Error if the provider doesn't support image generation
|
||||||
|
*/
|
||||||
|
public abstract imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse>;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing and inpainting
|
||||||
|
* @param optionsArg Options containing the image, prompt, and editing parameters
|
||||||
|
* @returns Promise resolving to the edited image(s)
|
||||||
|
* @throws Error if the provider doesn't support image editing
|
||||||
|
*/
|
||||||
|
public abstract imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse>;
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -96,6 +96,18 @@ export class Conversation {
|
|||||||
return conversation;
|
return conversation;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public static async createWithElevenlabs(smartaiRefArg: SmartAi) {
|
||||||
|
if (!smartaiRefArg.elevenlabsProvider) {
|
||||||
|
throw new Error('ElevenLabs provider not available');
|
||||||
|
}
|
||||||
|
const conversation = new Conversation(smartaiRefArg, {
|
||||||
|
processFunction: async (input) => {
|
||||||
|
return '' // TODO implement proper streaming
|
||||||
|
}
|
||||||
|
});
|
||||||
|
return conversation;
|
||||||
|
}
|
||||||
|
|
||||||
// INSTANCE
|
// INSTANCE
|
||||||
smartaiRef: SmartAi
|
smartaiRef: SmartAi
|
||||||
private systemMessage: string;
|
private systemMessage: string;
|
||||||
|
|||||||
@@ -1,6 +1,7 @@
|
|||||||
import { Conversation } from './classes.conversation.js';
|
import { Conversation } from './classes.conversation.js';
|
||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import { AnthropicProvider } from './provider.anthropic.js';
|
import { AnthropicProvider } from './provider.anthropic.js';
|
||||||
|
import { ElevenLabsProvider } from './provider.elevenlabs.js';
|
||||||
import { OllamaProvider } from './provider.ollama.js';
|
import { OllamaProvider } from './provider.ollama.js';
|
||||||
import { OpenAiProvider } from './provider.openai.js';
|
import { OpenAiProvider } from './provider.openai.js';
|
||||||
import { PerplexityProvider } from './provider.perplexity.js';
|
import { PerplexityProvider } from './provider.perplexity.js';
|
||||||
@@ -15,6 +16,7 @@ export interface ISmartAiOptions {
|
|||||||
perplexityToken?: string;
|
perplexityToken?: string;
|
||||||
groqToken?: string;
|
groqToken?: string;
|
||||||
xaiToken?: string;
|
xaiToken?: string;
|
||||||
|
elevenlabsToken?: string;
|
||||||
exo?: {
|
exo?: {
|
||||||
baseUrl?: string;
|
baseUrl?: string;
|
||||||
apiKey?: string;
|
apiKey?: string;
|
||||||
@@ -24,9 +26,13 @@ export interface ISmartAiOptions {
|
|||||||
model?: string;
|
model?: string;
|
||||||
visionModel?: string;
|
visionModel?: string;
|
||||||
};
|
};
|
||||||
|
elevenlabs?: {
|
||||||
|
defaultVoiceId?: string;
|
||||||
|
defaultModelId?: string;
|
||||||
|
};
|
||||||
}
|
}
|
||||||
|
|
||||||
export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama' | 'exo' | 'groq' | 'xai';
|
export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama' | 'exo' | 'groq' | 'xai' | 'elevenlabs';
|
||||||
|
|
||||||
export class SmartAi {
|
export class SmartAi {
|
||||||
public options: ISmartAiOptions;
|
public options: ISmartAiOptions;
|
||||||
@@ -38,6 +44,7 @@ export class SmartAi {
|
|||||||
public exoProvider: ExoProvider;
|
public exoProvider: ExoProvider;
|
||||||
public groqProvider: GroqProvider;
|
public groqProvider: GroqProvider;
|
||||||
public xaiProvider: XAIProvider;
|
public xaiProvider: XAIProvider;
|
||||||
|
public elevenlabsProvider: ElevenLabsProvider;
|
||||||
|
|
||||||
constructor(optionsArg: ISmartAiOptions) {
|
constructor(optionsArg: ISmartAiOptions) {
|
||||||
this.options = optionsArg;
|
this.options = optionsArg;
|
||||||
@@ -74,6 +81,14 @@ export class SmartAi {
|
|||||||
});
|
});
|
||||||
await this.xaiProvider.start();
|
await this.xaiProvider.start();
|
||||||
}
|
}
|
||||||
|
if (this.options.elevenlabsToken) {
|
||||||
|
this.elevenlabsProvider = new ElevenLabsProvider({
|
||||||
|
elevenlabsToken: this.options.elevenlabsToken,
|
||||||
|
defaultVoiceId: this.options.elevenlabs?.defaultVoiceId,
|
||||||
|
defaultModelId: this.options.elevenlabs?.defaultModelId,
|
||||||
|
});
|
||||||
|
await this.elevenlabsProvider.start();
|
||||||
|
}
|
||||||
if (this.options.ollama) {
|
if (this.options.ollama) {
|
||||||
this.ollamaProvider = new OllamaProvider({
|
this.ollamaProvider = new OllamaProvider({
|
||||||
baseUrl: this.options.ollama.baseUrl,
|
baseUrl: this.options.ollama.baseUrl,
|
||||||
@@ -107,6 +122,9 @@ export class SmartAi {
|
|||||||
if (this.xaiProvider) {
|
if (this.xaiProvider) {
|
||||||
await this.xaiProvider.stop();
|
await this.xaiProvider.stop();
|
||||||
}
|
}
|
||||||
|
if (this.elevenlabsProvider) {
|
||||||
|
await this.elevenlabsProvider.stop();
|
||||||
|
}
|
||||||
if (this.ollamaProvider) {
|
if (this.ollamaProvider) {
|
||||||
await this.ollamaProvider.stop();
|
await this.ollamaProvider.stop();
|
||||||
}
|
}
|
||||||
@@ -134,6 +152,8 @@ export class SmartAi {
|
|||||||
return Conversation.createWithGroq(this);
|
return Conversation.createWithGroq(this);
|
||||||
case 'xai':
|
case 'xai':
|
||||||
return Conversation.createWithXai(this);
|
return Conversation.createWithXai(this);
|
||||||
|
case 'elevenlabs':
|
||||||
|
return Conversation.createWithElevenlabs(this);
|
||||||
default:
|
default:
|
||||||
throw new Error('Provider not available');
|
throw new Error('Provider not available');
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -7,3 +7,4 @@ export * from './provider.groq.js';
|
|||||||
export * from './provider.ollama.js';
|
export * from './provider.ollama.js';
|
||||||
export * from './provider.xai.js';
|
export * from './provider.xai.js';
|
||||||
export * from './provider.exo.js';
