PlanOpticon

planopticon / CLAUDE.md
Source Blame History 63 lines
b363c5b… noreply 1 # PlanOpticon
b363c5b… noreply 2
b363c5b… noreply 3 Video analysis and knowledge extraction CLI. Processes recordings into structured knowledge graphs with entities, relationships, and insights.
b363c5b… noreply 4
b363c5b… noreply 5 ## Knowledge Graph Query Skill
b363c5b… noreply 6
b363c5b… noreply 7 PlanOpticon can build and query knowledge graphs from video content. If you see `knowledge_graph.db` or `knowledge_graph.json` files in the workspace, you can query them to understand what was discussed.
b363c5b… noreply 8
b363c5b… noreply 9 ### Auto-detection
b363c5b… noreply 10
b363c5b… noreply 11 Look for these files (checked automatically):
0981a08… noreply 12 - `knowledge_graph.db` — SQLite graph database (preferred)
b363c5b… noreply 13 - `knowledge_graph.json` — JSON export (fallback)
b363c5b… noreply 14
b363c5b… noreply 15 Common locations: project root, `results/`, `output/`, `knowledge-base/`.
b363c5b… noreply 16
b363c5b… noreply 17 ### Quick commands
b363c5b… noreply 18
b363c5b… noreply 19 ```bash
b363c5b… noreply 20 # Show graph stats (entity/relationship counts)
b363c5b… noreply 21 planopticon query
b363c5b… noreply 22
b363c5b… noreply 23 # List entities filtered by type
b363c5b… noreply 24 planopticon query "entities --type technology"
b363c5b… noreply 25 planopticon query "entities --type person"
b363c5b… noreply 26
b363c5b… noreply 27 # Search entities by name
b363c5b… noreply 28 planopticon query "entities --name python"
b363c5b… noreply 29
b363c5b… noreply 30 # See what connects to an entity
b363c5b… noreply 31 planopticon query "neighbors Alice"
b363c5b… noreply 32
b363c5b… noreply 33 # List relationships
b363c5b… noreply 34 planopticon query "relationships --source Alice"
b363c5b… noreply 35
b363c5b… noreply 36 # Natural language (requires API key)
b363c5b… noreply 37 planopticon query "What technologies were discussed?"
b363c5b… noreply 38 planopticon query "Who are the key people mentioned?"
b363c5b… noreply 39
b363c5b… noreply 40 # Output as JSON or Mermaid diagram
b363c5b… noreply 41 planopticon query --format json stats
b363c5b… noreply 42 planopticon query --format mermaid "neighbors Alice"
b363c5b… noreply 43
b363c5b… noreply 44 # Interactive REPL
b363c5b… noreply 45 planopticon query -I
b363c5b… noreply 46 ```
b363c5b… noreply 47
b363c5b… noreply 48 ### When to use
b363c5b… noreply 49
b363c5b… noreply 50 - **Direct mode** (`stats`, `entities`, `neighbors`, `relationships`): No API key needed. Fast, deterministic. Use for structured lookups.
b363c5b… noreply 51 - **Agentic mode** (natural language questions): Requires an API key (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.). Use when the user asks open-ended questions about the content.
b363c5b… noreply 52
b363c5b… noreply 53 ### Python API
b363c5b… noreply 54
b363c5b… noreply 55 ```python
b363c5b… noreply 56 from video_processor.integrators.graph_query import GraphQueryEngine
b363c5b… noreply 57 from video_processor.integrators.graph_discovery import find_nearest_graph
b363c5b… noreply 58
b363c5b… noreply 59 path = find_nearest_graph()
b363c5b… noreply 60 engine = GraphQueryEngine.from_db_path(path)
b363c5b… noreply 61 result = engine.stats()
b363c5b… noreply 62 print(result.to_text())
b363c5b… noreply 63 ```

Keyboard Shortcuts

Open search /
Next entry (timeline) j
Previous entry (timeline) k
Open focused entry Enter
Show this help ?
Toggle theme Top nav button