memra 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

memra/__init__.py

@@ -6,18 +6,22 @@ Think of it as "Kubernetes for business logic" where agents are the pods and
 departments are the deployments.
 """
 
-__version__ = "0.2.2"
+__version__ = "0.2.3"
 
 # Core imports
-from .models import Agent, Department, Tool
+from .models import Agent, Department, Tool, LLM
 from .execution import ExecutionEngine
+from .discovery_client import check_api_health, get_api_status
 
 # Make key classes available at package level
 __all__ = [
     "Agent",
     "Department", 
     "Tool",
+    "LLM",
     "ExecutionEngine",
+    "check_api_health",
+    "get_api_status",
     "__version__"
 ]
 

memra/execution.py

@@ -216,6 +216,21 @@ class ExecutionEngine:
                     # Use local registry for MCP and other local tools
                     print(f"🏠 {agent.role}: Using local registry for {tool_name}")
                     config_to_pass = tool_spec.get("config") if isinstance(tool_spec, dict) else tool_spec.config
+                    
+                    # For MCP tools, merge department context MCP configuration
+                    if hosted_by == "mcp":
+                        mcp_config = {}
+                        dept_context = context.get("department_context", {})
+                        if "mcp_bridge_url" in dept_context:
+                            mcp_config["bridge_url"] = dept_context["mcp_bridge_url"]
+                        if "mcp_bridge_secret" in dept_context:
+                            mcp_config["bridge_secret"] = dept_context["mcp_bridge_secret"]
+                        
+                        # Merge with tool-specific config if it exists
+                        if config_to_pass:
+                            mcp_config.update(config_to_pass)
+                        config_to_pass = mcp_config
+                    
                     print(f"🔧 {agent.role}: Config for {tool_name}: {config_to_pass}")
                     tool_result = self.tool_registry.execute_tool(
                         tool_name, 
@@ -325,6 +340,34 @@ class ExecutionEngine:
                 not tool_data.get("_mock", False)  # Not mock data
             )
         
+        elif tool_name == "FileDiscovery":
+            # Real work if it actually discovered files in a real directory
+            return (
+                "files" in tool_data and
+                isinstance(tool_data["files"], list) and
+                "directory" in tool_data and
+                tool_data.get("success", False) == True
+            )
+            
+        elif tool_name == "FileCopy":
+            # Real work if it actually copied a file
+            return (
+                "destination_path" in tool_data and
+                "source_path" in tool_data and
+                tool_data.get("success", False) == True and
+                tool_data.get("operation") == "copy_completed"
+            )
+        
+        elif tool_name == "TextToSQL":
+            # Real work if it actually executed SQL and returned real results
+            return (
+                "generated_sql" in tool_data and
+                "results" in tool_data and
+                isinstance(tool_data["results"], list) and
+                tool_data.get("success", False) == True and
+                not tool_data.get("_mock", False)  # Not mock data
+            )
+        
         # Default to mock work
         return False
     

memra/tool_registry.py

@@ -24,6 +24,8 @@ class ToolRegistry:
             ("OCRTool", "Perform OCR on images and documents"),
             ("InvoiceExtractionWorkflow", "Extract structured data from invoices"),
             ("FileReader", "Read files from the filesystem"),
+            ("FileDiscovery", "Discover and list files in directories"),
+            ("FileCopy", "Copy files to standard processing directories"),
         ]
         
         for tool_name, description in server_tools:
@@ -33,6 +35,9 @@ class ToolRegistry:
         mcp_tools = [
             ("DataValidator", "Validate data against schemas"),
             ("PostgresInsert", "Insert data into PostgreSQL database"),
+            ("TextToSQL", "Convert natural language questions to SQL queries and execute them"),
+            ("SQLExecutor", "Execute SQL queries against PostgreSQL database"),
+            ("TextToSQLGenerator", "Generate SQL from natural language questions"),
         ]
         
