File Processing

curl -X POST "http://localhost:8084/api/v1/digital/store" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "content": "https://arxiv.org/pdf/1706.03762.pdf",
    "content_type": "pdf",
    "metadata": {
      "source": "arxiv",
      "title": "Attention Is All You Need"
    }
  }'

PDF URL → Download → Extract ─┬─▶ Text → Chunk → Embed → Store
                              ├─▶ Tables → Structure → Store
                              └─▶ Images → OCR → Store

{
  "success": true,
  "content_type": "pdf",
  "chunks_stored": 45,
  "metadata": {
    "title": "Attention Is All You Need",
    "pages": 15,
    "tables_extracted": 3,
    "images_extracted": 8
  }
}

curl -X POST "http://localhost:8084/api/v1/digital/store" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "content": "https://images.unsplash.com/photo-1506905925346-21bda4d32df4",
    "content_type": "image",
    "metadata": {
      "source": "unsplash"
    }
  }'

{
  "success": true,
  "content_type": "image",
  "ai_metadata": {
    "ai_categories": ["landscape"],
    "ai_tags": ["mountains", "snow", "glaciers", "clouds", "sunset", "alpine", "nature", "scenic", "majestic"],
    "ai_mood": "peaceful",
    "ai_style": "professional",
    "ai_quality_score": 0.88,
    "ai_has_people": false,
    "ai_has_text": false,
    "ai_dominant_colors": ["blue", "orange", "white"],
    "ai_composition": "rule-of-thirds"
  }
}

curl -X POST "http://localhost:8084/api/v1/digital/search" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "query": "peaceful mountain sunset landscape",
    "search_options": {"top_k": 5}
  }'

curl -X POST "http://localhost:8084/api/v1/digital/store" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "content": "https://example.com/podcast.mp3",
    "content_type": "audio",
    "metadata": {
      "title": "Tech Talk Episode 1"
    }
  }'

curl -X POST "http://localhost:8084/api/v1/digital/search" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "query": "discussion about machine learning",
    "search_options": {"top_k": 5}
  }'

curl -X POST "http://localhost:8084/api/v1/digital/store" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "content": "https://example.com/tutorial.mp4",
    "content_type": "video",
    "metadata": {
      "title": "Python Tutorial"
    }
  }'

# In store request
{
    "content": "Your text content...",
    "content_type": "text",
    "chunking_options": {
        "strategy": "semantic",
        "chunk_size": 512,
        "chunk_overlap": 50
    }
}

from isa_data import DigitalService
 
service = DigitalService("http://localhost:8084")
 
# Store PDF
result = await service.store(
    user_id="user123",
    content="https://example.com/document.pdf",
    content_type="pdf"
)
 
# Store image with AI analysis
result = await service.store(
    user_id="user123",
    content="https://example.com/photo.jpg",
    content_type="image"
)
 
# Access AI metadata
print(result.ai_metadata.ai_tags)
print(result.ai_metadata.ai_mood)
 
# Search
results = await service.search(
    user_id="user123",
    query="mountain landscape"
)

# Build knowledge base from PDF documents
documents = [
    "https://example.com/manual1.pdf",
    "https://example.com/manual2.pdf",
    "https://example.com/guide.pdf"
]
 
for doc in documents:
    await service.store(
        user_id="kb_admin",
        content=doc,
        content_type="pdf",
        metadata={"collection": "product_docs"}
    )
 
# Query the knowledge base
response = await service.response(
    user_id="user",
    query="How do I configure the system?",
    response_options={"rag_mode": "simple"}
)

# Index image library
images = get_image_urls_from_storage()
 
for img in images:
    await service.store(
        user_id="media_team",
        content=img,
        content_type="image"
    )
 
# Search by visual content
results = await service.search(
    user_id="designer",
    query="professional headshot corporate"
)
 
# Filter by AI metadata
results = await service.search(
    user_id="designer",
    query="high quality landscape",
    filters={"ai_quality_score": {"$gte": 0.8}}
)

# Process meeting recording
await service.store(
    user_id="team",
    content="https://storage.com/meeting-2024-01-15.mp4",
    content_type="video",
    metadata={"meeting": "Q1 Planning"}
)
 
# Find specific discussions
results = await service.search(
    user_id="manager",
    query="budget allocation discussion"
)