|
export * from './provider.exo.js';
|
||||||
|
export * from './provider.elevenlabs.js';
|
||||||
|
|||||||
@@ -1,7 +1,16 @@
|
|||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import * as paths from './paths.js';
|
import * as paths from './paths.js';
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ChatOptions, ChatResponse, ChatMessage, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ChatMessage,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
import type { ImageBlockParam, TextBlockParam } from '@anthropic-ai/sdk/resources/messages';
|
import type { ImageBlockParam, TextBlockParam } from '@anthropic-ai/sdk/resources/messages';
|
||||||
|
|
||||||
type ContentBlock = ImageBlockParam | TextBlockParam;
|
type ContentBlock = ImageBlockParam | TextBlockParam;
|
||||||
@@ -11,6 +20,7 @@ export interface IAnthropicProviderOptions {
|
|||||||
enableWebSearch?: boolean;
|
enableWebSearch?: boolean;
|
||||||
searchDomainAllowList?: string[];
|
searchDomainAllowList?: string[];
|
||||||
searchDomainBlockList?: string[];
|
searchDomainBlockList?: string[];
|
||||||
|
extendedThinking?: 'quick' | 'normal' | 'deep' | 'off';
|
||||||
}
|
}
|
||||||
|
|
||||||
export class AnthropicProvider extends MultiModalModel {
|
export class AnthropicProvider extends MultiModalModel {
|
||||||
@@ -33,6 +43,25 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
await super.stop();
|
await super.stop();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Returns the thinking configuration based on provider options.
|
||||||
|
* Defaults to 'normal' mode (8000 tokens) if not specified.
|
||||||
|
*/
|
||||||
|
private getThinkingConfig(): { type: 'enabled'; budget_tokens: number } | undefined {
|
||||||
|
const mode = this.options.extendedThinking ?? 'normal';
|
||||||
|
|
||||||
|
const budgetMap = {
|
||||||
|
quick: 2048,
|
||||||
|
normal: 8000,
|
||||||
|
deep: 16000,
|
||||||
|
off: 0,
|
||||||
|
};
|
||||||
|
|
||||||
|
const budget = budgetMap[mode];
|
||||||
|
|
||||||
|
return budget > 0 ? { type: 'enabled', budget_tokens: budget } : undefined;
|
||||||
|
}
|
||||||
|
|
||||||
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||||
// Create a TextDecoder to handle incoming chunks
|
// Create a TextDecoder to handle incoming chunks
|
||||||
const decoder = new TextDecoder();
|
const decoder = new TextDecoder();
|
||||||
@@ -67,12 +96,14 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
|
|
||||||
// If we have a complete message, send it to Anthropic
|
// If we have a complete message, send it to Anthropic
|
||||||
if (currentMessage) {
|
if (currentMessage) {
|
||||||
|
const thinkingConfig = this.getThinkingConfig();
|
||||||
const stream = await this.anthropicApiClient.messages.create({
|
const stream = await this.anthropicApiClient.messages.create({
|
||||||
model: 'claude-3-opus-20240229',
|
model: 'claude-sonnet-4-5-20250929',
|
||||||
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
messages: [{ role: currentMessage.role, content: currentMessage.content }],
|
||||||
system: '',
|
system: '',
|
||||||
stream: true,
|
stream: true,
|
||||||
max_tokens: 4000,
|
max_tokens: 20000,
|
||||||
|
...(thinkingConfig && { thinking: thinkingConfig }),
|
||||||
});
|
});
|
||||||
|
|
||||||
// Process each chunk from Anthropic
|
// Process each chunk from Anthropic
|
||||||
@@ -111,14 +142,16 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
content: msg.content
|
content: msg.content
|
||||||
}));
|
}));
|
||||||
|
|
||||||
|
const thinkingConfig = this.getThinkingConfig();
|
||||||
const result = await this.anthropicApiClient.messages.create({
|
const result = await this.anthropicApiClient.messages.create({
|
||||||
model: 'claude-3-opus-20240229',
|
model: 'claude-sonnet-4-5-20250929',
|
||||||
system: optionsArg.systemMessage,
|
system: optionsArg.systemMessage,
|
||||||
messages: [
|
messages: [
|
||||||
...messages,
|
...messages,
|
||||||
{ role: 'user' as const, content: optionsArg.userMessage }
|
{ role: 'user' as const, content: optionsArg.userMessage }
|
||||||
],
|
],
|
||||||
max_tokens: 4000,
|
max_tokens: 20000,
|
||||||
|
...(thinkingConfig && { thinking: thinkingConfig }),
|
||||||
});
|
});
|
||||||
|
|
||||||
// Extract text content from the response
|
// Extract text content from the response
|
||||||
@@ -158,13 +191,15 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
}
|
}
|
||||||
];
|
];
|
||||||
|
|
||||||
|
const thinkingConfig = this.getThinkingConfig();
|
||||||
const result = await this.anthropicApiClient.messages.create({
|
const result = await this.anthropicApiClient.messages.create({
|
||||||
model: 'claude-3-opus-20240229',
|
model: 'claude-sonnet-4-5-20250929',
|
||||||
messages: [{
|
messages: [{
|
||||||
role: 'user',
|
role: 'user',
|
||||||
content
|
content
|
||||||
}],
|
}],
|
||||||
max_tokens: 1024
|
max_tokens: 10000,
|
||||||
|
...(thinkingConfig && { thinking: thinkingConfig }),
|
||||||
});
|
});
|
||||||
|
|
||||||
// Extract text content from the response
|
// Extract text content from the response
|
||||||
@@ -183,11 +218,14 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
pdfDocuments: Uint8Array[];
|
pdfDocuments: Uint8Array[];
|
||||||
messageHistory: ChatMessage[];
|
messageHistory: ChatMessage[];
|
||||||
}): Promise<{ message: any }> {
|
}): Promise<{ message: any }> {
|
||||||
|
// Ensure SmartPdf is initialized before processing documents
|
||||||
|
await this.ensureSmartpdfReady();
|
||||||
|
|
||||||
// Convert PDF documents to images using SmartPDF
|
// Convert PDF documents to images using SmartPDF
|
||||||
let documentImageBytesArray: Uint8Array[] = [];
|
let documentImageBytesArray: Uint8Array[] = [];
|
||||||
|
|
||||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
