dao-ai 0.1.2__tar.gz → 0.1.4__tar.gz

{dao_ai-0.1.2 → dao_ai-0.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.1.2
+Version: 0.1.4
 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
@@ -79,7 +79,7 @@ Description-Content-Type: text/markdown
 
 # DAO: Declarative Agent Orchestration
 
-[![Version](https://img.shields.io/badge/version-0.1.0-blue.svg)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.1.2-blue.svg)](CHANGELOG.md)
 [![Python](https://img.shields.io/badge/python-3.11+-green.svg)](https://www.python.org/)
 [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 
@@ -293,6 +293,16 @@ This single command:
 3. Deploys it to Databricks
 4. Creates a serving endpoint
 
+**Deploying to a specific workspace:**
+
+```bash
+# Deploy to AWS workspace
+dao-ai bundle --deploy --run -c config/my_agent.yaml --profile aws-field-eng
+
+# Deploy to Azure workspace
+dao-ai bundle --deploy --run -c config/my_agent.yaml --profile azure-retail
+```
+
 **Step 5: Interact with your agent**
 
 Once deployed, you can chat with your agent using Python:
@@ -422,10 +432,34 @@ dao-ai graph -c config/my_config.yaml -o workflow.png
 # Deploy with Databricks Asset Bundles
 dao-ai bundle --deploy --run -c config/my_config.yaml
 
+# Deploy to a specific workspace (multi-cloud support)
+dao-ai bundle --deploy -c config/my_config.yaml --profile aws-field-eng
+dao-ai bundle --deploy -c config/my_config.yaml --profile azure-retail
+
 # Interactive chat with agent
 dao-ai chat -c config/my_config.yaml
 ```
 
+### Multi-Cloud Deployment
+
+DAO AI supports deploying to Azure, AWS, and GCP workspaces with automatic cloud detection:
+
+```bash
+# Deploy to AWS workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile aws-prod
+
+# Deploy to Azure workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile azure-prod
+
+# Deploy to GCP workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile gcp-prod
+```
+
+The CLI automatically:
+- Detects the cloud provider from your profile's workspace URL
+- Selects appropriate compute node types for each cloud
+- Creates isolated deployment state per profile
+
 👉 **Learn more:** [CLI Reference Documentation](docs/cli-reference.md)
 
 ---

{dao_ai-0.1.2 → dao_ai-0.1.4}/README.md

@@ -1,6 +1,6 @@
 # DAO: Declarative Agent Orchestration
 
-[![Version](https://img.shields.io/badge/version-0.1.0-blue.svg)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.1.2-blue.svg)](CHANGELOG.md)
 [![Python](https://img.shields.io/badge/python-3.11+-green.svg)](https://www.python.org/)
 [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 
@@ -214,6 +214,16 @@ This single command:
 3. Deploys it to Databricks
 4. Creates a serving endpoint
 
+**Deploying to a specific workspace:**
+
+```bash
+# Deploy to AWS workspace
+dao-ai bundle --deploy --run -c config/my_agent.yaml --profile aws-field-eng
+
+# Deploy to Azure workspace
+dao-ai bundle --deploy --run -c config/my_agent.yaml --profile azure-retail
+```
+
 **Step 5: Interact with your agent**
 
 Once deployed, you can chat with your agent using Python:
@@ -343,10 +353,34 @@ dao-ai graph -c config/my_config.yaml -o workflow.png
 # Deploy with Databricks Asset Bundles
 dao-ai bundle --deploy --run -c config/my_config.yaml
 
+# Deploy to a specific workspace (multi-cloud support)
+dao-ai bundle --deploy -c config/my_config.yaml --profile aws-field-eng
+dao-ai bundle --deploy -c config/my_config.yaml --profile azure-retail
+
 # Interactive chat with agent
 dao-ai chat -c config/my_config.yaml
 ```
 
+### Multi-Cloud Deployment
+
+DAO AI supports deploying to Azure, AWS, and GCP workspaces with automatic cloud detection:
+
+```bash
+# Deploy to AWS workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile aws-prod
+
+# Deploy to Azure workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile azure-prod
+
+# Deploy to GCP workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile gcp-prod
+```
+
+The CLI automatically:
+- Detects the cloud provider from your profile's workspace URL
+- Selects appropriate compute node types for each cloud
+- Creates isolated deployment state per profile
+
 👉 **Learn more:** [CLI Reference Documentation](docs/cli-reference.md)
 
 ---

{dao_ai-0.1.2 → dao_ai-0.1.4}/config/examples/03_reranking/vector_search_with_reranking.yaml

