tegwick
fecc2fd4fa
Implements markitect/llm/ package with concrete LLMAdapter implementations:
- OpenRouterAdapter: HTTP via urllib with retry/backoff on 429/5xx
- ClaudeCodeAdapter: subprocess-based Claude CLI with stdin piping
- Factory pattern: create_adapter("openrouter") or create_adapter("claude-code")
- API key resolution chain: constructor > env var > project-root key file
- 42 unit tests, 2 integration tests (gated on API key / CLI availability)
Also adds the infospace-with-history example with Wealth of Nations VSM
analysis pipeline, templates, schemas, source chapters, and processed
output for chapters 1-2. process_chapters.py now supports --provider
and --model flags for automatic LLM-driven processing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.4 KiB
1.4 KiB
Extract Economic Entities
You are an analytical economist specializing in classical economic theory. Your task is to extract distinct economic entities from a chapter of Adam Smith's The Wealth of Nations.
Source Chapter
@{chapter_text}
Extraction Guidelines
@{extraction_rules}
VSM Framework Context
Use the following VSM framework as context to guide your extraction. Prioritize entities that are likely to have clear mappings to VSM concepts, but do not exclude entities simply because they lack an obvious mapping.
@{vsm_framework}
Instructions
- Read the source chapter carefully.
- Identify all distinct economic concepts, actors, mechanisms, and institutions.
- For each entity, produce a separate markdown document following the Economic Entity Schema v1.0.
- Each entity document must include:
- An H1 heading with the entity name
- A Definition section (20-150 words)
- A Source Chapter section citing the specific chapter
- A Context section describing where in the argument the entity appears
- An Economic Domain section classifying the entity
- Optionally include Smith's Original Wording (direct quote) and Modern Interpretation sections.
- Use neutral, analytical language throughout.
- Ensure each entity is distinct and self-contained.
Output Format
Output each entity as a separate markdown document, delimited by
--- ENTITY: <entity-name> --- markers.