const documentImageArray = await this.smartpdfInstance!.convertPDFToPngBytes(pdfDocument);
|
||||||
documentImageBytesArray = documentImageBytesArray.concat(documentImageArray);
|
documentImageBytesArray = documentImageBytesArray.concat(documentImageArray);
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -211,20 +249,22 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
type: 'image',
|
type: 'image',
|
||||||
source: {
|
source: {
|
||||||
type: 'base64',
|
type: 'base64',
|
||||||
media_type: 'image/jpeg',
|
media_type: 'image/png',
|
||||||
data: Buffer.from(imageBytes).toString('base64')
|
data: Buffer.from(imageBytes).toString('base64')
|
||||||
}
|
}
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
|
const thinkingConfig = this.getThinkingConfig();
|
||||||
const result = await this.anthropicApiClient.messages.create({
|
const result = await this.anthropicApiClient.messages.create({
|
||||||
model: 'claude-3-opus-20240229',
|
model: 'claude-sonnet-4-5-20250929',
|
||||||
system: optionsArg.systemMessage,
|
system: optionsArg.systemMessage,
|
||||||
messages: [
|
messages: [
|
||||||
...messages,
|
...messages,
|
||||||
{ role: 'user', content }
|
{ role: 'user', content }
|
||||||
],
|
],
|
||||||
max_tokens: 4096
|
max_tokens: 20000,
|
||||||
|
...(thinkingConfig && { thinking: thinkingConfig }),
|
||||||
});
|
});
|
||||||
|
|
||||||
// Extract text content from the response
|
// Extract text content from the response
|
||||||
@@ -251,31 +291,35 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
|
|
||||||
try {
|
try {
|
||||||
// Build the tool configuration for web search
|
// Build the tool configuration for web search
|
||||||
const tools = this.options.enableWebSearch ? [
|
const tools: any[] = [];
|
||||||
{
|
|
||||||
type: 'web_search_20250305' as const,
|
if (this.options.enableWebSearch) {
|
||||||
name: 'web_search',
|
const webSearchTool: any = {
|
||||||
description: 'Search the web for current information',
|
type: 'web_search_20250305',
|
||||||
input_schema: {
|
name: 'web_search'
|
||||||
type: 'object' as const,
|
};
|
||||||
properties: {
|
|
||||||
query: {
|
// Add optional parameters
|
||||||
type: 'string',
|
if (optionsArg.maxSources) {
|
||||||
description: 'The search query'
|
webSearchTool.max_uses = optionsArg.maxSources;
|
||||||
}
|
|
||||||
},
|
|
||||||
required: ['query']
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
] : [];
|
|
||||||
|
if (this.options.searchDomainAllowList?.length) {
|
||||||
|
webSearchTool.allowed_domains = this.options.searchDomainAllowList;
|
||||||
|
} else if (this.options.searchDomainBlockList?.length) {
|
||||||
|
webSearchTool.blocked_domains = this.options.searchDomainBlockList;
|
||||||
|
}
|
||||||
|
|
||||||
|
tools.push(webSearchTool);
|
||||||
|
}
|
||||||
|
|
||||||
// Configure the request based on search depth
|
// Configure the request based on search depth
|
||||||
const maxTokens = optionsArg.searchDepth === 'deep' ? 8192 :
|
const maxTokens = optionsArg.searchDepth === 'deep' ? 20000 :
|
||||||
optionsArg.searchDepth === 'advanced' ? 6144 : 4096;
|
optionsArg.searchDepth === 'advanced' ? 20000 : 20000;
|
||||||
|
|
||||||
// Create the research request
|
// Create the research request
|
||||||
const requestParams: any = {
|
const requestParams: any = {
|
||||||
model: 'claude-3-opus-20240229',
|
model: 'claude-sonnet-4-5-20250929',
|
||||||
system: systemMessage,
|
system: systemMessage,
|
||||||
messages: [
|
messages: [
|
||||||
{
|
{
|
||||||
@@ -290,7 +334,12 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
// Add tools if web search is enabled
|
// Add tools if web search is enabled
|
||||||
if (tools.length > 0) {
|
if (tools.length > 0) {
|
||||||
requestParams.tools = tools;
|
requestParams.tools = tools;
|
||||||
requestParams.tool_choice = { type: 'auto' };
|
}
|
||||||
|
|
||||||
|
// Add thinking configuration if enabled
|
||||||
|
const thinkingConfig = this.getThinkingConfig();
|
||||||
|
if (thinkingConfig) {
|
||||||
|
requestParams.thinking = thinkingConfig;
|
||||||
}
|
}
|
||||||
|
|
||||||
// Execute the research request
|
// Execute the research request
|
||||||
@@ -304,54 +353,71 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
// Process content blocks
|
// Process content blocks
|
||||||
for (const block of result.content) {
|
for (const block of result.content) {
|
||||||
if ('text' in block) {
|
if ('text' in block) {
|
||||||
|
// Accumulate text content
|
||||||
answer += block.text;
|
answer += block.text;
|
||||||
|
|
||||||
|
// Extract citations if present
|
||||||
|
if ('citations' in block && Array.isArray(block.citations)) {
|
||||||
|
for (const citation of block.citations) {
|
||||||
|
if (citation.type === 'web_search_result_location') {
|
||||||
|
sources.push({
|
||||||
|
title: citation.title || '',
|
||||||
|
url: citation.url || '',
|
||||||
|
snippet: citation.cited_text || ''
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else if ('type' in block && block.type === 'server_tool_use') {
|
||||||
|
// Extract search queries from server tool use
|
||||||
|
if (block.name === 'web_search' && block.input && typeof block.input === 'object' && 'query' in block.input) {
|
||||||
|
searchQueries.push((block.input as any).query);
|
||||||
|
}
|
||||||
|
} else if ('type' in block && block.type === 'web_search_tool_result') {
|
||||||
|
// Extract sources from web search results
|
||||||
|
if (Array.isArray(block.content)) {
|
||||||
|
for (const result of block.content) {
|
||||||
|
if (result.type === 'web_search_result') {
|
||||||
|
// Only add if not already in sources (avoid duplicates from citations)
|
||||||
|
if (!sources.some(s => s.url === result.url)) {
|
||||||
|
sources.push({
|
||||||
|