@@ -83,7 +83,7 @@ retrievers:
       filters: {}
       query_type: ANN
     rerank:                                         # Custom reranking configuration
-      model: ms-marco-MiniLM-L-6-v2                 # Faster, lighter model
+      model: ms-marco-TinyBERT-L-2-v2               # Fastest, smallest model (~4MB)
       top_n: 5                                      # Return top 5 after reranking
       # cache_dir: ~/.dao_ai/cache/flashrank        # Cache directory (default shown)
 
@@ -258,7 +258,7 @@ app:
 #    - Use when: Need better results than standard search
 #
 # 3. Fast Reranking - fast_search_agent
-#    - Uses lighter model (ms-marco-MiniLM-L-6-v2)
+#    - Uses lighter model (ms-marco-TinyBERT-L-2-v2)
 #    - Retrieves 100 candidates, returns top 5
 #    - Faster than default but still improves results
 #    - Use when: High volume, need speed with some accuracy boost
@@ -286,8 +286,10 @@ app:
 #   - More candidates = better reranking but slower
 #   - Cache directory should be on fast storage
 #
-# Model Selection:
-#   - ms-marco-TinyBERT-L-2-v2: Fastest, basic accuracy
-#   - ms-marco-MiniLM-L-6-v2: Fast, good accuracy
-#   - ms-marco-MiniLM-L-12-v2: Balanced (default)
-#   - rank-T5-flan: Most accurate, slowest
+# Model Selection (see https://github.com/PrithivirajDamodaran/FlashRank):
+#   - ms-marco-TinyBERT-L-2-v2: ~4MB, fastest
+#   - ms-marco-MiniLM-L-12-v2: ~34MB, best cross-encoder (default)
+#   - rank-T5-flan: ~110MB, best non cross-encoder
+#   - ms-marco-MultiBERT-L-12: ~150MB, multilingual (100+ languages)
+#   - ce-esci-MiniLM-L12-v2: e-commerce optimized (Amazon ESCI)
+#   - miniReranker_arabic_v1: Arabic language

{dao_ai-0.1.2 → dao_ai-0.1.4}/config/examples/15_complete_applications/hardware_store_lakebase.yaml

@@ -689,7 +689,7 @@ app:
   registered_model:                                 # MLflow registered model configuration
     schema: *retail_schema                          # Schema where model will be registered
     name: hardware_store_lakebase_dao
-  endpoint_name: hardware_store_postgres_beta           # Model serving endpoint name
+  endpoint_name: hardware_store_lakebase_dao           # Model serving endpoint name
   environment_vars: 
     PGHOST: "{{secrets/retail_ai/PGHOST}}"  # Databricks host URL
     RETAIL_AI_DATABRICKS_CLIENT_ID: "{{secrets/retail_ai/RETAIL_AI_DATABRICKS_CLIENT_ID}}"

{dao_ai-0.1.2 → dao_ai-0.1.4}/databricks.yaml.template

@@ -13,8 +13,9 @@ variables:
   config_path:
     description: Path to the configuration file for the job.
   node_type: 
-    description: The job compute node type
-    default: Standard_D4ads_v5
+    description: The job compute node type (cloud-specific, set per target)
+  cloud:
+    description: Cloud provider (azure, aws, gcp) - auto-detected or set per target
 
 resources:
   jobs:
@@ -93,12 +94,23 @@ resources:
               config-path: ${var.config_path}
           environment_key: dao-ai-env
           
+# Cloud-specific targets with appropriate node types
+# The CLI auto-selects the target based on workspace cloud detection
 targets:
-  __APP_NAME__:
+  azure:
     mode: development
-    default: true
-
-
-
-
-
+    variables:
+      cloud: azure
+      node_type: Standard_D4ads_v5
+  
+  aws:
+    mode: development
+    variables:
+      cloud: aws
+      node_type: i3.xlarge
+  
+  gcp:
+    mode: development
+    variables:
+      cloud: gcp
+      node_type: n1-standard-4