         for tool_name, description in mcp_tools:
@@ -169,6 +174,155 @@ class ToolRegistry:
                         "_mock": True
                     }
                 }
+            elif tool_name == "FileDiscovery":
+                # Mock file discovery - in real implementation, would scan directories
+                directory = input_data.get("directory", "invoices")
+                file_pattern = input_data.get("pattern", "*.pdf")
+                
+                # Simulate finding files in the directory
+                mock_files = [
+                    {
+                        "filename": "10352259310.PDF",
+                        "path": f"{directory}/10352259310.PDF",
+                        "size": "542KB",
+                        "modified": "2024-05-28",
+                        "type": "PDF"
+                    }
+                ]
+                
+                return {
+                    "success": True,
+                    "data": {
+                        "directory": directory,
+                        "pattern": file_pattern,
+                        "files_found": len(mock_files),
+                        "files": mock_files,
+                        "message": f"Found {len(mock_files)} files in {directory}/ directory"
+                    }
+                }
+                
+            elif tool_name == "FileCopy":
+                # Mock file copy - in real implementation, would copy files
+                source_path = input_data.get("source_path", "")
+                destination_dir = input_data.get("destination_dir", "invoices")
+                
+                if not source_path:
+                    return {
+                        "success": False,
+                        "error": "Source path is required"
+                    }
+                
+                # Extract filename from path
+                import os
+                filename = os.path.basename(source_path)
+                destination_path = f"{destination_dir}/{filename}"
+                
+                return {
+                    "success": True,
+                    "data": {
+                        "source_path": source_path,
+                        "destination_path": destination_path,
+                        "message": f"File copied from {source_path} to {destination_path}",
+                        "file_size": "245KB",
+                        "operation": "copy_completed"
+                    }
+                }
+            elif tool_name == "TextToSQL":
+                # Mock text-to-SQL - in real implementation, would use LLM to generate SQL
+                question = input_data.get("question", "")
+                schema = input_data.get("schema", {})
+                
+                if not question:
+                    return {
+                        "success": False,
+                        "error": "Question is required for text-to-SQL conversion"
+                    }
+                
+                # Simulate SQL generation and execution
+                mock_sql = "SELECT vendor_name, invoice_number, total_amount FROM invoices WHERE vendor_name ILIKE '%air liquide%' ORDER BY invoice_date DESC LIMIT 5;"
+                mock_results = [
+                    {
+                        "vendor_name": "Air Liquide Canada Inc.",
+                        "invoice_number": "INV-12345",
+                        "total_amount": 1234.56
+                    },
+                    {
+                        "vendor_name": "Air Liquide Canada Inc.", 
+                        "invoice_number": "INV-67890",
+                        "total_amount": 2345.67
+                    }
+                ]
+                
+                return {
+                    "success": True,
+                    "data": {
+                        "question": question,
+                        "generated_sql": mock_sql,
+                        "results": mock_results,
+                        "row_count": len(mock_results),
+                        "message": f"Found {len(mock_results)} results for: {question}",
+                        "_mock": True
+                    }
+                }
+            elif tool_name == "SQLExecutor":
+                # Mock SQL execution
+                sql_query = input_data.get("sql_query", "")
+                
+                if not sql_query:
+                    return {
+                        "success": False,
+                        "error": "SQL query is required"
+                    }
+                
+                # Mock results based on query type
+                if sql_query.upper().startswith("SELECT"):
+                    mock_results = [
+                        {"vendor_name": "Air Liquide Canada Inc.", "invoice_number": "INV-12345", "total_amount": 1234.56},
+                        {"vendor_name": "Air Liquide Canada Inc.", "invoice_number": "INV-67890", "total_amount": 2345.67}
+                    ]
+                    return {
+                        "success": True,
+                        "data": {
+                            "query": sql_query,
+                            "results": mock_results,
+                            "row_count": len(mock_results),
+                            "columns": ["vendor_name", "invoice_number", "total_amount"],
+                            "_mock": True
+                        }
+                    }
+                else:
+                    return {
+                        "success": True,
+                        "data": {
+                            "query": sql_query,
+                            "affected_rows": 1,
+                            "message": "Query executed successfully",
+                            "_mock": True
+                        }
+                    }
+            elif tool_name == "TextToSQLGenerator":
+                # Mock SQL generation
+                question = input_data.get("question", "")
+                
+                if not question:
+                    return {
+                        "success": False,
+                        "error": "Question is required for SQL generation"
+                    }
+                
+                # Generate mock SQL based on question
+                mock_sql = "SELECT * FROM invoices WHERE vendor_name ILIKE '%air liquide%'"
+                
+                return {
+                    "success": True,
+                    "data": {
+                        "question": question,
+                        "generated_sql": mock_sql,
+                        "explanation": "Generated SQL query based on natural language question",
+                        "confidence": "medium",
+                        "_mock": True
+                    }
+                }
             else:
                 return {
                     "success": False,

