realtimex-agent-flows 0.3.2__tar.gz

realtimex_agent_flows-0.3.2/.gitignore

@@ -0,0 +1,284 @@
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### venv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# App-specific
+!scripts/
+.tasks/
+debug_logs/
+debug/
+perf/
+# docs/
+reports/
+TODO
+README.md
+note.md
+prompt.md
+demo.py
+dev/
+!docs/executors/web_scraping/README.md
+web_scraping_mcp
+!realtimex/*
+agent-flows/*
+docs/executors/stream_ui/
+debug_configs/
+fusesell-check/
+!agent_flows/core/execution/stages/README.md

realtimex_agent_flows-0.3.2/PKG-INFO

@@ -0,0 +1,368 @@
+Metadata-Version: 2.4
+Name: realtimex-agent-flows
+Version: 0.3.2
+Summary: Python library for executing Agent Flows - visual, no-code workflows for AI agents
+Author-email: RealTimeX Team <info@realtimex.ai>
+Keywords: agents,ai,automation,llm,workflows
+Requires-Python: >=3.11
+Requires-Dist: aiofiles>=23.2.0
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: cryptography==44.0.3
+Requires-Dist: jmespath>=1.0.1
+Requires-Dist: jsonpath-ng>=1.6.0
+Requires-Dist: litellm>=1.76.3
+Requires-Dist: mcp>=1.0.0
+Requires-Dist: pydantic>=2.5.0
+Requires-Dist: python-dotenv>=1.1.1
+Requires-Dist: pyyaml>=6.0.0
+Requires-Dist: realtimex-web-scraping-mcp-server
+Requires-Dist: realtimex-web-search-mcp-server
+Requires-Dist: redis>=6.4.0
+Requires-Dist: simpleeval>=1.0.3
+Requires-Dist: structlog>=23.2.0
+Requires-Dist: tenacity>=8.2.0
+Requires-Dist: typing-extensions>=4.8.0
+Description-Content-Type: text/markdown
+
+# Agent Flows Python Package
+
+A powerful Python library for executing Agent Flows - visual, no-code workflows that integrate seamlessly into Python applications.
+
+## Features
+
+- **Multiple Executors**: Built-in support for 8 different executor types (API calls, LLM instructions, MCP servers, etc.)
+- **Flow Initialization**: Use the `flow_variables` step type (`start` remains as a deprecated alias) to seed runtime data consistently across flows.
+- **MCP Integration**: Native support for Model Context Protocol (MCP) servers and tools
+- **Flexible Usage**: Run flows from RealTimeX instances or local JSON files
+- **Simple API**: Easy-to-use methods with explicit parameters
+- **CLI Interface**: Command-line tools with `uvx` support (no installation required)
+- **Async & Sync**: Both async/await and synchronous execution options
+- **Type Safety**: Full type hints and Pydantic validation
+- **JSON Configuration**: Simple, consistent configuration format
+- **Testing Framework**: Deep pinning support for testing flows without API costs, including composite nodes (loops, conditionals)
+
+## Quick Start
+
+### Installation
+
+```bash
+# Install via pip
+pip install agent-flows
+
+# Or use with uvx for one-time execution (no installation required)
+uvx agent-flows execute --flow-id <uuid> --api-key <key> --base-url <url>
+```
+
+### Configuration
+
+Configure using environment variables:
+
+```bash
+export AGENT_FLOWS_API_KEY="your-realtimex-api-key"
+export AGENT_FLOWS_BASE_URL="https://your-realtimex-instance.com"
+export LITELLM_API_KEY="your-llm-api-key"
+
+# For MCP server integration
+export MCP_ACI_API_KEY="your-aci-api-key"
+export MCP_ACI_LINKED_ACCOUNT_OWNER_ID="your-linked-account-owner-id"
+```
+
+## Usage
+
+### 1. Execute Flows from RealTimeX
+
+```python
+import asyncio
+from agent_flows import FlowExecutor, AgentFlowsConfig, LiteLLMConfig
+
+# Option 1: Use environment variables (recommended)
+executor = FlowExecutor()
+
+# Option 2: Create explicit configuration
+system_config = AgentFlowsConfig(
+    api_key="your-realtimex-api-key",
+    base_url="https://your-realtimex-instance.com",
+    litellm=LiteLLMConfig(
+        api_key="your-llm-api-key",