dao_ai-0.1.4/docs/cli-reference.md

@@ -0,0 +1,237 @@
+# CLI Reference
+
+## Validate Configuration
+
+Check your configuration for errors:
+
+```bash
+dao-ai validate -c config/my_config.yaml
+```
+
+## Generate JSON Schema
+
+Generate JSON schema for IDE support and validation:
+
+```bash
+dao-ai schema > schemas/model_config_schema.json
+```
+
+## Visualize Agent Workflow
+
+Generate a diagram showing how your agent works:
+
+```bash
+dao-ai graph -c config/my_config.yaml -o workflow.png
+```
+
+## Deploy with Databricks Asset Bundles
+
+Deploy your agent to Databricks. The CLI supports multi-cloud deployments with automatic cloud detection.
+
+### Basic Deployment
+
+```bash
+# Deploy using default profile or environment
+dao-ai bundle --deploy -c config/my_config.yaml
+```
+
+### Multi-Cloud Deployment
+
+The CLI automatically detects the cloud provider from your Databricks workspace and selects the appropriate configuration (node types, etc.):
+
+```bash
+# Deploy to AWS workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile aws-field-eng
+
+# Deploy to Azure workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile azure-retail
+
+# Deploy to GCP workspace
+dao-ai bundle --deploy -c config/my_config.yaml --profile gcp-analytics
+```
+
+### Deploy and Run
+
+```bash
+# Deploy and immediately run the job
+dao-ai bundle --deploy --run -c config/my_config.yaml --profile aws-field-eng
+```
+
+### Explicit Cloud Override
+
+If cloud auto-detection doesn't work, you can specify the cloud explicitly:
+
+```bash
+dao-ai bundle --deploy -c config/my_config.yaml --cloud aws
+```
+
+### Dry Run
+
+Preview commands without executing:
+
+```bash
+dao-ai bundle --deploy -c config/my_config.yaml --profile aws-field-eng --dry-run
+```
+
+## Interactive Chat
+
+Start an interactive chat session with your agent:
+
+```bash
+dao-ai chat -c config/my_config.yaml
+```
+
+## Verbose Output
+
+Increase verbosity for debugging (use `-v` through `-vvvv`):
+
+```bash
+dao-ai -vvvv validate -c config/my_config.yaml
+```
+
+---
+
+## Command Options
+
+### Common Options
+
+| Option | Description |
+|--------|-------------|
+| `-c, --config FILE` | Path to configuration file (required) |
+| `-p, --profile NAME` | Databricks CLI profile to use |
+| `-v, --verbose` | Increase verbosity (can be repeated up to 4 times) |
+| `--help` | Show help message |
+
+### Validate Options
+
+```bash
+dao-ai validate -c config/my_config.yaml [OPTIONS]
+```
+
+### Graph Options
+
+```bash
+dao-ai graph -c config/my_config.yaml -o output.png [OPTIONS]
+```
+
+| Option | Description |
+|--------|-------------|
+| `-o, --output FILE` | Output file path (supports .png, .pdf, .svg) |
+
+### Bundle Options
+
+```bash
+dao-ai bundle -c config/my_config.yaml [OPTIONS]
+```
+
+| Option | Description |
+|--------|-------------|
+| `-d, --deploy` | Deploy the bundle to Databricks |
+| `-r, --run` | Run the deployment job after deploying |
+| `--destroy` | Destroy the deployed bundle |
+| `-p, --profile NAME` | Databricks CLI profile to use |
+| `--cloud {azure,aws,gcp}` | Cloud provider (auto-detected if not specified) |
+| `-t, --target NAME` | Bundle target name (auto-generated if not specified) |
+| `--dry-run` | Preview commands without executing |
+
+### Chat Options
+
+```bash
+dao-ai chat -c config/my_config.yaml [OPTIONS]
+```
+
+Starts an interactive REPL session where you can chat with your agent locally.
+
+---
+
+## Multi-Cloud Support
+
+DAO AI supports deploying to Azure, AWS, and GCP Databricks workspaces. The CLI handles cloud-specific configurations automatically.
+
+### How It Works
+
+1. **Cloud Detection**: When you specify a `--profile`, the CLI detects the cloud provider from the workspace URL
+2. **Target Selection**: The CLI uses the profile name as the deployment target for per-profile isolation
+3. **Node Types**: Cloud-appropriate compute node types are automatically selected:
+   - Azure: `Standard_D4ads_v5`
+   - AWS: `i3.xlarge`
+   - GCP: `n1-standard-4`
+
+### Profile Configuration
+
+Profiles are configured in `~/.databrickscfg`:
+
+```ini
+[aws-field-eng]
+host = https://my-workspace.cloud.databricks.com
+token = dapi...
+
+[azure-retail]
+host = https://adb-123456789.azuredatabricks.net
+token = dapi...
+
+[gcp-analytics]
+host = https://my-workspace.gcp.databricks.com
+token = dapi...
+```
+
+### Deployment Isolation
+
+Each profile gets its own isolated deployment state:
+
+```
+/.bundle/my_app/aws-field-eng/files    # AWS deployment
+/.bundle/my_app/azure-retail/files     # Azure deployment
+/.bundle/my_app/gcp-analytics/files    # GCP deployment
+```
+
+This allows you to deploy the same application to multiple workspaces without conflicts.
+
+---
+
+## Examples
+
+### Deploy to Multiple Clouds
+
+```bash
+# Deploy to AWS
+dao-ai bundle --deploy -c config/hardware_store.yaml --profile aws-prod
+
+# Deploy same app to Azure
+dao-ai bundle --deploy -c config/hardware_store.yaml --profile azure-prod
+
+# Deploy same app to GCP
+dao-ai bundle --deploy -c config/hardware_store.yaml --profile gcp-prod
+```
+
+### Development vs Production
+
+```bash
+# Deploy to development workspace
+dao-ai bundle --deploy -c config/my_app.yaml --profile aws-dev
+
+# Deploy to production workspace
+dao-ai bundle --deploy -c config/my_app.yaml --profile aws-prod
+```
+
+### Full Deployment Pipeline
+
+```bash
+# Validate configuration
+dao-ai validate -c config/my_app.yaml
+
+# Generate workflow diagram
+dao-ai graph -c config/my_app.yaml -o workflow.png
+
+# Deploy and run
+dao-ai bundle --deploy --run -c config/my_app.yaml --profile aws-field-eng
+```
+
+---
+
+## Navigation
+
+- [← Previous: Examples](examples.md)
+- [↑ Back to Documentation Index](../README.md#-documentation)
+- [Next: Python API →](python-api.md)
+

