dao-ai 0.0.15__tar.gz → 0.0.17__tar.gz

{dao_ai-0.0.15 → dao_ai-0.0.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.0.15
+Version: 0.0.17
 Summary: DAO AI: A modular, multi-agent orchestration framework for complex AI workflows. Supports agent handoff, tool integration, and dynamic configuration via YAML.
 Project-URL: Homepage, https://github.com/natefleming/dao-ai
 Project-URL: Documentation, https://natefleming.github.io/dao-ai
@@ -30,6 +30,7 @@ Requires-Dist: databricks-sdk[openai]>=0.55.0
 Requires-Dist: duckduckgo-search>=8.0.2
 Requires-Dist: grandalf>=0.8
 Requires-Dist: langchain-mcp-adapters>=0.1.9
+Requires-Dist: langchain-tavily>=0.2.11
 Requires-Dist: langchain>=0.3.27
 Requires-Dist: langgraph-checkpoint-postgres>=2.0.23
 Requires-Dist: langgraph-supervisor>=0.0.29

dao_ai-0.0.17/config/examples/deep_research.yaml

@@ -0,0 +1,237 @@
+# yaml-language-server: $schema=../../schemas/model_config_schema.json
+
+variables:
+  tavily_search_key: &tavily_search_key                                                                                       
+    options:
+      - env: TAVILY_API_KEY                         
+      - scope: retail_consumer_goods                    
+        secret: TAVILY_API_KEY                      
+
+schemas:
+  executive_assistant_schema: &executive_assistant_schema
+    catalog_name: retail_consumer_goods                  
+    schema_name: store_ops                
+
+resources:
+  llms:
+
+    fast_llm: &fast_llm
+      name: databricks-meta-llama-3-1-8b-instruct 
+      temperature: 0.1                              
+      max_tokens: 8192                             
+
+    tool_calling_llm: &tool_calling_llm
+      name: databricks-claude-3-7-sonnet
+      temperature: 0.1
+      max_tokens: 8192
+      fallbacks:                                   
+        - databricks-meta-llama-3-3-70b-instruct
+
+    # LLM for complex reasoning tasks
+    reasoning_llm: &reasoning_llm
+      name: databricks-claude-3-7-sonnet
+      temperature: 0.1
+      max_tokens: 8192
+
+    deep_reasoning_llm: &deep_reasoning_llm
+      name: databricks-claude-sonnet-4
+      temperature: 0.1
+      max_tokens: 8192
+      fallbacks: 
+        - databricks-claude-3-7-sonnet
+
+    judge_llm: &judge_llm
+      name: databricks-claude-3-7-sonnet
+      temperature: 0.5                            
+      max_tokens: 8192
+
+    embedding_model: &embedding_model
+      name: databricks-gte-large-en              
+
+
+  tables:
+    employee_performance:
+      schema: *executive_assistant_schema                        
+      name: employee_performance                              
+    
+    products:
+      schema: *executive_assistant_schema
+      name: products
+
+    inventory: 
+      schema: *executive_assistant_schema
+      name: inventory
+
+    customers: 
+      schema: *executive_assistant_schema
+      name: customers
+
+    managers:
+      schema: *executive_assistant_schema
+      name: managers
+
+    employee_tasks: 
+      schema: *executive_assistant_schema
+      name: employee_tasks
+
+    appointments: 
+      schema: *executive_assistant_schema
+      name: appointments
+
+    evaluation: 
+      schema: *executive_assistant_schema
+      name: evaluation
+
+
+  functions:
+
+    find_inventory_by_sku: &find_inventory_by_sku
+      schema: *executive_assistant_schema
+      name: find_inventory_by_sku
+
+    find_inventory_by_upc: &find_inventory_by_upc
+      schema: *executive_assistant_schema
+      name: find_inventory_by_upc     
+    
+    find_product_by_sku: &find_product_by_sku
+      schema: *executive_assistant_schema
+      name: find_product_by_sku     
+
+    find_product_by_upc: &find_product_by_upc
+      schema: *executive_assistant_schema
+      name: find_product_by_upc     
+
+    find_store_by_number: &find_store_by_number
+      schema: *executive_assistant_schema
+      name: find_store_by_number     
+    
+    find_store_inventory_by_sku: &find_store_inventory_by_sku
+      schema: *executive_assistant_schema
+      name: find_store_inventory_by_sku     
+
+    find_store_inventory_by_upc: &find_store_inventory_by_upc
+      schema: *executive_assistant_schema
+      name: find_store_inventory_by_upc
+
+  genie_rooms:
+    executive_assistant_genie_room: &executive_assistant_genie_room
+      name: "Executive Assistant Genie Room"                       
+      description: "A room for Genie agents to interact" 
+      space_id: 01f05dd06c421ad6b522bf7a517cf6d2          
+
+
+tools:
+  executive_assistant_genie_tool: &executive_assistant_genie_tool
+    name: executive_assistant_genie_tool
+    function:
+      type: factory                                 
+      name: dao_ai.tools.create_genie_tool     
+      args:                                     
+        name: executive_assistant_genie_tool
+        description: Query the data warehouse for customer KPIs, business metrics, employee performance, inventory data, and other operational insights. Use this tool multiple times as needed to gather comprehensive data for executive-level analysis and recommendations.
+        genie_room: *executive_assistant_genie_room            
+
+
+  tavily_search_tool: &tavily_search_tool
