dao-ai 0.1.7__tar.gz → 0.1.11__tar.gz

{dao_ai-0.1.7 → dao_ai-0.1.11}/.gitignore

@@ -278,3 +278,6 @@ mlruns/
 databricks.yaml
 
 .cursor/
+
+# Deployment directory for local source code
+deploy/

{dao_ai-0.1.7 → dao_ai-0.1.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.1.7
+Version: 0.1.11
 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
@@ -28,7 +28,7 @@ Requires-Python: >=3.11
 Requires-Dist: databricks-agents>=1.9.0
 Requires-Dist: databricks-langchain[memory]>=0.12.1
 Requires-Dist: databricks-mcp>=0.5.0
-Requires-Dist: databricks-sdk[openai]>=0.76.0
+Requires-Dist: databricks-sdk[openai]>=0.77.0
 Requires-Dist: ddgs>=9.10.0
 Requires-Dist: dspy>=2.6.27
 Requires-Dist: flashrank>=0.2.10
@@ -43,7 +43,7 @@ Requires-Dist: langgraph>=1.0.5
 Requires-Dist: langmem>=0.0.30
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp>=1.24.0
-Requires-Dist: mlflow>=3.8.1
+Requires-Dist: mlflow[databricks]>=3.8.1
 Requires-Dist: nest-asyncio>=1.6.0
 Requires-Dist: openevals>=0.1.3
 Requires-Dist: openpyxl>=3.1.5

dao_ai-0.1.11/app.yaml

@@ -0,0 +1,12 @@
+command: ["uv", "run", "python", "-m", "dao_ai.apps.server"]
+# Databricks Apps listen by default on port 8000
+
+env:
+  - name: MLFLOW_TRACKING_URI
+    value: "databricks"
+  - name: MLFLOW_REGISTRY_URI
+    value: "databricks-uc"
+  # Path to the dao-ai configuration file
+  # This can be set to a workspace path or local file path
+  - name: DAO_AI_CONFIG_PATH
+    value: "model_config.yaml"

{dao_ai-0.1.7 → dao_ai-0.1.11}/config/examples/02_mcp/filtered_mcp.yaml

@@ -85,8 +85,8 @@ tools:
         - execute_query        # Exact match
         - list_tables          # Exact match
         - describe_table       # Exact match
-        - get_*                # Pattern: all getters
-        - show_*               # Pattern: all show operations
+        - "get_*"              # Pattern: all getters
+        - "show_*"             # Pattern: all show operations
 
   # ---------------------------------------------------------------------------
   # Example 2: Exclude Dangerous Tools (Denylist)
@@ -104,11 +104,11 @@ tools:
       workspace_host: *workspace_host
       # Load all tools EXCEPT these dangerous ones
       exclude_tools:
-        - drop_*               # Block all drop operations
-        - delete_*             # Block all delete operations
-        - truncate_*           # Block all truncate operations
+        - "drop_*"             # Block all drop operations
+        - "delete_*"           # Block all delete operations
+        - "truncate_*"         # Block all truncate operations
         - execute_ddl          # Block DDL execution
-        - alter_*              # Block all alter operations
+        - "alter_*"            # Block all alter operations
 
   # ---------------------------------------------------------------------------
   # Example 3: Hybrid Filtering (Include + Exclude)
@@ -126,14 +126,14 @@ tools:
       workspace_host: *workspace_host
       # Start with these categories
       include_tools:
-        - query_*              # All query functions
-        - get_*                # All getter functions
-        - list_*               # All list functions
+        - "query_*"            # All query functions
+        - "get_*"              # All getter functions
+        - "list_*"             # All list functions
       # But exclude sensitive ones
       exclude_tools:
-        - *_sensitive          # Exclude anything with "_sensitive"
-        - *_admin              # Exclude admin functions
-        - get_secret_*         # Exclude secret getters
+        - "*_sensitive"        # Exclude anything with "_sensitive"
+        - "*_admin"            # Exclude admin functions
+        - "get_secret_*"       # Exclude secret getters
 