{dao_ai-0.1.2 → dao_ai-0.1.4}/docs/key-capabilities.md

@@ -298,12 +298,16 @@ Vector embeddings capture semantic similarity but may rank loosely related docum
 
 ### Available Models
 
-| Model | Speed | Quality | Use Case |
-|-------|-------|---------|----------|
-| `ms-marco-TinyBERT-L-2-v2` | ⚡⚡⚡ Fastest | Good | High-throughput, latency-sensitive |
-| `ms-marco-MiniLM-L-6-v2` | ⚡⚡ Fast | Better | Balanced performance |
-| `ms-marco-MiniLM-L-12-v2` | ⚡ Moderate | Best | Default, recommended |
-| `rank-T5-flan` | Slower | Excellent | Maximum accuracy |
+See [FlashRank](https://github.com/PrithivirajDamodaran/FlashRank) for the full list of supported models.
+
+| Model | Size | Speed | Use Case |
+|-------|------|-------|----------|
+| `ms-marco-TinyBERT-L-2-v2` | ~4MB | ⚡⚡⚡ Fastest | High-throughput, latency-sensitive |
+| `ms-marco-MiniLM-L-12-v2` | ~34MB | ⚡⚡ Fast | Default, best cross-encoder |
+| `rank-T5-flan` | ~110MB | ⚡ Moderate | Best non cross-encoder |
+| `ms-marco-MultiBERT-L-12` | ~150MB | Slower | Multilingual (100+ languages) |
+| `ce-esci-MiniLM-L12-v2` | - | ⚡⚡ Fast | E-commerce optimized |
+| `miniReranker_arabic_v1` | - | ⚡⚡ Fast | Arabic language |
 