memra-0.2.3.dist-info/METADATA

@@ -0,0 +1,101 @@
+Metadata-Version: 2.4
+Name: memra
+Version: 0.2.3
+Summary: Declarative framework for enterprise workflows with MCP integration - Client SDK
+Home-page: https://github.com/memra/memra-sdk
+Author: Memra
+Author-email: Memra <support@memra.com>
+License: MIT
+Project-URL: Homepage, https://memra.co
+Project-URL: Repository, https://github.com/memra-platform/memra-sdk
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic>=1.8.0
+Requires-Dist: httpx>=0.24.0
+Requires-Dist: typing-extensions>=4.0.0
+Requires-Dist: aiohttp>=3.8.0
+Requires-Dist: aiohttp-cors>=0.7.0
+Provides-Extra: dev
+Requires-Dist: pytest>=6.0; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+Provides-Extra: mcp
+Requires-Dist: psycopg2-binary>=2.9.0; extra == "mcp"
+Dynamic: author
+Dynamic: home-page
+Dynamic: requires-python
+
+# Memra SDK
+
+The core Memra framework for building AI-powered business workflows.
+
+## Installation
+
+```bash
+pip install memra
+```
+
+## Quick Start
+
+```python
+from memra import Agent, Department, LLM, ExecutionEngine
+
+# Define an agent
+agent = Agent(
+    role="Data Analyst",
+    job="Analyze customer data",
+    llm=LLM(model="llama-3.2-11b-vision-preview"),
+    sops=["Load data", "Perform analysis", "Generate report"],
+    output_key="analysis_result"
+)
+
+# Create a department
+department = Department(
+    name="Analytics",
+    mission="Provide data insights",
+    agents=[agent],
+    workflow_order=["Data Analyst"]
+)
+
+# Execute the workflow
+engine = ExecutionEngine()
+result = engine.execute_department(department, {"data": "customer_data.csv"})
+```
+
+## Core Components
+
+### Agent
+An AI worker that performs specific tasks using LLMs and tools.
+
+### Department
+A team of agents working together to accomplish a mission.
+
+### ExecutionEngine
+Orchestrates the execution of departments and their workflows.
+
+### LLM
+Configuration for language models used by agents.
+
+## Examples
+
+See the `examples/` directory for basic usage examples:
+- `simple_text_to_sql.py` - Basic text-to-SQL conversion
+- `ask_questions.py` - Simple question answering
+
+## Documentation
+
+For detailed documentation, visit [docs.memra.co](https://docs.memra.co)
+
+## License
+
+MIT License - see LICENSE file for details. 