   # ---------------------------------------------------------------------------
   # Example 4: Pattern-Based Inclusion
@@ -151,10 +151,10 @@ tools:
       workspace_host: *workspace_host
       # Only read operations with patterns
       include_tools:
-        - query_*              # All queries
-        - list_*               # All lists
-        - describe_*           # All describe operations
-        - show_*               # All show operations
+        - "query_*"            # All queries
+        - "list_*"             # All lists
+        - "describe_*"         # All describe operations
+        - "show_*"             # All show operations
 
   # ---------------------------------------------------------------------------
   # Example 5: Maximum Security (Very Restrictive)
@@ -192,8 +192,8 @@ tools:
       workspace_host: *workspace_host
       # Allow everything except the really dangerous stuff
       exclude_tools:
-        - drop_*               # Can't drop anything
-        - truncate_*           # Can't truncate
+        - "drop_*"             # Can't drop anything
+        - "truncate_*"         # Can't truncate
         - execute_ddl          # Can't run arbitrary DDL
 
 # =============================================================================
@@ -295,17 +295,44 @@ agents:
 # APPLICATION CONFIGURATION
 # =============================================================================
 
-app_name: filtered_mcp_example
-entry_agent: safe_sql_agent
+app:
+  name: filtered_mcp_example              # Application name
+  log_level: INFO                         # Logging level (DEBUG, INFO, WARNING, ERROR)
+  registered_model:                       # MLflow registered model configuration
+    schema: *retail_schema                # Schema where model will be registered
+    name: filtered_mcp_example            # Model name in MLflow registry
+  agents:                                 # List of agents included in the system
+    - *safe_sql_agent                     # Safe SQL agent (read-only)
+    - *analyst_agent                      # Data analyst agent
+    - *dev_agent                          # Development agent
+    - *secure_agent                       # High-security agent
+    - *functions_agent                    # Functions agent
+  orchestration:                          # Agent orchestration configuration
+    swarm:                                # Supervisor orchestration pattern
+      model: *default_llm                 # LLM for routing decisions
+      # Agents will be automatically routed based on their capabilities
 
 # =============================================================================
 # USAGE NOTES
 # =============================================================================
 #
+# Deployment:
+#   databricks apps deploy dao-ai-filtered-mcp --source-dir . --config-file config/examples/02_mcp/filtered_mcp.yaml
+#
+# The app uses swarm orchestration to automatically route user queries to the
+# most appropriate agent based on their capabilities and tool access:
+#
+# - safe_sql_agent: Read-only SQL queries (allowlist of 5 safe operations)
+# - analyst_agent: Data analysis queries (query_*, list_*, describe_*, show_*)
+# - dev_agent: Development queries (all tools except dangerous DDL operations)
+# - secure_agent: Maximum security (only 3 specific tools)
+# - functions_agent: UC Functions access (filtered to exclude sensitive/admin)
+#
 # Testing Filters:
-# 1. Run with safe_sql_agent - try to call drop_table (should not be available)
-# 2. Run with dev_agent - verify you can query but not drop
-# 3. Run with secure_agent - verify only 3 tools are available
+# 1. Ask to query data → Routes to analyst_agent or safe_sql_agent
+# 2. Ask to drop a table → Routes to dev_agent, which will refuse (blocked)
+# 3. Ask in secure mode → Routes to secure_agent (only 3 tools available)
+# 4. Ask to call a function → Routes to functions_agent (sensitive functions blocked)
 #
 # Pattern Examples:
 # - "query_*" matches: query_sales, query_inventory, query_anything

{dao_ai-0.1.7 → dao_ai-0.1.11}/config/examples/15_complete_applications/hardware_store_lakebase.yaml