+    name: tavily_search_tool
+    function:
+      type: factory
+      name: langchain_tavily.TavilySearch
+      args:
+        max_results: 5
+        topic: general
+        search_depth: advanced
+        include_domains: ~
+        exclude_domains: ~
+
+agents:
+  executive_assistant_genie: &executive_assistant_genie
+    name: executive_assistant_genie                    
+    description: "Executive Assistant Genie Agent"
+    model: *reasoning_llm                            
+    tools:                                        
+      - *executive_assistant_genie_tool
+      - *tavily_search_tool
+    prompt: |
+      You are an executive-level data analyst and strategic advisor for a retail consumer goods company. Your primary audience is C-suite executives and senior management who need actionable insights about business performance, customer KPIs, and strategic recommendations.
+
+      ## Your Core Responsibilities:
+      
+      ### 1. Customer KPI Analysis & Reporting
+      - Analyze customer acquisition, retention, lifetime value, and churn metrics
+      - Track customer satisfaction scores, NPS, and engagement metrics
+      - Monitor customer segment performance and behavior patterns
+      - Provide trend analysis and year-over-year comparisons
+      - Identify customer pain points and opportunities
+      
+      ### 2. Business Performance Insights
+      - Monitor revenue, profit margins, and growth trajectories
+      - Analyze inventory turnover, stockouts, and supply chain efficiency
+      - Track employee performance and operational KPIs
+      - Evaluate store performance across locations
+      - Assess product performance and category trends
+      
+      ### 3. Strategic Reasoning & Recommendations
+      - Provide context and root cause analysis for performance changes
+      - Identify correlations between different business metrics
+      - Suggest data-driven action plans and strategic initiatives
+      - Recommend resource allocation and investment priorities
+      - Highlight risks and opportunities based on data trends
+      
+      ## How to Operate:
+      
+      ### Tool Usage Strategy
+      - **Use multiple tool calls** when needed to build comprehensive answers
+      - Query different data sources to cross-validate insights
+      - Drill down into specific metrics when initial results show concerning trends
+      - Always verify assumptions with data before making recommendations
+
+      ### Communication Style
+      - **Executive Summary First**: Lead with key findings and recommendations
+      - **Data-Driven**: Support all claims with specific metrics and evidence
+      - **Action-Oriented**: Provide clear, implementable next steps
+      - **Risk-Aware**: Highlight potential challenges and mitigation strategies
+      - **Strategic Context**: Connect findings to broader business objectives
+      
+      ### Response Structure
+      1. **Executive Summary** (2-3 bullet points of key insights)
+      2. **Key Metrics & Analysis** (specific data points with context)
+      3. **Root Cause Analysis** (why trends are occurring)
+      4. **Strategic Recommendations** (actionable next steps)
+      5. **Risk Assessment** (potential challenges and opportunities)
+      
+      ## Guidelines:
+      
+      - Always query the data warehouse using your genie tool to get current, accurate information
+      - Make multiple queries if needed to build a complete picture
+      - Translate technical metrics into business impact language
+      - Provide both short-term tactical and long-term strategic recommendations
+      - When data shows concerning trends, immediately investigate potential causes
+      - Use industry benchmarks and best practices in your recommendations when relevant
+      - Be proactive in identifying trends before they become problems
+      
+      Remember: You are trusted advisor to senior leadership. Your insights directly influence major business decisions, resource allocation, and strategic direction. Ensure your analysis is thorough, your reasoning is sound, and your recommendations are actionable.
+
+
+app:
+  name: executive_assistant_agent                        
+  description: "An executive assistant application"
+  log_level: DEBUG                                  
+  registered_model:                                
+    schema: *executive_assistant_schema                        
+    name: executive_assistant_agent                          
+  endpoint_name: executive_assistant_agent    
+  environment_vars: 
+    TAVILY_API_KEY: "{{secrets/retail_consumer_goods/TAVILY_API_KEY}}" 
+  tags:                                            
+    business: rcg                                 
+    streaming: true                                
+  permissions:                                     
+    - principals: [users]                         
+      entitlements:
+        - CAN_QUERY                               
+  agents:                                        
+    - *executive_assistant_genie                                      
+  orchestration:                                  
+    swarm:                                    
+      model: *fast_llm                           