memra-0.2.3.dist-info/RECORD

@@ -0,0 +1,12 @@
+memra/__init__.py,sha256=zVO29fnEDclBI9x9SFVzF9uJYAKhPDTNrMFMWuw6JC8,787
+memra/discovery.py,sha256=yJIQnrDQu1nyzKykCIuzG_5SW5dIXHCEBLLKRWacIoY,480
+memra/discovery_client.py,sha256=AbnKn6qhyrf7vmOvknEeDzH4tiGHsqPHtDaein_qaW0,1271
+memra/execution.py,sha256=P7tAur0SEMtX6uLlfxTfCZBgMLIRj6Wl3dsv2EA9fHc,23443
+memra/models.py,sha256=sXMPRnMB_mUVtJdBFyd0ElCf_uh1yqx7iLssIYNm0vI,3333
+memra/tool_registry.py,sha256=P2TafpiqV19yzi0jVrQQrXFGBpQkbmePbRfEW_ai24M,14700
+memra/tool_registry_client.py,sha256=uzMQ4COvRams9vuPLcqcdljUpDlAYU_tyFxrRhrA0Lc,4009
+memra-0.2.3.dist-info/METADATA,sha256=gr4yyJc9wX49JFvxLdbQCP7HFdoEC_NqSH06uxvnq08,2737
+memra-0.2.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+memra-0.2.3.dist-info/entry_points.txt,sha256=LBVjwWoxWJRzNLgeByPn6xUvWFIRnqnemvAZgIoSt08,41
+memra-0.2.3.dist-info/top_level.txt,sha256=pXWcTRS1zctdiSUivW4iyKpJ4tcfIu-1BW_fpbal3OY,6
+memra-0.2.3.dist-info/RECORD,,

{memra-0.2.2.dist-info → memra-0.2.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.7.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

memra-0.2.2.dist-info/METADATA

@@ -1,148 +0,0 @@
-Metadata-Version: 2.1
-Name: memra
-Version: 0.2.2
-Summary: Declarative framework for enterprise workflows with MCP integration - Client SDK
-Home-page: https://github.com/memra/memra-sdk
-Author: Memra
-Author-email: Memra <support@memra.com>
-License: MIT
-Project-URL: Homepage, https://memra.co
-Project-URL: Repository, https://github.com/memra-platform/memra-sdk
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pydantic>=1.8.0
-Requires-Dist: httpx>=0.24.0
-Requires-Dist: typing-extensions>=4.0.0
-Requires-Dist: aiohttp>=3.8.0
-Requires-Dist: aiohttp-cors>=0.7.0
-Provides-Extra: dev
-Requires-Dist: pytest>=6.0; extra == "dev"
-Requires-Dist: pytest-asyncio; extra == "dev"
-Requires-Dist: black; extra == "dev"
-Requires-Dist: flake8; extra == "dev"
-Provides-Extra: mcp
-Requires-Dist: psycopg2-binary>=2.9.0; extra == "mcp"
-
-# Memra SDK
-
-A declarative orchestration framework for AI-powered business workflows. Think of it as "Kubernetes for business logic" where agents are the pods and departments are the deployments.
-
-## 🚀 Team Setup
-
-**New team member?** See the complete setup guide: **[TEAM_SETUP.md](TEAM_SETUP.md)**
-
-This includes:
-- Database setup (PostgreSQL + Docker)
-- Local development environment
-- Testing instructions
-- Troubleshooting guide
-
-## Quick Start
-
-```python
-from memra.sdk.models import Agent, Department, Tool
-
-# Define your agents
-data_extractor = Agent(
-    role="Data Extraction Specialist",
-    job="Extract and validate data",
-    tools=[Tool(name="DataExtractor", hosted_by="memra")],
-    input_keys=["input_data"],
-    output_key="extracted_data"
-)
-
-# Create a department
-dept = Department(
-    name="Data Processing",
-    mission="Process and validate data",
-    agents=[data_extractor]
-)
-
-# Run the workflow
-result = dept.run({"input_data": {...}})
-```
-
-## Installation
-
-```bash
-pip install memra
-```
-
-## API Access
-
-Memra requires an API key to execute workflows on the hosted infrastructure.
-
-### Get Your API Key
-Contact [info@memra.co](mailto:info@memra.co) for API access.
-
-### Set Your API Key
-```bash
-# Set environment variable
-export MEMRA_API_KEY="your-api-key-here"
-
-# Or add to your shell profile for persistence
-echo 'export MEMRA_API_KEY="your-api-key-here"' >> ~/.zshrc
-```
-
-### Test Your Setup
-```bash
-python examples/accounts_payable_client.py
-```
-
-## Architecture
-
-The Memra platform consists of three main components:
-
-- **Memra SDK** (this repository): Client library for building and executing workflows
-- **Memra Server**: Hosted infrastructure for heavy AI processing tools
-- **MCP Bridge**: Local execution environment for database operations
-
-Tools are automatically routed between server and local execution based on their `hosted_by` configuration.
-
-## Documentation
-
-Documentation is coming soon. For now, see the examples below and in the `examples/` directory.
-
-## Example: Propane Delivery Workflow
-
-See the `examples/propane_delivery.py` file for a complete example of how to use Memra to orchestrate a propane delivery workflow.
-
-## Contributing
-
-We welcome contributions! Please see our [contributing guide](CONTRIBUTING.md) for details.
-
-## License
-
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
-
-## Repository Structure
-
-```
-├── examples/                       # Example workflows and use cases
-│   ├── accounts_payable_client.py  # API-based accounts payable workflow
-│   ├── accounts_payable_mcp.py     # MCP-enabled accounts payable workflow
-│   ├── invoice_processing.py       # Simple invoice processing example
-│   └── propane_delivery.py         # Propane delivery domain example
-├── memra/                          # Core SDK package
-│   ├── __init__.py                 # Package initialization
-│   ├── tool_registry.py            # Tool discovery and routing
-│   └── sdk/                        # SDK components
-│       ├── __init__.py
-│       ├── client.py               # API client
-│       ├── execution_engine.py     # Workflow execution
-│       └── models.py               # Core data models
-├── docs/                           # Documentation
-├── tests/                          # Test suite
-├── local/dependencies/             # Local development setup
-└── scripts/                        # Utility scripts
-```