title: result.title || '',
|
||||||
|
url: result.url || '',
|
||||||
|
snippet: '' // Search results don't include snippets, only citations do
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// Parse sources from the answer (Claude includes citations in various formats)
|
// Fallback: Parse markdown-style links if no citations found
|
||||||
const urlRegex = /\[([^\]]+)\]\(([^)]+)\)/g;
|
if (sources.length === 0) {
|
||||||
let match: RegExpExecArray | null;
|
const urlRegex = /\[([^\]]+)\]\(([^)]+)\)/g;
|
||||||
|
let match: RegExpExecArray | null;
|
||||||
|
|
||||||
while ((match = urlRegex.exec(answer)) !== null) {
|
while ((match = urlRegex.exec(answer)) !== null) {
|
||||||
sources.push({
|
|
||||||
title: match[1],
|
|
||||||
url: match[2],
|
|
||||||
snippet: ''
|
|
||||||
});
|
|
||||||
}
|
|
||||||
|
|
||||||
// Also look for plain URLs
|
|
||||||
const plainUrlRegex = /https?:\/\/[^\s\)]+/g;
|
|
||||||
const plainUrls = answer.match(plainUrlRegex) || [];
|
|
||||||
|
|
||||||
for (const url of plainUrls) {
|
|
||||||
// Check if this URL is already in sources
|
|
||||||
if (!sources.some(s => s.url === url)) {
|
|
||||||
sources.push({
|
sources.push({
|
||||||
title: new URL(url).hostname,
|
title: match[1],
|
||||||
url: url,
|
url: match[2],
|
||||||
snippet: ''
|
snippet: ''
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// Extract tool use information if available
|
// Check if web search was used based on usage info
|
||||||
if ('tool_use' in result && Array.isArray(result.tool_use)) {
|
const webSearchCount = result.usage?.server_tool_use?.web_search_requests || 0;
|
||||||
for (const toolUse of result.tool_use) {
|
|
||||||
if (toolUse.name === 'web_search' && toolUse.input?.query) {
|
|
||||||
searchQueries.push(toolUse.input.query);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
answer,
|
answer,
|
||||||
sources,
|
sources,
|
||||||
searchQueries: searchQueries.length > 0 ? searchQueries : undefined,
|
searchQueries: searchQueries.length > 0 ? searchQueries : undefined,
|
||||||
metadata: {
|
metadata: {
|
||||||
model: 'claude-3-opus-20240229',
|
model: 'claude-sonnet-4-5-20250929',
|
||||||
searchDepth: optionsArg.searchDepth || 'basic',
|
searchDepth: optionsArg.searchDepth || 'basic',
|
||||||
tokensUsed: result.usage?.output_tokens
|
tokensUsed: result.usage?.output_tokens,
|
||||||
|
webSearchesPerformed: webSearchCount
|
||||||
}
|
}
|
||||||
};
|
};
|
||||||
} catch (error) {
|
} catch (error) {
|
||||||
@@ -359,4 +425,18 @@ export class AnthropicProvider extends MultiModalModel {
|
|||||||
throw new Error(`Failed to perform research: ${error.message}`);
|
throw new Error(`Failed to perform research: ${error.message}`);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation is not supported by Anthropic
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image generation is not supported by Anthropic. Claude can only analyze images, not generate them. Please use OpenAI provider for image generation.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing is not supported by Anthropic
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image editing is not supported by Anthropic. Claude can only analyze images, not edit them. Please use OpenAI provider for image editing.');
|
||||||
|
}
|
||||||
}
|
}
|
||||||
114
ts/provider.elevenlabs.ts
Normal file
114
ts/provider.elevenlabs.ts
Normal file
@@ -0,0 +1,114 @@
|
|||||||
|
import * as plugins from './plugins.js';
|
||||||
|
|
||||||
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
|
|
||||||
|
export interface IElevenLabsProviderOptions {
|
||||||
|
elevenlabsToken: string;
|
||||||
|
defaultVoiceId?: string;
|
||||||
|
defaultModelId?: string;
|
||||||
|
}
|
||||||
|
|
||||||
|
export interface IElevenLabsVoiceSettings {
|
||||||
|
stability?: number;
|
||||||
|
similarity_boost?: number;
|
||||||
|
style?: number;
|
||||||
|
use_speaker_boost?: boolean;
|
||||||
|
}
|
||||||
|
|
||||||
|
export class ElevenLabsProvider extends MultiModalModel {
|
||||||
|
private options: IElevenLabsProviderOptions;
|
||||||
|
private baseUrl: string = 'https://api.elevenlabs.io/v1';
|
||||||
|
|
||||||
|
constructor(optionsArg: IElevenLabsProviderOptions) {
|
||||||
|
super();
|
||||||
|
this.options = optionsArg;
|
||||||
|
}
|
||||||
|
|
||||||
|
public async start() {
|
||||||
|
await super.start();
|
||||||
|
}
|
||||||
|
|
||||||
|
public async stop() {
|
||||||
|
await super.stop();
|
||||||
|
}
|
||||||
|
|
||||||
|
public async chat(optionsArg: ChatOptions): Promise<ChatResponse> {
|
||||||
|
throw new Error('ElevenLabs does not support chat functionality. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
|
||||||
|
public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
|
||||||
|
throw new Error('ElevenLabs does not support chat streaming functionality. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
|
||||||
|
public async audio(optionsArg: {
|
||||||
|
message: string;
|
||||||
|
voiceId?: string;
|
||||||
|
modelId?: string;
|
||||||
|
voiceSettings?: IElevenLabsVoiceSettings;
|
||||||
|
}): Promise<NodeJS.ReadableStream> {
|
||||||
|
// Use Samara voice as default fallback
|
||||||
|
const voiceId = optionsArg.voiceId || this.options.defaultVoiceId || '19STyYD15bswVz51nqLf';
|
||||||
|
|
||||||
|
const modelId = optionsArg.modelId || this.options.defaultModelId || 'eleven_v3';
|
||||||
|
|
||||||
|
const url = `${this.baseUrl}/text-to-speech/${voiceId}`;
|
||||||
|
|
||||||
|
const requestBody: any = {
|
||||||
|
text: optionsArg.message,
|
||||||
|
model_id: modelId,
|
||||||
|
};
|
||||||
|
|
||||||
|
if (optionsArg.voiceSettings) {
|
||||||
|
requestBody.voice_settings = optionsArg.voiceSettings;
|
||||||
|
}
|
||||||
|
|
||||||
|
