Tim Olson
d41fcd0499
- Add model-tags parser for @Tag syntax in chat messages - Support Anthropic models (Sonnet, Haiku, Opus) via @tag - Remove Qdrant vector database from infrastructure and configs - Simplify license model config to use null fallbacks - Add greeting stream after model switch via @tag - Fix protobuf field names to camelCase for v7 compatibility - Add 429 rate limit retry logic with exponential backoff - Remove RAG references from agent harness documentation
2.4 KiB
2.4 KiB
Dexorder Knowledge Base
This directory contains global knowledge documents that are automatically loaded into the agent's context at startup.
Structure
- platform/: Platform architecture and capabilities
- trading/: Trading concepts and fundamentals
- indicators/: Indicator development and usage
- strategies/: Strategy development and patterns
Document Format
Documents should be in Markdown format with:
- Clear headings for chunking
- Optional YAML frontmatter for tags
- Code examples where relevant
- Cross-references to other docs
Frontmatter Fields
description (required) — One or two sentences describing what the article covers. This is injected into every agent's system prompt as a KB catalog so agents know what to look up without making an extra tool call.
tags (optional) — List of topic tags for categorization.
Example with Frontmatter
---
description: "Patterns for writing custom Python indicator scripts that compute values from OHLCV data and plot live on the chart."
tags: [indicators, python, development]
---
# Custom Indicator Development
Content here...
How It Works
- At gateway startup, the DocumentLoader scans this directory
- Each markdown file is chunked by headers (max ~1000 tokens per chunk)
- Content hash tracking enables incremental updates
Updating Documents
During Development
- Edit markdown files
- Restart gateway or call reload endpoint:
POST /admin/reload-knowledge
In Production
- Update markdown files in git
- Deploy new version
- Gateway will detect changes and update vectors automatically
Adding New Documents
- Create markdown file in appropriate subdirectory
- Use clear section headers (##, ###) for automatic chunking
- Include practical examples and code samples
- Add tags in frontmatter if using complex categorization
- Restart gateway or reload knowledge
Best Practices
- Keep chunks focused: Each section should cover one topic
- Use examples: Code samples and practical examples help
- Link concepts: Reference other docs for deeper dives
- Update regularly: Keep knowledge current with platform changes
- Test queries: Verify RAG retrieves relevant chunks
Maintenance
The DocumentLoader tracks:
- Content hashes for change detection
- Number of chunks per document
- Last update timestamps
Check logs for load statistics:
Knowledge documents loaded: { loaded: 5, updated: 2, skipped: 3 }