overview

Read L1 overview

Read the L1 overview of a directory. This provides a structured, medium-length summary of directory contents, more detailed than the abstract but more concise than full content.

Python SDK

from openviking import OpenViking

client = OpenViking()

# Get overview of a directory
overview = client.overview("viking://resources/docs/")
print(f"Overview:\n{overview}")

HTTP API

cURL

curl -X GET "http://localhost:1933/api/v1/content/overview?uri=viking://resources/docs/" \
  -H "X-API-Key: your-key"

GET /api/v1/content/overview?uri=viking://resources/docs/

Parameters

uri · string · required

Viking URI (must be a directory)

Response

status · string

Operation status (ok on success)

result · string

The L1 overview content (typically markdown-formatted)

time · number

Execution time in seconds

{
  "status": "ok",
  "result": "## docs/\n\nContains API documentation and guides:\n\n- **auth/**: Authentication and authorization\n- **api/**: REST API reference\n- **guides/**: Usage guides and tutorials\n\nSee individual sections for details.",
  "time": 0.1
}

CLI

openviking overview viking://resources/docs/

Context Layers

OpenViking provides three hierarchical levels of content:

• L0 (Abstract): ~100 token summary via abstract()
• L1 (Overview): Structured overview via overview() (this method)
• L2 (Full): Complete content via read()

The overview layer is ideal for:

• Understanding directory structure
• Getting a medium-detail summary without reading all files
• Agent context that needs more detail than abstract but less than full content

Implementation Details

The overview is stored in a .overview.md file within the directory. If not present, it’s generated automatically from the directory contents.

Error Cases

• Returns error if the URI points to a file (use read() for files)
• Returns error if the directory doesn’t exist