const response = await plugins.smartrequest.SmartRequest.create()
|
||||||
|
.url(url)
|
||||||
|
.header('xi-api-key', this.options.elevenlabsToken)
|
||||||
|
.json(requestBody)
|
||||||
|
.autoDrain(false)
|
||||||
|
.post();
|
||||||
|
|
||||||
|
if (!response.ok) {
|
||||||
|
const errorText = await response.text();
|
||||||
|
throw new Error(`ElevenLabs API error: ${response.status} ${response.statusText} - ${errorText}`);
|
||||||
|
}
|
||||||
|
|
||||||
|
const nodeStream = response.streamNode();
|
||||||
|
return nodeStream;
|
||||||
|
}
|
||||||
|
|
||||||
|
public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
|
||||||
|
throw new Error('ElevenLabs does not support vision functionality. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
|
||||||
|
public async document(optionsArg: {
|
||||||
|
systemMessage: string;
|
||||||
|
userMessage: string;
|
||||||
|
pdfDocuments: Uint8Array[];
|
||||||
|
messageHistory: any[];
|
||||||
|
}): Promise<{ message: any }> {
|
||||||
|
throw new Error('ElevenLabs does not support document processing. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
|
||||||
|
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
||||||
|
throw new Error('ElevenLabs does not support research capabilities. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('ElevenLabs does not support image generation. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('ElevenLabs does not support image editing. This provider is specialized for text-to-speech only.');
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -1,7 +1,16 @@
|
|||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import * as paths from './paths.js';
|
import * as paths from './paths.js';
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ChatOptions, ChatResponse, ChatMessage, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ChatMessage,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
|
import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
|
||||||
|
|
||||||
export interface IExoProviderOptions {
|
export interface IExoProviderOptions {
|
||||||
@@ -129,4 +138,18 @@ export class ExoProvider extends MultiModalModel {
|
|||||||
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
||||||
throw new Error('Research capabilities are not yet supported by Exo provider.');
|
throw new Error('Research capabilities are not yet supported by Exo provider.');
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation is not supported by Exo
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image generation is not supported by Exo. Please use OpenAI provider for image generation.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing is not supported by Exo
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image editing is not supported by Exo. Please use OpenAI provider for image editing.');
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,7 +1,16 @@
|
|||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import * as paths from './paths.js';
|
import * as paths from './paths.js';
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ChatOptions, ChatResponse, ChatMessage, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ChatMessage,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
|
|
||||||
export interface IGroqProviderOptions {
|
export interface IGroqProviderOptions {
|
||||||
groqToken: string;
|
groqToken: string;
|
||||||
@@ -193,4 +202,18 @@ export class GroqProvider extends MultiModalModel {
|
|||||||
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
||||||
throw new Error('Research capabilities are not yet supported by Groq provider.');
|
throw new Error('Research capabilities are not yet supported by Groq provider.');
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation is not supported by Groq
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image generation is not supported by Groq. Please use OpenAI provider for image generation.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing is not supported by Groq
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image editing is not supported by Groq. Please use OpenAI provider for image editing.');
|
||||||
|
}
|
||||||
}
|
}
|
||||||
@@ -1,7 +1,16 @@
|
|||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import * as paths from './paths.js';
|
import * as paths from './paths.js';
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ChatOptions, ChatResponse, ChatMessage, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ChatMessage,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
|
|
||||||
export interface IOllamaProviderOptions {
|
export interface IOllamaProviderOptions {
|
||||||
baseUrl?: string;
|
baseUrl?: string;
|
||||||
@@ -207,11 +216,14 @@ export class OllamaProvider extends MultiModalModel {
|
|||||||
pdfDocuments: Uint8Array[];
|
pdfDocuments: Uint8Array[];
|
||||||
messageHistory: ChatMessage[];
|
messageHistory: ChatMessage[];
|
||||||
}): Promise<{ message: any }> {
|
}): Promise<{ message: any }> {
|
||||||
|
// Ensure SmartPdf is initialized before processing documents
|
||||||
|
await this.ensureSmartpdfReady();
|
||||||
|
|
||||||
// Convert PDF documents to images using SmartPDF
|
// Convert PDF documents to images using SmartPDF
|
||||||
let documentImageBytesArray: Uint8Array[] = [];
|
let documentImageBytesArray: Uint8Array[] = [];
|
||||||
|
|
||||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
const documentImageArray = await this.smartpdfInstance!.convertPDFToPngBytes(pdfDocument);
|
||||||
documentImageBytesArray = documentImageBytesArray.concat(documentImageArray);
|
documentImageBytesArray = documentImageBytesArray.concat(documentImageArray);
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -255,4 +267,18 @@ export class OllamaProvider extends MultiModalModel {