@@ -10,6 +10,20 @@
 # DATABRICKS SCHEMAS
 # =============================================================================
 # Define Unity Catalog schemas where data and functions will be stored
+
+
+variables:
+  client_id: &client_id
+    options:
+      - env: RETAIL_AI_DATABRICKS_CLIENT_ID      # Service principal client ID
+      - scope: retail_consumer_goods
+        secret: RETAIL_AI_DATABRICKS_CLIENT_ID
+  client_secret: &client_secret
+    options:
+      - env: RETAIL_AI_DATABRICKS_CLIENT_SECRET  # Service principal secret
+      - scope: retail_consumer_goods
+        secret: RETAIL_AI_DATABRICKS_CLIENT_SECRET
+
 schemas:
   retail_schema: &retail_schema
     catalog_name: retail_consumer_goods                    # Unity Catalog name
@@ -134,6 +148,8 @@ resources:
       instance_name: "retail-consumer-goods"  # Use instance_name for Databricks Lakebase
       description: "Database for agent memory and checkpoints" 
    
+      client_id: *client_id
+      client_secret: *client_secret
       on_behalf_of_user: false
 
 # =============================================================================

{dao_ai-0.1.7 → dao_ai-0.1.11}/databricks.yaml.template

@@ -16,6 +16,9 @@ variables:
     description: The job compute node type (cloud-specific, set per target)
   cloud:
     description: Cloud provider (azure, aws, gcp) - auto-detected or set per target
+  deployment_target:
+    description: Agent deployment target (model_serving or apps) - defaults to model_serving
+    default: model_serving
 
 resources:
   jobs:
@@ -83,6 +86,7 @@ resources:
             notebook_path: ./notebooks/05_deploy_agent.py
             base_parameters:
               config-path: ${var.config_path}
+              deployment-target: ${var.deployment_target}
           environment_key: dao-ai-env
         - task_key: run-evaluation
           depends_on:

{dao_ai-0.1.7 → dao_ai-0.1.11}/notebooks/05_deploy_agent.py

@@ -28,16 +28,23 @@ def find_yaml_files_os_walk(base_path: str) -> Sequence[str]:
 # COMMAND ----------
 
 dbutils.widgets.text(name="config-path", defaultValue="")
+dbutils.widgets.dropdown(
+    name="deployment-target",
+    choices=["", "model_serving", "apps"],
+    defaultValue="",
+)
 
 config_files: Sequence[str] = find_yaml_files_os_walk("../config")
 dbutils.widgets.dropdown(name="config-paths", choices=config_files, defaultValue=next(iter(config_files), ""))
 
 config_path: str | None = dbutils.widgets.get("config-path") or None
 project_path: str = dbutils.widgets.get("config-paths") or None
+deployment_target_str: str | None = dbutils.widgets.get("deployment-target") or None
 
 config_path: str = config_path or project_path
 
-print(config_path)
+print(f"Config path: {config_path}")
+print(f"Deployment target: {deployment_target_str or '(using config default)'}")
 
 # COMMAND ----------
 
@@ -93,10 +100,21 @@ nest_asyncio.apply()
 
 # COMMAND ----------
 
-from dao_ai.config import AppConfig
+from dao_ai.config import AppConfig, DeploymentTarget
 
 config: AppConfig = AppConfig.from_file(path=config_path)
 
+# Resolve deployment target from widget (hybrid resolution)
+# If widget is empty/None, deploy_agent() will use config.app.deployment_target or default
+deployment_target: DeploymentTarget | None = None
+if deployment_target_str:
+    deployment_target = DeploymentTarget(deployment_target_str)
+    print(f"Using widget-specified deployment target: {deployment_target.value}")
+elif config.app and config.app.deployment_target:
+    print(f"Using config file deployment target: {config.app.deployment_target.value}")
+else:
+    print("Using default deployment target: model_serving")
+
 # COMMAND ----------
 
 config.display_graph()
@@ -107,4 +125,4 @@ config.create_agent()
 
 # COMMAND ----------
 
-config.deploy_agent()
+config.deploy_agent(target=deployment_target)

{dao_ai-0.1.7 → dao_ai-0.1.11}/notebooks/99_scratchpad.py

@@ -618,7 +618,7 @@ result = reflection_app.invoke({"messages": example_query})
 