+        api_base="https://api.openai.com/v1"
+    )
+)
+executor = FlowExecutor(config=system_config)
+
+# Execute flow with explicit parameters
+result = await executor.execute_flow(
+    flow_id="550e8400-e29b-41d4-a716-446655440000",
+    variables={"input_param": "value", "max_results": 10}
+)
+
+print(f"Success: {result.success}")
+print(f"Steps executed: {result.steps_executed}")
+print(f"Execution time: {result.execution_time:.2f}s")
+```
+
+### 2. Execute Local Flow Files
+
+```python
+from agent_flows import FlowExecutor
+
+# Create executor from local flow file (uses environment variables for LLM/API config)
+executor = FlowExecutor.from_file(
+    flow_file="examples/1_basic_executors/start.json"
+)
+
+# Execute with explicit parameters
+result = await executor.execute_flow(
+    variables={"name": "World", "greeting": "Hello"}
+)
+
+print(f"Local flow result: {result.success}")
+```
+
+### 3. Synchronous Execution (No async/await)
+
+```python
+from agent_flows import FlowExecutor
+
+# Create executor (uses environment variables)
+executor = FlowExecutor.from_file(flow_file="examples/simple_flow.json")
+
+# Run synchronously with explicit parameters
+result = executor.run(
+    variables={"name": "World"}
+)
+
+print(f"Success: {result.success}")
+```
+
+### 4. Configuration Options
+
+```python
+from agent_flows import FlowExecutor, AgentFlowsConfig
+
+# Option 1: From environment variables (recommended)
+executor = FlowExecutor()  # Uses AGENT_FLOWS_* env vars
+
+# Option 2: Explicit configuration
+system_config = AgentFlowsConfig(
+    api_key="your-key",
+    base_url="https://your-instance.com"
+)
+executor = FlowExecutor(config=system_config)
+
+# Option 3: From flow dictionary
+flow_dict = {"uuid": "123", "name": "Test", "steps": [...]}
+executor = FlowExecutor.from_dict(flow_dict=flow_dict)
+```
+
+### CLI Usage
+
+#### Execute flows from RealTimeX
+
+```bash
+# Execute with environment variables (recommended)
+agent-flows execute \
+  --flow-id "550e8400-e29b-41d4-a716-446655440000"
+
+# Execute with inline config
+agent-flows execute \
+  --flow-id "550e8400-e29b-41d4-a716-446655440000" \
+  --config '{"api_key":"key","base_url":"url","litellm":{"api_key":"llm-key"}}'
+
+# Execute with variables
+agent-flows execute \
+  --flow-id "550e8400-e29b-41d4-a716-446655440000" \
+  --variables '{"input_text":"Hello World","max_results":10}'
+```
+
+#### Execute local flow files
+
+```bash
+# Run a local flow file
+agent-flows run examples/1_basic_executors/start.json
+
+# Run with variables (JSON string)
+agent-flows run examples/3_workflows/2_breaking_news_to_linkedin/flow.json \
+  --variables '{"name":"John","age":30}'
+
+# Run with variables from file
+agent-flows run examples/3_workflows/2_breaking_news_to_linkedin/flow.json \
+  --variables-file examples/3_workflows/2_breaking_news_to_linkedin/variables.json
+
+# Run with explicit config for LLM settings
+agent-flows run examples/3_workflows/2_breaking_news_to_linkedin/flow.json \
+  --config '{"litellm":{"api_key":"your-llm-key"}}'
+```
+
+#### Using uvx (no installation required)
+
+```bash
+# Execute a flow with uvx
+uvx agent-flows execute \
+  --flow-id "550e8400-e29b-41d4-a716-446655440000" \
+  --config '{"api_key":"key","base_url":"url","litellm":{"api_key":"llm-key"}}'
+
+# Run a local flow with uvx
+uvx agent-flows run examples/1_basic_executors/start.json \
+  --variables '{"greeting":"Hello from uvx!"}'
+```
+
+## Supported Flow Types
+
+The package includes **8 built-in executors**:
+
+- **Flow Variables**: Variable initialization and flow setup
+- **API Call**: HTTP requests with full REST API support and retry logic
+- **LLM Instruction**: Multi-provider LLM integration (OpenAI, Anthropic, etc.)