memra-0.2.2.dist-info/RECORD

@@ -1,13 +0,0 @@
-memra/__init__.py,sha256=5WPh9vku8_ZV4T6WayAqArKAj1RDkbL47SsnA9GWD7A,662
-memra/discovery.py,sha256=yJIQnrDQu1nyzKykCIuzG_5SW5dIXHCEBLLKRWacIoY,480
-memra/discovery_client.py,sha256=AbnKn6qhyrf7vmOvknEeDzH4tiGHsqPHtDaein_qaW0,1271
-memra/execution.py,sha256=bg822ED6yYN7APjPac1LRhv48gtxV4DUPvzpyLyBa2I,21443
-memra/models.py,sha256=sXMPRnMB_mUVtJdBFyd0ElCf_uh1yqx7iLssIYNm0vI,3333
-memra/tool_registry.py,sha256=N7kpYQxgJcSMDDCX-_6og1-of3QKEaoz6H16ptCCg48,7784
-memra/tool_registry_client.py,sha256=uzMQ4COvRams9vuPLcqcdljUpDlAYU_tyFxrRhrA0Lc,4009
-memra-0.2.2.dist-info/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-memra-0.2.2.dist-info/METADATA,sha256=jrZ9AwcGtPK-pc9TGGGoi1oJzXxcGx7LUsbsd6NxcxA,4856
-memra-0.2.2.dist-info/WHEEL,sha256=A3WOREP4zgxI0fKrHUG8DC8013e3dK3n7a6HDbcEIwE,91
-memra-0.2.2.dist-info/entry_points.txt,sha256=LBVjwWoxWJRzNLgeByPn6xUvWFIRnqnemvAZgIoSt08,41
-memra-0.2.2.dist-info/top_level.txt,sha256=pXWcTRS1zctdiSUivW4iyKpJ4tcfIu-1BW_fpbal3OY,6
-memra-0.2.2.dist-info/RECORD,,