|
|||||||
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
||||||
throw new Error('Research capabilities are not yet supported by Ollama provider.');
|
throw new Error('Research capabilities are not yet supported by Ollama provider.');
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation is not supported by Ollama
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image generation is not supported by Ollama. Please use OpenAI provider for image generation.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing is not supported by Ollama
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image editing is not supported by Ollama. Please use OpenAI provider for image editing.');
|
||||||
|
}
|
||||||
}
|
}
|
||||||
@@ -9,7 +9,13 @@ export type TChatCompletionRequestMessage = {
|
|||||||
};
|
};
|
||||||
|
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
|
|
||||||
export interface IOpenaiProviderOptions {
|
export interface IOpenaiProviderOptions {
|
||||||
openaiToken: string;
|
openaiToken: string;
|
||||||
@@ -17,6 +23,7 @@ export interface IOpenaiProviderOptions {
|
|||||||
audioModel?: string;
|
audioModel?: string;
|
||||||
visionModel?: string;
|
visionModel?: string;
|
||||||
researchModel?: string;
|
researchModel?: string;
|
||||||
|
imageModel?: string;
|
||||||
enableWebSearch?: boolean;
|
enableWebSearch?: boolean;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -166,11 +173,14 @@ export class OpenAiProvider extends MultiModalModel {
|
|||||||
content: any;
|
content: any;
|
||||||
}[];
|
}[];
|
||||||
}) {
|
}) {
|
||||||
|
// Ensure SmartPdf is initialized before processing documents
|
||||||
|
await this.ensureSmartpdfReady();
|
||||||
|
|
||||||
let pdfDocumentImageBytesArray: Uint8Array[] = [];
|
let pdfDocumentImageBytesArray: Uint8Array[] = [];
|
||||||
|
|
||||||
// Convert each PDF into one or more image byte arrays.
|
// Convert each PDF into one or more image byte arrays.
|
||||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
const documentImageArray = await this.smartpdfInstance!.convertPDFToPngBytes(pdfDocument);
|
||||||
pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
|
pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -233,52 +243,37 @@ export class OpenAiProvider extends MultiModalModel {
|
|||||||
}
|
}
|
||||||
|
|
||||||
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
||||||
// Determine which model to use based on search depth
|
// Determine which model to use - Deep Research API requires specific models
|
||||||
let model: string;
|
let model: string;
|
||||||
if (optionsArg.searchDepth === 'deep') {
|
if (optionsArg.searchDepth === 'deep') {
|
||||||
model = this.options.researchModel || 'o4-mini-deep-research-2025-06-26';
|
model = this.options.researchModel || 'o4-mini-deep-research-2025-06-26';
|
||||||
} else {
|
} else {
|
||||||
model = this.options.chatModel || 'gpt-5-mini';
|
// For basic/advanced, still use deep research models if web search is needed
|
||||||
|
if (optionsArg.includeWebSearch) {
|
||||||
|
model = this.options.researchModel || 'o4-mini-deep-research-2025-06-26';
|
||||||
|
} else {
|
||||||
|
model = this.options.chatModel || 'gpt-5-mini';
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// Prepare the request parameters
|
const systemMessage = 'You are a research assistant. Provide comprehensive answers with citations and sources when available.';
|
||||||
|
|
||||||
|
// Prepare request parameters using Deep Research API format
|
||||||
const requestParams: any = {
|
const requestParams: any = {
|
||||||
model,
|
model,
|
||||||
messages: [
|
instructions: systemMessage,
|
||||||
{
|
input: optionsArg.query
|
||||||
role: 'system',
|
|
||||||
content: 'You are a research assistant. Provide comprehensive answers with citations and sources when available.'
|
|
||||||
},
|
|
||||||
{
|
|
||||||
role: 'user',
|
|
||||||
content: optionsArg.query
|
|
||||||
}
|
|
||||||
],
|
|
||||||
temperature: 0.7
|
|
||||||
};
|
};
|
||||||
|
|
||||||
// Add web search tools if requested
|
// Add web search tool if requested
|
||||||
if (optionsArg.includeWebSearch || optionsArg.searchDepth === 'deep') {
|
if (optionsArg.includeWebSearch || optionsArg.searchDepth === 'deep') {
|
||||||
requestParams.tools = [
|
requestParams.tools = [
|
||||||
{
|
{
|
||||||
type: 'function',
|
type: 'web_search_preview',
|
||||||
function: {
|
search_context_size: optionsArg.searchDepth === 'deep' ? 'high' :
|
||||||
name: 'web_search',
|
optionsArg.searchDepth === 'advanced' ? 'medium' : 'low'
|
||||||
description: 'Search the web for information',
|
|
||||||
parameters: {
|
|
||||||
type: 'object',
|
|
||||||
properties: {
|
|
||||||
query: {
|
|
||||||
type: 'string',
|
|
||||||
description: 'The search query'
|
|
||||||
}
|
|
||||||
},
|
|
||||||
required: ['query']
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
];
|
];
|
||||||
requestParams.tool_choice = 'auto';
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Add background flag for deep research
|
// Add background flag for deep research
|
||||||
@@ -287,14 +282,36 @@ export class OpenAiProvider extends MultiModalModel {
|
|||||||
}
|
}
|
||||||
|
|
||||||
try {
|
try {
|
||||||
// Execute the research request
|
// Execute the research request using Deep Research API
|
||||||
const result = await this.openAiApiClient.chat.completions.create(requestParams);
|
const result = await this.openAiApiClient.responses.create(requestParams);
|
||||||
|
|
||||||
// Extract the answer
|
// Extract the answer from output items
|
||||||
const answer = result.choices[0].message.content || '';
|
let answer = '';
|
||||||
|
|
||||||
// Parse sources from the response (OpenAI often includes URLs in markdown format)
