AI Video Generation Implementation
This commit is contained in:
@@ -5,10 +5,38 @@ ALwrity's Assistive Writing feature revolutionizes content creation by providing
|
||||
## Visuals
|
||||
|
||||
<p align="center">
|
||||
<img src="../../assets/assistive-1.png" alt="Assistive writing selection tools" width="45%">
|
||||
<img src="../../assets/assistive-2.png" alt="Inline fact checking and quick edits" width="45%">
|
||||
<img src="../../assests/assistive-1.png" alt="Assistive writing selection tools" width="45%">
|
||||
<img src="../../assests/assistive-2.png" alt="Inline fact checking and quick edits" width="45%">
|
||||
</p>
|
||||
|
||||
## Quick Reference
|
||||
|
||||
1. Enable: Toggle “Assistive Writing” in the LinkedIn Writer header
|
||||
2. Write: Type at least 5 words
|
||||
3. Wait: 5 seconds for the first automatic suggestion
|
||||
4. Accept/Dismiss: Use buttons in the suggestion card
|
||||
|
||||
### How It Works
|
||||
- First suggestion: Automatic (5 words + 5 seconds)
|
||||
- More suggestions: Click “Continue writing”
|
||||
- Daily limit: 50 suggestions (resets every 24 hours)
|
||||
|
||||
### Best Practices
|
||||
- Write specific, clear content
|
||||
- Review source links before accepting
|
||||
- Use manual “Continue writing” for additional suggestions
|
||||
- Don’t expect suggestions for very short text
|
||||
- Don’t ignore source verification
|
||||
|
||||
### Common Issues (Quick Table)
|
||||
|
||||
| Problem | Solution |
|
||||
| --- | --- |
|
||||
| No suggestions | Write 5+ words, then wait 5 seconds |
|
||||
| “API quota exceeded” | Wait 24 hours or upgrade plan |
|
||||
| “No relevant sources” | Be more specific in your writing |
|
||||
| Suggestions not relevant | Try different wording or topics |
|
||||
|
||||
## What is Assistive Writing?
|
||||
|
||||
Assistive Writing is an AI-powered feature that provides real-time writing assistance, suggestions, and enhancements to help you create compelling content. It combines advanced natural language processing with contextual understanding to offer intelligent recommendations that improve your writing quality and efficiency.
|
||||
@@ -160,6 +188,67 @@ Assistive Writing is an AI-powered feature that provides real-time writing assis
|
||||
- **Message Alignment**: Align with brand messaging
|
||||
- **Value Integration**: Incorporate brand values
|
||||
|
||||
## Workflow
|
||||
|
||||
```text
|
||||
1. ENABLE ASSISTIVE WRITING
|
||||
┌─────────────────────────┐
|
||||
│ Toggle "Assistive │
|
||||
│ Writing" ON (blue) │
|
||||
└─────────────────────────┘
|
||||
│
|
||||
▼
|
||||
|
||||
2. START WRITING
|
||||
┌─────────────────────────┐
|
||||
│ Type at least 5 words │
|
||||
│ in the text area │
|
||||
└─────────────────────────┘
|
||||
│
|
||||
▼
|
||||
|
||||
3. WAIT FOR AI ANALYSIS
|
||||
┌─────────────────────────┐
|
||||
│ Wait 5 seconds │
|
||||
│ AI analyzes your text │
|
||||
└─────────────────────────┘
|
||||
│
|
||||
▼
|
||||
|
||||
4. RECEIVE FIRST SUGGESTION
|
||||
┌─────────────────────────┐
|
||||
│ Suggestion card appears │
|
||||
│ near your cursor │
|
||||
│ │
|
||||
│ [Accept] [Dismiss] │
|
||||
└─────────────────────────┘
|
||||
│
|
||||
▼
|
||||
|
||||
5. AFTER FIRST SUGGESTION
|
||||
┌─────────────────────────┐
|
||||
│ "Continue writing" │
|
||||
│ prompt appears │
|
||||
│ │
|
||||
│ [Continue writing] │
|
||||
│ [Dismiss] │
|
||||
└─────────────────────────┘
|
||||
│
|
||||
▼
|
||||
|
||||
6. MANUAL SUGGESTIONS
|
||||
┌─────────────────────────┐
|
||||