 # COMMAND ----------
 
-from agent_as_code import app
+from dao_ai.apps.model_serving import app
 
 
 # COMMAND ----------

{dao_ai-0.1.7 → dao_ai-0.1.11}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dao-ai"
-version = "0.1.7"
+version = "0.1.11"
 description = "DAO AI: A modular, multi-agent orchestration framework for complex AI workflows. Supports agent handoff, tool integration, and dynamic configuration via YAML."
 readme = "README.md"
 license = { text = "MIT" }
@@ -46,7 +46,7 @@ dependencies = [
     "databricks-agents>=1.9.0",
     "databricks-langchain[memory]>=0.12.1",
     "databricks-mcp>=0.5.0",
-    "databricks-sdk[openai]>=0.76.0",
+    "databricks-sdk[openai]>=0.77.0",
     "ddgs>=9.10.0",
     "dspy>=2.6.27",
     "flashrank>=0.2.10",
@@ -61,7 +61,7 @@ dependencies = [
     "langmem>=0.0.30",
     "loguru>=0.7.3",
     "mcp>=1.24.0",
-    "mlflow>=3.8.1",
+    "mlflow[databricks]>=3.8.1",
     "nest-asyncio>=1.6.0",
     "openevals>=0.1.3",
     "openpyxl>=3.1.5",

{dao_ai-0.1.7 → dao_ai-0.1.11}/requirements.txt

@@ -9,6 +9,9 @@ anthropic==0.75.0
 anyio==4.12.0
 asyncer==0.0.8
 attrs==25.4.0
+azure-core==1.37.0
+azure-storage-blob==12.28.0
+azure-storage-file-datalake==12.23.0
 backoff==2.2.1
 blinker==1.9.0
 boto3==1.42.16
@@ -30,7 +33,7 @@ databricks-agents==1.9.0
 databricks-ai-bridge==0.11.0
 databricks-langchain==0.12.1
 databricks-mcp==0.5.1
-databricks-sdk==0.76.0
+databricks-sdk==0.77.0
 dataclasses-json==0.6.7
 datasets==4.4.2
 ddgs==9.10.0
@@ -57,7 +60,12 @@ fsspec==2025.10.0
 gepa==0.0.22
 gitdb==4.0.12
 gitpython==3.1.45
+google-api-core==2.28.1
 google-auth==2.45.0
+google-cloud-core==2.5.0
+google-cloud-storage==3.7.0
+google-crc32c==1.8.0
+google-resumable-media==2.8.0
 googleapis-common-protos==1.72.0
 grandalf==0.8
 graphene==3.4.3
@@ -82,6 +90,7 @@ identify==2.6.15
 idna==3.11
 importlib-metadata==8.7.1
 iniconfig==2.3.0
+isodate==0.7.2
 itsdangerous==2.2.0
 jinja2==3.1.6
 jiter==0.12.0
@@ -152,6 +161,7 @@ pluggy==1.6.0
 pre-commit==4.5.1
 primp==0.15.0
 propcache==0.4.1
+proto-plus==1.27.0
 protobuf==6.33.2
 psycopg==3.3.2
 psycopg-binary==3.3.2