dao_ai-0.0.17/config/examples/executive_assistant.yaml

@@ -0,0 +1,239 @@
+# yaml-language-server: $schema=../../schemas/model_config_schema.json
+
+variables:
+  tavily_search_key: &tavily_search_key                                                                                       
+    options:
+      - env: TAVILY_API_KEY                         
+      - scope: retail_consumer_goods                    
+        secret: TAVILY_API_KEY                      
+
+schemas:
+  executive_assistant_schema: &executive_assistant_schema
+    catalog_name: retail_consumer_goods                  
+    schema_name: store_ops                
+
+resources:
+  llms:
+
+    fast_llm: &fast_llm
+      name: databricks-meta-llama-3-1-8b-instruct 
+      temperature: 0.1                              
+      max_tokens: 8192                             
+
+    tool_calling_llm: &tool_calling_llm
+      name: databricks-claude-3-7-sonnet
+      temperature: 0.1
+      max_tokens: 8192
+      fallbacks:                                   
+        - databricks-meta-llama-3-3-70b-instruct
+
+    # LLM for complex reasoning tasks
+    reasoning_llm: &reasoning_llm
+      name: databricks-claude-3-7-sonnet
+      temperature: 0.1
+      max_tokens: 8192
+
+    deep_reasoning_llm: &deep_reasoning_llm
+      name: databricks-claude-sonnet-4
+      temperature: 0.1
+      max_tokens: 8192
+      fallbacks: 
+        - databricks-claude-3-7-sonnet
+
+    judge_llm: &judge_llm
+      name: databricks-claude-3-7-sonnet
+      temperature: 0.5                            
+      max_tokens: 8192
+
+    embedding_model: &embedding_model
+      name: databricks-gte-large-en              
+
+
+  tables:
+    employee_performance:
+      schema: *executive_assistant_schema                        
+      name: employee_performance                              
+    
+    products:
+      schema: *executive_assistant_schema
+      name: products
+
+    inventory: 
+      schema: *executive_assistant_schema
+      name: inventory
+
+    customers: 
+      schema: *executive_assistant_schema
+      name: customers
+
+    managers:
+      schema: *executive_assistant_schema
+      name: managers
+
+    employee_tasks: 
+      schema: *executive_assistant_schema
+      name: employee_tasks
+
+    appointments: 
+      schema: *executive_assistant_schema
+      name: appointments
+
+    evaluation: 
+      schema: *executive_assistant_schema
+      name: evaluation
+
+
+  functions:
+
+    find_inventory_by_sku: &find_inventory_by_sku
+      schema: *executive_assistant_schema
+      name: find_inventory_by_sku
+
+    find_inventory_by_upc: &find_inventory_by_upc
+      schema: *executive_assistant_schema
+      name: find_inventory_by_upc     
+    
+    find_product_by_sku: &find_product_by_sku
+      schema: *executive_assistant_schema
+      name: find_product_by_sku     
+
+    find_product_by_upc: &find_product_by_upc
+      schema: *executive_assistant_schema
+      name: find_product_by_upc     
+
+    find_store_by_number: &find_store_by_number
+      schema: *executive_assistant_schema
+      name: find_store_by_number     
+    
+    find_store_inventory_by_sku: &find_store_inventory_by_sku
+      schema: *executive_assistant_schema
+      name: find_store_inventory_by_sku     
+
+    find_store_inventory_by_upc: &find_store_inventory_by_upc
+      schema: *executive_assistant_schema
+      name: find_store_inventory_by_upc
+
+  genie_rooms:
+    executive_assistant_genie_room: &executive_assistant_genie_room
+      name: "Executive Assistant Genie Room"                       
+      description: "A room for Genie agents to interact" 
+      space_id: 01f05dd06c421ad6b522bf7a517cf6d2          
+
+
+tools:
+  executive_assistant_genie_tool: &executive_assistant_genie_tool
+    name: executive_assistant_genie_tool
+    function:
+      type: factory                                 
+      name: dao_ai.tools.create_genie_tool     
+      args:                                     
+        name: executive_assistant_genie_tool
+        description: Query the data warehouse for customer KPIs, business metrics, employee performance, inventory data, and other operational insights. Use this tool multiple times as needed to gather comprehensive data for executive-level analysis and recommendations.
+        genie_room: *executive_assistant_genie_room            
+
+
+  tavily_search_tool: &tavily_search_tool
+    name: tavily_search_tool
+    function:
+      type: factory
+      name: langchain_tavily.TavilySearch
+      args:
+        max_results: 5
+        topic: general
+        search_depth: advanced
+        include_domains: ~
+        exclude_domains: ~
+
+agents:
+  executive_assistant_genie: &executive_assistant_genie
+    name: executive_assistant_genie                    
+    description: "Executive Assistant Genie Agent"