 ### Configuration Options
 
@@ -311,11 +315,11 @@ Vector embeddings capture semantic similarity but may rank loosely related docum
 rerank:
   model: ms-marco-MiniLM-L-12-v2    # FlashRank model name
   top_n: 10                          # Documents to return (default: all)
-  cache_dir: /tmp/flashrank_cache    # Model weights cache location
+  cache_dir: ~/.dao_ai/cache/flashrank  # Model weights cache location
   columns: [description, name]       # Columns for Databricks Reranker (optional)
 ```
 
-**Note:** Model weights are downloaded automatically on first use (~20MB for MiniLM-L-12-v2).
+**Note:** Model weights are downloaded automatically on first use (~34MB for MiniLM-L-12-v2).
 
 ## 5. Human-in-the-Loop Approvals
 

{dao_ai-0.1.2 → dao_ai-0.1.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dao-ai"
-version = "0.1.2"
+version = "0.1.4"
 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" }

{dao_ai-0.1.2 → dao_ai-0.1.4}/schemas/model_config_schema.json

@@ -3402,7 +3402,7 @@
     },
     "RerankParametersModel": {
       "additionalProperties": false,
-      "description": "Configuration for reranking retrieved documents using FlashRank.\n\nFlashRank provides fast, local reranking without API calls using lightweight\ncross-encoder models. Reranking improves retrieval quality by reordering results\nbased on semantic relevance to the query.\n\nTypical workflow:\n1. Retrieve more documents than needed (e.g., 50 via num_results)\n2. Rerank all retrieved documents\n3. Return top_n best matches (e.g., 5)\n\nExample:\n    ```yaml\n    retriever:\n      search_parameters:\n        num_results: 50  # Retrieve more candidates\n      rerank:\n        model: ms-marco-MiniLM-L-12-v2\n        top_n: 5  # Return top 5 after reranking\n    ```\n\nAvailable models (from fastest to most accurate):\n- \"ms-marco-TinyBERT-L-2-v2\" (fastest, smallest)\n- \"ms-marco-MiniLM-L-6-v2\"\n- \"ms-marco-MiniLM-L-12-v2\" (default, good balance)\n- \"rank-T5-flan\" (most accurate, slower)",
+      "description": "Configuration for reranking retrieved documents using FlashRank.\n\nFlashRank provides fast, local reranking without API calls using lightweight\ncross-encoder models. Reranking improves retrieval quality by reordering results\nbased on semantic relevance to the query.\n\nTypical workflow:\n1. Retrieve more documents than needed (e.g., 50 via num_results)\n2. Rerank all retrieved documents\n3. Return top_n best matches (e.g., 5)\n\nExample:\n    ```yaml\n    retriever:\n      search_parameters:\n        num_results: 50  # Retrieve more candidates\n      rerank:\n        model: ms-marco-MiniLM-L-12-v2\n        top_n: 5  # Return top 5 after reranking\n    ```\n\nAvailable models (see https://github.com/PrithivirajDamodaran/FlashRank):\n- \"ms-marco-TinyBERT-L-2-v2\" (~4MB, fastest)\n- \"ms-marco-MiniLM-L-12-v2\" (~34MB, best cross-encoder, default)\n- \"rank-T5-flan\" (~110MB, best non cross-encoder)\n- \"ms-marco-MultiBERT-L-12\" (~150MB, multilingual 100+ languages)\n- \"ce-esci-MiniLM-L12-v2\" (e-commerce optimized, Amazon ESCI)\n- \"miniReranker_arabic_v1\" (Arabic language)",
       "properties": {
         "model": {
           "default": "ms-marco-MiniLM-L-12-v2",
@@ -4336,6 +4336,7 @@
     },
     "VectorStoreModel": {
       "additionalProperties": false,
+      "description": "Configuration model for a Databricks Vector Search store.\n\nSupports two modes:\n1. **Use Existing Index**: Provide only `index` (fully qualified name).\n   Used for querying an existing vector search index at runtime.\n2. **Provisioning Mode**: Provide `source_table` + `embedding_source_column`.\n   Used for creating a new vector search index.\n\nExamples:\n    Minimal configuration (use existing index):\n    ```yaml\n    vector_stores:\n      products_search:\n        index:\n          name: catalog.schema.my_index\n    ```\n\n    Full provisioning configuration:\n    ```yaml\n    vector_stores:\n      products_search:\n        source_table:\n          schema: *my_schema\n          name: products\n        embedding_source_column: description\n        endpoint:\n          name: my_endpoint\n    ```",
       "properties": {
         "on_behalf_of_user": {
           "anyOf": [
@@ -4492,10 +4493,10 @@
           "default": null,
           "title": "Pat"
         },
-        "embedding_model": {
+        "index": {
           "anyOf": [
             {
-              "$ref": "#/$defs/LLMModel"
+              "$ref": "#/$defs/IndexModel"
             },
             {
               "type": "null"
@@ -4503,10 +4504,33 @@
           ],
           "default": null
         },
-        "index": {
+        "source_table": {
           "anyOf": [
             {
-              "$ref": "#/$defs/IndexModel"
+              "$ref": "#/$defs/TableModel"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "embedding_source_column": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Embedding Source Column"
+        },
+        "embedding_model": {
+          "anyOf": [
+            {
+              "$ref": "#/$defs/LLMModel"
             },
             {
               "type": "null"
@@ -4525,9 +4549,6 @@
           ],
           "default": null
         },
-        "source_table": {
-          "$ref": "#/$defs/TableModel"
-        },
         "source_path": {
           "anyOf": [
             {
@@ -4587,16 +4608,8 @@
           ],
           "default": null,
           "title": "Doc Uri"
-        },
-        "embedding_source_column": {
-          "title": "Embedding Source Column",
-          "type": "string"
         }
       },
-      "required": [
-        "source_table",
-        "embedding_source_column"
-      ],
       "title": "VectorStoreModel",
       "type": "object"
     },