{dao_ai-0.1.7 → dao_ai-0.1.11}/schemas/model_config_schema.json

@@ -395,6 +395,18 @@
           "default": "3.12",
           "description": "Python version for Model Serving deployment. Defaults to 3.12 which is supported by Databricks Model Serving. This allows deploying from environments with different Python versions (e.g., Databricks Apps with 3.11).",
           "title": "Python Version"
+        },
+        "deployment_target": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/DeploymentTarget"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "description": "Default deployment target. If not specified, defaults to MODEL_SERVING. Can be overridden via CLI --target flag. Options: 'model_serving' or 'apps'."
         }
       },
       "required": [
@@ -1196,6 +1208,7 @@
     },
     "DatabricksAppModel": {
       "additionalProperties": false,
+      "description": "Configuration for a Databricks App resource.\n\nThe `name` is the unique instance name of the Databricks App within the workspace.\nThe `url` is dynamically retrieved from the workspace client by calling\n`apps.get(name)` and returning the app's URL.\n\nExample:\n    ```yaml\n    resources:\n      apps:\n        my_app:\n          name: my-databricks-app\n    ```",
       "properties": {
         "on_behalf_of_user": {
           "anyOf": [
@@ -1355,40 +1368,10 @@
         "name": {
           "title": "Name",
           "type": "string"
-        },
-        "url": {
-          "anyOf": [
-            {
-              "$ref": "#/$defs/CompositeVariableModel"
-            },
-            {
-              "$ref": "#/$defs/EnvironmentVariableModel"
-            },
-            {
-              "$ref": "#/$defs/SecretVariableModel"
-            },
-            {
-              "$ref": "#/$defs/PrimitiveVariableModel"
-            },
-            {
-              "type": "string"
-            },
-            {
-              "type": "integer"
-            },
-            {
-              "type": "number"
-            },
-            {
-              "type": "boolean"
-            }
-          ],
-          "title": "Url"
         }
       },
       "required": [
-        "name",
-        "url"
+        "name"
       ],
       "title": "DatabricksAppModel",
       "type": "object"
@@ -1501,6 +1484,15 @@
       "title": "DatasetModel",
       "type": "object"
     },
+    "DeploymentTarget": {
+      "description": "Target platform for agent deployment.",
+      "enum": [
+        "model_serving",
+        "apps"
+      ],
+      "title": "DeploymentTarget",
+      "type": "string"
+    },
     "Entitlement": {
       "enum": [
         "CAN_MANAGE",
@@ -2082,8 +2074,16 @@
           "title": "Pat"
         },
         "name": {
-          "title": "Name",
-          "type": "string"
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Name"
         },
         "description": {
           "anyOf": [
@@ -2128,7 +2128,6 @@
         }
       },
       "required": [
-        "name",
         "space_id"
       ],
       "title": "GenieRoomModel",
@@ -2935,6 +2934,17 @@
           "title": "Args",
           "type": "array"
         },
+        "app": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/DatabricksAppModel"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
         "connection": {
           "anyOf": [
             {
@@ -4932,6 +4942,7 @@
       "type": "object"
     },
     "WarehouseModel": {
+      "additionalProperties": false,
       "properties": {
         "on_behalf_of_user": {
           "anyOf": [
@@ -5089,8 +5100,16 @@
           "title": "Pat"
         },
         "name": {
-          "title": "Name",
-          "type": "string"
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Name"
         },
         "description": {
           "anyOf": [
@@ -5135,7 +5154,6 @@
         }
       },
       "required": [
-        "name",
         "warehouse_id"
       ],
       "title": "WarehouseModel",
@@ -5153,6 +5171,18 @@
   },
   "additionalProperties": false,
   "properties": {
+    "version": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Version"
+    },
     "variables": {
       "additionalProperties": {
         "anyOf": [

dao_ai-0.1.11/src/dao_ai/apps/__init__.py

@@ -0,0 +1,24 @@
+"""
+Databricks Apps deployment module for dao-ai.
+
+This subpackage contains all modules related to deploying dao-ai agents
+as Databricks Apps or Model Serving endpoints.
+
+Modules:
+    handlers: MLflow AgentServer request handlers (@invoke, @stream)
+    server: Entry point for Databricks Apps deployment
+    resources: Databricks App resource configuration generation
+    model_serving: Entry point for Databricks Model Serving deployment
+"""
+
+from dao_ai.apps.resources import (
+    generate_app_resources,
+    generate_app_yaml,
+    generate_sdk_resources,
+)
+
+__all__ = [
+    "generate_app_resources",
+    "generate_app_yaml",
+    "generate_sdk_resources",
+]