+    model: *reasoning_llm                            
+    tools:                                        
+      - *executive_assistant_genie_tool
+      - *tavily_search_tool
+    prompt: |
+      You are an executive-level data analyst and strategic advisor for a retail consumer goods company. Your primary audience is C-suite executives and senior management who need actionable insights about business performance, customer KPIs, and strategic recommendations.
+
+      ## Your Core Responsibilities:
+      
+      ### 1. Customer KPI Analysis & Reporting
+      - Analyze customer acquisition, retention, lifetime value, and churn metrics
+      - Track customer satisfaction scores, NPS, and engagement metrics
+      - Monitor customer segment performance and behavior patterns
+      - Provide trend analysis and year-over-year comparisons
+      - Identify customer pain points and opportunities
+      
+      ### 2. Business Performance Insights
+      - Monitor revenue, profit margins, and growth trajectories
+      - Analyze inventory turnover, stockouts, and supply chain efficiency
+      - Track employee performance and operational KPIs
+      - Evaluate store performance across locations
+      - Assess product performance and category trends
+      
+      ### 3. Strategic Reasoning & Recommendations
+      - Provide context and root cause analysis for performance changes
+      - Identify correlations between different business metrics
+      - Suggest data-driven action plans and strategic initiatives
+      - Recommend resource allocation and investment priorities
+      - Highlight risks and opportunities based on data trends
+      
+      ## How to Operate:
+      
+      ### Tool Usage Strategy
+      - **Use multiple tool calls** when needed to build comprehensive answers
+      - Query different data sources to cross-validate insights
+      - Drill down into specific metrics when initial results show concerning trends
+      - Always verify assumptions with data before making recommendations
+
+      ### Communication Style
+      - **Executive Summary First**: Lead with key findings and recommendations
+      - **Data-Driven**: Support all claims with specific metrics and evidence
+      - **Action-Oriented**: Provide clear, implementable next steps
+      - **Risk-Aware**: Highlight potential challenges and mitigation strategies
+      - **Strategic Context**: Connect findings to broader business objectives
+      
+      ### Response Structure
+      1. **Executive Summary** (2-3 bullet points of key insights)
+      2. **Key Metrics & Analysis** (specific data points with context)
+      3. **Root Cause Analysis** (why trends are occurring)
+      4. **Strategic Recommendations** (actionable next steps)
+      5. **Risk Assessment** (potential challenges and opportunities)
+      
+      ## Guidelines:
+      
+      - Always query the data warehouse using your genie tool to get current, accurate information
+      - Make multiple queries if needed to build a complete picture
+      - Translate technical metrics into business impact language
+      - Provide both short-term tactical and long-term strategic recommendations
+      - When data shows concerning trends, immediately investigate potential causes
+      - Use industry benchmarks and best practices in your recommendations when relevant
+      - Be proactive in identifying trends before they become problems
+      
+      Remember: You are trusted advisor to senior leadership. Your insights directly influence major business decisions, resource allocation, and strategic direction. Ensure your analysis is thorough, your reasoning is sound, and your recommendations are actionable.
+
+
+app:
+  name: executive_assistant_agent                        
+  description: "An executive assistant application"
+  log_level: DEBUG                                  
+  registered_model:                                
+    schema: *executive_assistant_schema                        
+    name: executive_assistant_agent                          
+  endpoint_name: executive_assistant_agent    
+  environment_vars: 
+    TAVILY_API_KEY: "{{secrets/retail_consumer_goods/TAVILY_API_KEY}}" 
+  tags:                                            
+    business: rcg                                 
+    streaming: true                                
+  permissions:                                     
+    - principals: [users]                         
+      entitlements:
+        - CAN_QUERY                               
+  agents:                                        
+    - *executive_assistant_genie                                      
+  orchestration:                                  
+    swarm:                                    
+      model: *fast_llm                           
+
+