│ Click "Continue writing"│
|
||||
│ to get more suggestions │
|
||||
│ (saves costs) │
|
||||
└─────────────────────────┘
|
||||
```
|
||||
|
||||
### Step-by-Step
|
||||
- Enable → Start writing (5+ words) → Wait 5s
|
||||
- First suggestion shows: suggested text, confidence score, source links, Accept/Dismiss
|
||||
- After first suggestion, trigger more via “Continue writing”
|
||||
|
||||
## Integration with Other Features
|
||||
|
||||
### Blog Writer Integration
|
||||
|
||||
@@ -5,13 +5,47 @@ ALwrity's Grounding UI feature provides AI-powered content verification and fact
|
||||
## Visuals
|
||||
|
||||
<p align="center">
|
||||
<img src="../../assets/assistive-2.png" alt="Inline fact checking with citations and claim statuses" width="60%">
|
||||
<img src="../../assests/assistive-2.png" alt="Inline fact checking with citations and claim statuses" width="60%">
|
||||
</p>
|
||||
|
||||
## What is Grounding UI?
|
||||
|
||||
Grounding UI is an intelligent content verification system that connects AI-generated content with real-world data sources, ensuring accuracy and reliability. It provides visual indicators, source citations, and verification status to help you create trustworthy, fact-checked content.
|
||||
|
||||
## Implementation Overview (Concise)
|
||||
|
||||
- Backend service: `backend/services/hallucination_detector.py` (claim extraction → evidence search → verification)
|
||||
- Models: `backend/models/hallucination_models.py`
|
||||
- API router: `backend/api/hallucination_detector.py` (registered in `backend/app.py`)
|
||||
- Frontend service: `frontend/src/services/hallucinationDetectorService.ts`
|
||||
- UI: LinkedIn Writer selection menu + FactCheckResults modal
|
||||
|
||||
### API Endpoints (Summary)
|
||||
- `POST /api/hallucination-detector/detect` – main fact-checking
|
||||
- `POST /api/hallucination-detector/extract-claims` – claims only
|
||||
- `POST /api/hallucination-detector/verify-claim` – single claim
|
||||
- `GET /api/hallucination-detector/health` – health check
|
||||
|
||||
### Minimal Setup
|
||||
- Backend env:
|
||||
- `EXA_API_KEY=...` (evidence search)
|
||||
- `OPENAI_API_KEY=...` (claim extraction + verification)
|
||||
- Frontend env:
|
||||
- `REACT_APP_API_URL=http://localhost:8000`
|
||||
|
||||
### Quick Usage (UI)
|
||||
1) In LinkedIn Writer, select a passage (10+ chars)
|
||||
2) Click “Check Facts” in the selection menu
|
||||
3) Review claims, assessments (supported/refuted/insufficient), confidence, and sources in the results modal
|
||||
|
||||
### Quick Usage (API)
|
||||
|
||||
```bash
|
||||
curl -X POST "$API_URL/api/hallucination-detector/detect" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"text":"The Eiffel Tower is in Paris and built in 1889.","include_sources":true,"max_claims":5}'
|
||||
```
|
||||
|
||||
### Key Benefits
|
||||
|
||||
- **Content Verification**: Verify facts and claims in real-time
|
||||
@@ -274,6 +308,11 @@ Grounding UI is an intelligent content verification system that connects AI-gene
|
||||
- **Display Problems**: Fix visual indicator issues
|
||||
- **Integration Errors**: Resolve integration problems
|
||||
|
||||
### Environment & Health
|
||||
- “EXA_API_KEY not found” → add key to backend `.env`, restart server
|
||||
- “OpenAI API key not found” → add `OPENAI_API_KEY`, verify credits
|
||||
- Health check: `GET /api/hallucination-detector/health`
|
||||
|
||||
### Getting Help
|
||||
|
||||
#### Support Resources
|
||||
|
||||
Reference in New Issue
Block a user