+- **Web Scraping**: Content extraction with CSS selectors and auto-summarization
+- **Conditional**: Branching logic with multiple comparison operators
+- **Switch**: Multi-case routing based on variable values
+- **Loop**: Iterative execution with for/while/forEach support and clean output format
+- **MCP Server Action**: Execute actions on Model Context Protocol (MCP) servers
+
+For detailed documentation on each executor, see [docs/executors/](docs/executors/).
+
+## MCP Integration
+
+Agent Flows provides native support for Model Context Protocol (MCP) servers, enabling seamless integration with external tools and services.
+
+### MCP Server Examples
+
+```python
+# Send email via Gmail MCP server
+{
+  "type": "mcpServerAction",
+  "config": {
+    "provider": "remote",
+    "serverId": "GMAIL",
+    "action": "GMAIL__SEND_EMAIL",
+    "params": {
+      "to": "recipient@example.com",
+      "subject": "Hello from Agent Flows",
+      "body": "This email was sent via MCP integration!"
+    },
+    "resultVariable": "email_result"
+  }
+}
+
+# Upload file to Google Drive
+{
+  "type": "mcpServerAction",
+  "config": {
+    "provider": "remote",
+    "serverId": "GOOGLE_DRIVE",
+    "action": "DRIVE__UPLOAD_FILE",
+    "params": {
+      "fileName": "report.pdf",
+      "fileContent": "${file_data}",
+      "folderId": "${target_folder}"
+    },
+    "resultVariable": "upload_result"
+  }
+}
+```
+
+### Available MCP Servers
+
+- **Gmail**: Email operations (send, read, manage)
+- **Google Drive**: File operations (upload, download, organize)
+- **Google Calendar**: Calendar management (create events, schedule meetings)
+- **Slack**: Messaging and channel operations
+- **Database**: Query execution and data management
+- **File Manager**: Local file system operations
+
+### MCP Configuration
+
+Set up MCP integration using environment variables or configuration files:
+
+```bash
+# Environment variables
+export MCP_ACI_API_KEY="your-aci-api-key"
+export MCP_ACI_LINKED_ACCOUNT_OWNER_ID="your-linked-account-owner-id"
+```
+
+Or in your configuration:
+
+```python
+from agent_flows import AgentFlowsConfig
+from agent_flows.models.config import MCPConfig
+
+config = AgentFlowsConfig(
+    mcp=MCPConfig(
+        aci_api_key="your-aci-api-key",
+        aci_linked_account_owner_id="your-linked-account-owner-id"
+    )
+)
+```
+
+## Architecture
+
+The package follows a modular, extensible architecture:
+
+```
+agent_flows/
+├── core/           # Core execution engine
+├── executors/      # Block-specific executors
+├── models/         # Pydantic data models
+├── api/           # API client for flow fetching
+├── cli/           # Command-line interface
+└── utils/         # Utility functions
+```
+
+## API Reference
+
+### FlowExecutor Methods
+
+```python
+# Constructor
+FlowExecutor(
+    config=None,           # AgentFlowsConfig: System configuration (uses env vars if None)
+    flow_config=None,      # FlowConfig: Local flow configuration
+    log_level="INFO",      # str: Logging level (e.g., "DEBUG", "INFO", "WARNING")
+    log_json_format=False  # bool: Format logs as JSON
+)
+
+# Class methods
+FlowExecutor.from_file(
+    flow_file,            # str: Path to flow JSON file
+    config=None,          # AgentFlowsConfig: System configuration (uses env vars if None)
+)
+
+FlowExecutor.from_dict(
+    flow_dict,            # dict: Flow configuration dictionary
+    config=None,          # AgentFlowsConfig: System configuration (uses env vars if None)
+)
+
+# Execution methods
+await executor.execute_flow(
+    flow_id=None,         # str: Flow UUID (optional if flow_config provided)
+    variables=None,       # dict: Flow variables
+    context=None          # dict: Additional execution context
+)
+
+executor.run(
+    flow_id=None,         # str: Flow UUID (optional if flow_config provided)
+    variables=None        # dict: Flow variables
+)
+```
+
+### Configuration Types
+
+**System Configuration** (`AgentFlowsConfig`): API credentials and LLM settings
+**Flow Configuration** (`FlowConfig`): The actual flow definition with steps
+
+## Demo
+
+Try the comprehensive demo:
+
+```bash
+python demo_packaging.py
+```
+
+## Requirements
+
+- Python 3.8+
+- Dependencies: aiohttp, pydantic, click, litellm
+
+## License
+
+MIT License