dao_ai-0.0.17/examples/deep_research/examples.yaml

@@ -0,0 +1,38 @@
+# DAIS Examples for Retail AI Agent System
+# Extracted from retail_ai.orig/notebooks/agent_config.yaml
+# These examples demonstrate various agent interactions and use cases
+
+examples:
+  comprehensive_executive_research:
+    messages:
+      - role: user
+        content: |
+          I need a comprehensive executive research report analyzing our Q3 2025 performance and strategic positioning. Please conduct a deep dive analysis covering:
+
+          **Core Analysis Areas:**
+          1. **Customer KPI Performance**: Analyze customer acquisition cost (CAC), lifetime value (LTV), churn rates, retention metrics, Net Promoter Score (NPS), and customer satisfaction trends over the past 12 months
+          2. **Financial Performance**: Examine revenue growth, margin trends, profitability metrics, cash flow patterns, and ROI on key initiatives
+          3. **Operational Efficiency**: Review inventory turnover, productivity ratios, supply chain performance, and operational cost trends
+          4. **Market Position**: Assess our competitive standing, market share trends, industry benchmarks, and external market dynamics affecting our business
+
+          **Strategic Questions to Address:**
+          - Where are we underperforming relative to industry benchmarks and why?
+          - What are the top 3 strategic opportunities for growth in the next 6-12 months?
+          - What operational improvements could deliver the highest ROI?
+          - How do current market trends impact our strategic priorities?
+          - What are the financial implications of recommended strategic initiatives?
+
+          **Deliverable Requirements:**
+          - Executive summary with 3-4 key strategic insights
+          - Integrated analysis across all business dimensions
+          - Prioritized strategic recommendations with clear rationale
+          - Implementation roadmap with timelines and resource requirements
+          - Risk assessment and mitigation strategies
+          - Success metrics for tracking progress
+
+          Please ensure the analysis is comprehensive, data-driven, and provides actionable insights suitable for C-suite decision-making. I expect this to involve coordination across your specialist teams to deliver a cohesive strategic narrative.
+    custom_inputs:
+      configurable:
+        thread_id: "1"
+        user_id: "ali_ghodsi"
+        store_num: 101

