aditya
41f90afaf9
Add 5 example actor configurations demonstrating all actor types: Simple Examples: - simple_llm.yaml: Basic LLM actor with code review prompt - llm_with_tools.yaml: LLM with mix of tool references and inline tools - tool_collection.yaml: Tool-only actor (no LLM) Graph Examples: - simple_graph.yaml: 3-node linear workflow (extract → analyze → summarize) - graph_workflow.yaml: Complex TDD workflow with 10 nodes * Conditional routing based on test results * Retry logic with max attempts * Subgraph composition (code review) * Error escalation paths Each example demonstrates: - Proper namespaced naming (namespace/name) - Type-specific configurations - Context and memory settings - Environment variable usage - Tool definitions (inline and references) Part 5 of C1.schema implementation (Actor YAML Schema Models).
79 lines
1.8 KiB
YAML
79 lines
1.8 KiB
YAML
# Simple Graph Actor - Sequential Processing
|
|
# Demonstrates a simple 3-node graph with linear execution
|
|
|
|
name: workflows/document_processor
|
|
type: graph
|
|
description: Simple document processing workflow (extract → analyze → summarize)
|
|
version: "1.0"
|
|
|
|
# LLM model
|
|
model: gpt-3.5-turbo
|
|
|
|
# Graph topology
|
|
route:
|
|
nodes:
|
|
# Node 1: Extract text from document
|
|
- id: extractor
|
|
type: tool
|
|
name: Text Extractor
|
|
description: Extracts text from various document formats
|
|
config:
|
|
tool_name: documents/extract_text
|
|
parameters:
|
|
formats:
|
|
- pdf
|
|
- docx
|
|
- txt
|
|
|
|
# Node 2: Analyze content
|
|
- id: analyzer
|
|
type: agent
|
|
name: Content Analyzer
|
|
description: Analyzes document structure and content
|
|
config:
|
|
model: gpt-3.5-turbo
|
|
prompt: |
|
|
Analyze the document content and identify:
|
|
- Main topics and themes
|
|
- Key entities (people, places, organizations)
|
|
- Sentiment and tone
|
|
- Document structure
|
|
tools:
|
|
- analysis/extract_entities
|
|
- analysis/sentiment_analysis
|
|
|
|
# Node 3: Generate summary
|
|
- id: summarizer
|
|
type: agent
|
|
name: Summarizer
|
|
description: Creates concise summary of document
|
|
config:
|
|
model: gpt-3.5-turbo
|
|
prompt: |
|
|
Create a concise summary of the document including:
|
|
- Main points (3-5 bullet points)
|
|
- Key findings
|
|
- Actionable insights
|
|
Keep it under 200 words.
|
|
|
|
# Linear edges
|
|
edges:
|
|
- from_node: extractor
|
|
to_node: analyzer
|
|
- from_node: analyzer
|
|
to_node: summarizer
|
|
|
|
# Entry and exit
|
|
entry_node: extractor
|
|
exit_nodes:
|
|
- summarizer
|
|
|
|
# Context settings
|
|
context_view: executor
|
|
memory:
|
|
enabled: true
|
|
max_messages: 10
|
|
|
|
context:
|
|
max_context_tokens: 4000
|