dao_ai-0.1.11/src/dao_ai/apps/handlers.py

@@ -0,0 +1,84 @@
+"""
+Agent request handlers for MLflow AgentServer.
+
+This module defines the invoke and stream handlers that are registered
+with the MLflow AgentServer. These handlers delegate to the ResponsesAgent
+created from the dao-ai configuration.
+
+The handlers use async methods (apredict, apredict_stream) to be compatible
+with both Databricks Model Serving and Databricks Apps environments.
+"""
+
+import os
+from typing import AsyncGenerator
+
+import mlflow
+from dotenv import load_dotenv
+from mlflow.genai.agent_server import invoke, stream
+from mlflow.types.responses import (
+    ResponsesAgentRequest,
+    ResponsesAgentResponse,
+    ResponsesAgentStreamEvent,
+)
+
+from dao_ai.config import AppConfig
+from dao_ai.logging import configure_logging
+from dao_ai.models import LanggraphResponsesAgent
+
+# Load environment variables from .env.local if it exists
+load_dotenv(dotenv_path=".env.local", override=True)
+
+# Configure MLflow
+mlflow.set_registry_uri("databricks-uc")
+mlflow.set_tracking_uri("databricks")
+mlflow.langchain.autolog()
+
+# Get config path from environment or use default
+config_path: str = os.environ.get("DAO_AI_CONFIG_PATH", "model_config.yaml")
+
+# Load configuration using AppConfig.from_file (consistent with CLI, notebook, builder)
+config: AppConfig = AppConfig.from_file(config_path)
+
+# Configure logging
+if config.app and config.app.log_level:
+    configure_logging(level=config.app.log_level)
+
+# Create the ResponsesAgent - cast to LanggraphResponsesAgent to access async methods
+_responses_agent: LanggraphResponsesAgent = config.as_responses_agent()  # type: ignore[assignment]
+
+
+@invoke()
+async def non_streaming(request: ResponsesAgentRequest) -> ResponsesAgentResponse:
+    """
+    Handle non-streaming requests by delegating to the ResponsesAgent.
+
+    Uses the async apredict() method for compatibility with both
+    Model Serving and Apps environments.
+
+    Args:
+        request: The incoming ResponsesAgentRequest
+
+    Returns:
+        ResponsesAgentResponse with the complete output
+    """
+    return await _responses_agent.apredict(request)
+
+
+@stream()
+async def streaming(
+    request: ResponsesAgentRequest,
+) -> AsyncGenerator[ResponsesAgentStreamEvent, None]:
+    """
+    Handle streaming requests by delegating to the ResponsesAgent.
+
+    Uses the async apredict_stream() method for compatibility with both
+    Model Serving and Apps environments.
+
+    Args:
+        request: The incoming ResponsesAgentRequest
+
+    Yields:
+        ResponsesAgentStreamEvent objects as they are generated
+    """
+    async for event in _responses_agent.apredict_stream(request):
+        yield event

dao_ai-0.1.11/src/dao_ai/apps/model_serving.py

@@ -0,0 +1,29 @@
+# Apply nest_asyncio FIRST before any other imports
+# This allows dao-ai's async/sync patterns to work in Model Serving
+# where there may already be an event loop running (e.g., notebook context)
+import nest_asyncio
+
+nest_asyncio.apply()
+
+import mlflow  # noqa: E402
+from mlflow.models import ModelConfig  # noqa: E402
+from mlflow.pyfunc import ResponsesAgent  # noqa: E402
+
+from dao_ai.config import AppConfig  # noqa: E402
+from dao_ai.logging import configure_logging  # noqa: E402
+
+mlflow.set_registry_uri("databricks-uc")
+mlflow.set_tracking_uri("databricks")
+
+mlflow.langchain.autolog()
+
+model_config: ModelConfig = ModelConfig()
+config: AppConfig = AppConfig(**model_config.to_dict())
+
+log_level: str = config.app.log_level
+
+configure_logging(level=log_level)
+
+app: ResponsesAgent = config.as_responses_agent()
+
+mlflow.models.set_model(app)