dao_ai-0.0.17/examples/executive_assistant/examples.yaml

@@ -0,0 +1,14 @@
+# DAIS Examples for Retail AI Agent System
+# Extracted from retail_ai.orig/notebooks/agent_config.yaml
+# These examples demonstrate various agent interactions and use cases
+
+examples:
+  average_sales_percentage:
+    messages:
+      - role: user
+        content: "Hey Assistant, What is the average sales achievement percentage for employees?"
+    custom_inputs:
+      configurable:
+        thread_id: "1"
+        user_id: "ali_ghodsi"
+        store_num: 101

{dao_ai-0.0.15 → dao_ai-0.0.17}/examples/hardware_store/examples.yaml

@@ -6,7 +6,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     inventory_example:
@@ -16,7 +16,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     comparison_example:
@@ -26,7 +26,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     comparison_image_example:
@@ -39,7 +39,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     general_example:
@@ -49,7 +49,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     diy_example:
@@ -59,7 +59,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 123
 
     orders_example:
@@ -69,7 +69,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     product_example:
@@ -79,7 +79,7 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887
 
     product_image_example:
@@ -91,5 +91,5 @@
       custom_inputs:
         configurable:
           thread_id: "1"
-          user_id: nate.fleming
+          user_id: john_smith
           store_num: 87887

{dao_ai-0.0.15 → dao_ai-0.0.17}/notebooks/05_agent_as_code_driver.py

@@ -49,6 +49,12 @@ print("\n".join(pip_requirements))
 
 # COMMAND ----------
 
+from dotenv import find_dotenv, load_dotenv
+
+_ = load_dotenv(find_dotenv())
+
+# COMMAND ----------
+
 import nest_asyncio
 nest_asyncio.apply()
 
@@ -66,7 +72,6 @@ config.display_graph()
 
 config.create_agent()
 
-
 # COMMAND ----------
 
 config.deploy_agent()

{dao_ai-0.0.15 → dao_ai-0.0.17}/notebooks/06_run_evaluation.py

@@ -14,6 +14,12 @@ print(config_path)
 
 # COMMAND ----------
 
+from dotenv import find_dotenv, load_dotenv
+
+_ = load_dotenv(find_dotenv())
+
+# COMMAND ----------
+
 # DBTITLE 1,Add Source Directory to System Path
 import sys
 

{dao_ai-0.0.15 → dao_ai-0.0.17}/notebooks/08_run_examples.py

@@ -38,10 +38,7 @@ pprint(config_path)
 
 import sys
 import mlflow
-from langgraph.graph.state import CompiledStateGraph
 from mlflow.pyfunc import ChatModel
-from dao_ai.graph import create_dao_ai_graph
-from dao_ai.models import create_agent 
 from dao_ai.config import AppConfig
 
 from loguru import logger

{dao_ai-0.0.15 → dao_ai-0.0.17}/notebooks/09_evaluate_inferences.py

@@ -10,6 +10,12 @@ print(config_path)
 
 # COMMAND ----------
 
+from dotenv import find_dotenv, load_dotenv
+
+_ = load_dotenv(find_dotenv())
+
+# COMMAND ----------
+
 import sys
 
 sys.path.insert(0, "../src")