|
|
||||||
const sources: Array<{ url: string; title: string; snippet: string }> = [];
|
const sources: Array<{ url: string; title: string; snippet: string }> = [];
|
||||||
|
const searchQueries: string[] = [];
|
||||||
|
|
||||||
|
// Process output items
|
||||||
|
for (const item of result.output || []) {
|
||||||
|
// Extract message content
|
||||||
|
if (item.type === 'message' && 'content' in item) {
|
||||||
|
const messageItem = item as any;
|
||||||
|
for (const contentItem of messageItem.content || []) {
|
||||||
|
if (contentItem.type === 'output_text' && 'text' in contentItem) {
|
||||||
|
answer += contentItem.text;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Extract web search queries
|
||||||
|
if (item.type === 'web_search_call' && 'action' in item) {
|
||||||
|
const searchItem = item as any;
|
||||||
|
if (searchItem.action && searchItem.action.type === 'search' && 'query' in searchItem.action) {
|
||||||
|
searchQueries.push(searchItem.action.query);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Parse sources from markdown links in the answer
|
||||||
const urlRegex = /\[([^\]]+)\]\(([^)]+)\)/g;
|
const urlRegex = /\[([^\]]+)\]\(([^)]+)\)/g;
|
||||||
let match: RegExpExecArray | null;
|
let match: RegExpExecArray | null;
|
||||||
|
|
||||||
@@ -302,27 +319,10 @@ export class OpenAiProvider extends MultiModalModel {
|
|||||||
sources.push({
|
sources.push({
|
||||||
title: match[1],
|
title: match[1],
|
||||||
url: match[2],
|
url: match[2],
|
||||||
snippet: '' // OpenAI doesn't provide snippets in standard responses
|
snippet: ''
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
// Extract search queries if tools were used
|
|
||||||
const searchQueries: string[] = [];
|
|
||||||
if (result.choices[0].message.tool_calls) {
|
|
||||||
for (const toolCall of result.choices[0].message.tool_calls) {
|
|
||||||
if ('function' in toolCall && toolCall.function.name === 'web_search') {
|
|
||||||
try {
|
|
||||||
const args = JSON.parse(toolCall.function.arguments);
|
|
||||||
if (args.query) {
|
|
||||||
searchQueries.push(args.query);
|
|
||||||
}
|
|
||||||
} catch (e) {
|
|
||||||
// Ignore parsing errors
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
answer,
|
answer,
|
||||||
sources,
|
sources,
|
||||||
@@ -338,4 +338,121 @@ export class OpenAiProvider extends MultiModalModel {
|
|||||||
throw new Error(`Failed to perform research: ${error.message}`);
|
throw new Error(`Failed to perform research: ${error.message}`);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation using OpenAI's gpt-image-1 or DALL-E models
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
|
||||||
|
|
||||||
|
try {
|
||||||
|
const requestParams: any = {
|
||||||
|
model,
|
||||||
|
prompt: optionsArg.prompt,
|
||||||
|
n: optionsArg.n || 1,
|
||||||
|
};
|
||||||
|
|
||||||
|
// Add gpt-image-1 specific parameters
|
||||||
|
if (model === 'gpt-image-1') {
|
||||||
|
if (optionsArg.quality) requestParams.quality = optionsArg.quality;
|
||||||
|
if (optionsArg.size) requestParams.size = optionsArg.size;
|
||||||
|
if (optionsArg.background) requestParams.background = optionsArg.background;
|
||||||
|
if (optionsArg.outputFormat) requestParams.output_format = optionsArg.outputFormat;
|
||||||
|
if (optionsArg.outputCompression !== undefined) requestParams.output_compression = optionsArg.outputCompression;
|
||||||
|
if (optionsArg.moderation) requestParams.moderation = optionsArg.moderation;
|
||||||
|
if (optionsArg.stream !== undefined) requestParams.stream = optionsArg.stream;
|
||||||
|
if (optionsArg.partialImages !== undefined) requestParams.partial_images = optionsArg.partialImages;
|
||||||
|
} else if (model === 'dall-e-3') {
|
||||||
|
// DALL-E 3 specific parameters
|
||||||
|
if (optionsArg.quality) requestParams.quality = optionsArg.quality;
|
||||||
|
if (optionsArg.size) requestParams.size = optionsArg.size;
|
||||||
|
if (optionsArg.style) requestParams.style = optionsArg.style;
|
||||||
|
requestParams.response_format = 'b64_json'; // Always use base64 for consistency
|
||||||
|
} else if (model === 'dall-e-2') {
|
||||||
|
// DALL-E 2 specific parameters
|
||||||
|
if (optionsArg.size) requestParams.size = optionsArg.size;
|
||||||
|
requestParams.response_format = 'b64_json';
|
||||||
|
}
|
||||||
|
|
||||||
|
const result = await this.openAiApiClient.images.generate(requestParams);
|
||||||
|
|
||||||
|
const images = (result.data || []).map(img => ({
|
||||||
|
b64_json: img.b64_json,
|
||||||
|
url: img.url,
|
||||||
|
revisedPrompt: img.revised_prompt
|
||||||
|
}));
|
||||||
|
|
||||||
|
return {
|
||||||
|
images,
|
||||||
|
metadata: {
|
||||||
|
model,
|
||||||
|
quality: result.quality,
|
||||||
|
size: result.size,
|
||||||
|
outputFormat: result.output_format,
|
||||||
|
tokensUsed: result.usage?.total_tokens
|
||||||
|
}
|
||||||
|
};
|
||||||
|
} catch (error) {
|
||||||
|
console.error('Image generation error:', error);
|
||||||
|
throw new Error(`Failed to generate image: ${error.message}`);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing using OpenAI's gpt-image-1 or DALL-E 2 models
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
|
||||||
|
|
||||||
|
try {
|
||||||
|
const requestParams: any = {
|
||||||
|
model,
|
||||||
|
image: optionsArg.image,
|
||||||
|
prompt: optionsArg.prompt,
|
||||||
|
n: optionsArg.n || 1,
|
||||||
|
};
|
||||||
|
|
||||||
|
// Add mask if provided
|
||||||
|
if (optionsArg.mask) {
|
||||||
|
requestParams.mask = optionsArg.mask;
|
||||||
|
}
|
||||||
|
|
||||||
|
// Add gpt-image-1 specific parameters
|
||||||
|
if (model === 'gpt-image-1') {
|
||||||
|
if (optionsArg.quality) requestParams.quality = optionsArg.quality;
|
||||||
|
if (optionsArg.size) requestParams.size = optionsArg.size;
|
||||||
|
if (optionsArg.background) requestParams.background = optionsArg.background;
|
||||||
|
if (optionsArg.outputFormat) requestParams.output_format = optionsArg.outputFormat;
|
||||||
|
if (optionsArg.outputCompression !== undefined) requestParams.output_compression = optionsArg.outputCompression;
|
||||||
|
if (optionsArg.stream !== undefined) requestParams.stream = optionsArg.stream;
|
||||||
|
if (optionsArg.partialImages !== undefined) requestParams.partial_images = optionsArg.partialImages;
|
||||||
|
} else if (model === 'dall-e-2') {
|
||||||
|
// DALL-E 2 specific parameters
|
||||||
|
if (optionsArg.size) requestParams.size = optionsArg.size;
|
||||||
|
requestParams.response_format = 'b64_json';
|
||||||
|
}
|
||||||
|
|
||||||
|
const result = await this.openAiApiClient.images.edit(requestParams);
|
||||||
|
|
||||||
|
const images = (result.data || []).map(img => ({
|
||||||
|
b64_json: img.b64_json,
|
||||||
|
url: img.url,
|
||||||
|
revisedPrompt: img.revised_prompt
|
||||||
|
}));
|
||||||
|
|
||||||
|
return {
|
||||||
|
images,
|
||||||
|
metadata: {
|
||||||
|
model,
|
||||||
|
quality: result.quality,
|
||||||
|
size: result.size,
|
||||||
|
outputFormat: result.output_format,
|
||||||
|
tokensUsed: result.usage?.total_tokens
|
||||||
|
}
|
||||||
|
};
|
||||||
|
} catch (error) {
|
||||||
|
console.error('Image edit error:', error);
|
||||||
|
throw new Error(`Failed to edit image: ${error.message}`);
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
@@ -1,7 +1,16 @@
|
|||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import * as paths from './paths.js';
|
import * as paths from './paths.js';
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ChatOptions, ChatResponse, ChatMessage, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ChatMessage,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
|
|
||||||
export interface IPerplexityProviderOptions {
|
export interface IPerplexityProviderOptions {
|
||||||
perplexityToken: string;
|
perplexityToken: string;
|
||||||
@@ -233,4 +242,18 @@ export class PerplexityProvider extends MultiModalModel {
|
|||||||
throw new Error(`Failed to perform research: ${error.message}`);
|
throw new Error(`Failed to perform research: ${error.message}`);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation is not supported by Perplexity
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image generation is not supported by Perplexity. Please use OpenAI provider for image generation.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing is not supported by Perplexity
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image editing is not supported by Perplexity. Please use OpenAI provider for image editing.');
|
||||||
|
}
|
||||||
}
|
}
|
||||||
@@ -1,7 +1,16 @@
|
|||||||
import * as plugins from './plugins.js';
|
import * as plugins from './plugins.js';
|
||||||
import * as paths from './paths.js';
|
import * as paths from './paths.js';
|
||||||
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
import { MultiModalModel } from './abstract.classes.multimodal.js';
|
||||||
import type { ChatOptions, ChatResponse, ChatMessage, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
|
import type {
|
||||||
|
ChatOptions,
|
||||||
|
ChatResponse,
|
||||||
|
ChatMessage,
|
||||||
|
ResearchOptions,
|
||||||
|
ResearchResponse,
|
||||||
|
ImageGenerateOptions,
|
||||||
|
ImageEditOptions,
|
||||||
|
ImageResponse
|
||||||
|
} from './abstract.classes.multimodal.js';
|
||||||
import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
|
import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
|
||||||
|
|
||||||
export interface IXAIProviderOptions {
|
export interface IXAIProviderOptions {
|
||||||
@@ -140,11 +149,14 @@ export class XAIProvider extends MultiModalModel {
|
|||||||
pdfDocuments: Uint8Array[];
|
pdfDocuments: Uint8Array[];
|
||||||
messageHistory: { role: string; content: string; }[];
|
messageHistory: { role: string; content: string; }[];
|
||||||
}): Promise<{ message: any }> {
|
}): Promise<{ message: any }> {
|
||||||
|
// Ensure SmartPdf is initialized before processing documents
|
||||||
|
await this.ensureSmartpdfReady();
|
||||||
|
|
||||||
// First convert PDF documents to images
|
// First convert PDF documents to images
|
||||||
let pdfDocumentImageBytesArray: Uint8Array[] = [];
|
let pdfDocumentImageBytesArray: Uint8Array[] = [];
|
||||||
|
|
||||||
for (const pdfDocument of optionsArg.pdfDocuments) {
|
for (const pdfDocument of optionsArg.pdfDocuments) {
|
||||||
const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
|
const documentImageArray = await this.smartpdfInstance!.convertPDFToPngBytes(pdfDocument);
|
||||||
pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
|
pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -185,4 +197,18 @@ export class XAIProvider extends MultiModalModel {
|
|||||||
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
|
||||||
throw new Error('Research capabilities are not yet supported by xAI provider.');
|
throw new Error('Research capabilities are not yet supported by xAI provider.');
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image generation is not supported by xAI
|
||||||
|
*/
|
||||||
|
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image generation is not supported by xAI. Please use OpenAI provider for image generation.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Image editing is not supported by xAI
|
||||||
|
*/
|
||||||
|
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
|
||||||
|
throw new Error('Image editing is not supported by xAI. Please use OpenAI provider for image editing.');
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user