Metadata-Version: 2.4
Name: abstractflow
Version: 0.3.6
Summary: Diagram-based AI workflow generation built on AbstractCore
Author-email: AbstractFlow Team <contact@abstractflow.ai>
Maintainer-email: AbstractFlow Team <contact@abstractflow.ai>
License-Expression: MIT
Project-URL: Homepage, https://github.com/lpalbou/AbstractFlow
Project-URL: Documentation, https://abstractflow.readthedocs.io
Project-URL: Repository, https://github.com/lpalbou/AbstractFlow
Project-URL: Bug Tracker, https://github.com/lpalbou/AbstractFlow/issues
Project-URL: Changelog, https://github.com/lpalbou/AbstractFlow/blob/main/CHANGELOG.md
Keywords: ai,workflow,diagram,llm,automation,visual-programming,abstractcore,machine-learning
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: System :: Distributed Computing
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: AbstractRuntime>=0.4.0
Requires-Dist: abstractcore[tools]>=2.6.8
Requires-Dist: pydantic>=2.0.0
Requires-Dist: typing-extensions>=4.0.0
Provides-Extra: agent
Requires-Dist: abstractagent>=0.2.0; extra == "agent"
Provides-Extra: editor
Requires-Dist: abstractagent>=0.2.0; extra == "editor"
Requires-Dist: fastapi>=0.100.0; extra == "editor"
Requires-Dist: uvicorn[standard]>=0.23.0; extra == "editor"
Requires-Dist: websockets>=11.0.0; extra == "editor"
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: black>=23.0.0; extra == "dev"
Requires-Dist: isort>=5.12.0; extra == "dev"
Requires-Dist: flake8>=6.0.0; extra == "dev"
Requires-Dist: mypy>=1.0.0; extra == "dev"
Requires-Dist: pre-commit>=3.0.0; extra == "dev"
Provides-Extra: server
Requires-Dist: fastapi>=0.100.0; extra == "server"
Requires-Dist: uvicorn[standard]>=0.23.0; extra == "server"
Requires-Dist: websockets>=11.0.0; extra == "server"
Provides-Extra: ui
Requires-Dist: streamlit>=1.28.0; extra == "ui"
Requires-Dist: plotly>=5.15.0; extra == "ui"
Requires-Dist: networkx>=3.1.0; extra == "ui"
Provides-Extra: all
Requires-Dist: abstractflow[agent,dev,server,ui]; extra == "all"
Dynamic: license-file

# AbstractFlow

Diagram-based, **durable** AI workflows for Python.

AbstractFlow provides:
- A portable workflow format (`VisualFlow` JSON) and helpers to execute it from any host (`abstractflow.visual`).
- A simple programmatic API (`Flow`, `FlowRunner`) backed by **AbstractRuntime**.
- A reference visual editor app in `web/` (FastAPI backend + React frontend).

Project status: **Pre-alpha** (`pyproject.toml`: `Development Status :: 2 - Pre-Alpha`). Expect breaking changes.

## Capabilities (implemented)

- Execute programmatic flows (`Flow` → `FlowRunner`) with a default in-memory runtime.
- Execute portable `VisualFlow` JSON from any host process (`abstractflow.visual`).
- Durable waits and resumption via AbstractRuntime (e.g. user/event/schedule waits).
- Package a flow tree as a WorkflowBundle (`.flow`) via the CLI.
- Author/run VisualFlows in the reference web editor (`web/`).

Evidence (code): `abstractflow/runner.py`, `abstractflow/visual/executor.py`, `abstractflow/cli.py`, `web/backend/routes/ws.py`.

## Docs

- Start here: `docs/getting-started.md`
- API reference: `docs/api.md`
- VisualFlow format: `docs/visualflow.md`
- Visual editor: `docs/web-editor.md`
- CLI: `docs/cli.md`
- FAQ: `docs/faq.md`
- Architecture: `docs/architecture.md`
- Docs index: `docs/README.md`

## Installation

```bash
pip install abstractflow
```

Requirements: Python **3.10+** (`pyproject.toml`: `requires-python`).

Optional extras:
- Agent nodes (ReAct workflows): `pip install "abstractflow[agent]"`
- Visual editor backend (FastAPI): `pip install "abstractflow[server]"`
- Visual editor backend + Agent nodes (recommended): `pip install "abstractflow[editor]"`
- Dev tools (tests/formatting): `pip install "abstractflow[dev]"`

Notes:
- `abstractflow` depends on `AbstractRuntime` and `abstractcore[tools]` (see `pyproject.toml`).
- Some VisualFlow node types require additional packages (e.g. `memory_kg_*` nodes need `abstractmemory`).

## Quickstart (programmatic)

```python
from abstractflow import Flow, FlowRunner

flow = Flow("linear")
flow.add_node("double", lambda x: x * 2, input_key="value", output_key="doubled")
flow.add_node("add_ten", lambda x: x + 10, input_key="doubled", output_key="final")
flow.add_edge("double", "add_ten")
flow.set_entry("double")

result = FlowRunner(flow).run({"value": 5})
print(result)  # {"success": True, "result": 20}
```

## Quickstart (execute a VisualFlow JSON)

```python
import json
from abstractflow.visual import VisualFlow, execute_visual_flow

with open("my-flow.json", "r", encoding="utf-8") as f:
    vf = VisualFlow.model_validate(json.load(f))
result = execute_visual_flow(vf, {"prompt": "Hello"}, flows={vf.id: vf})
print(result)  # {"success": True, "waiting": False, "result": ...}
```

If your flow uses subflows, load all referenced `*.json` into the `flows={...}` mapping (see `docs/getting-started.md`).

## Visual editor (local)

The visual editor is split into:
- a **Python backend** (FastAPI) shipped with `abstractflow[editor]` (or `abstractflow[server]`)
- a **JS frontend** shipped as `@abstractframework/flow` (runs via `npx`)

```bash
# Terminal 1: Editor backend (FastAPI)
pip install "abstractflow[editor]"
abstractflow serve --reload --port 8080

# Terminal 2: Editor UI (static server + /api proxy)
npx @abstractframework/flow
```

Open:
- UI: http://localhost:3003
- Backend health: http://localhost:8080/api/health

Optional: run an AbstractGateway at http://127.0.0.1:8081 and configure it in the UI “Connect” modal (used for embeddings-backed KG and bundle publishing). See `docs/web-editor.md` and `docs/architecture.md`.

## CLI (WorkflowBundle `.flow`)

```bash
abstractflow bundle pack web/flows/ac-echo.json --out /tmp/ac-echo.flow
abstractflow bundle inspect /tmp/ac-echo.flow
abstractflow bundle unpack /tmp/ac-echo.flow --dir /tmp/ac-echo
```

See `docs/cli.md` and `abstractflow/cli.py`.

## Related projects

- AbstractRuntime (durable execution kernel): https://github.com/lpalbou/AbstractRuntime
- AbstractCore (providers/models/tools): https://github.com/lpalbou/AbstractCore
- AbstractAgent (ReAct/CodeAct): https://github.com/lpalbou/AbstractAgent

## Changelog

See `CHANGELOG.md`.

## Contributing

See `CONTRIBUTING.md`.

## Security

See `SECURITY.md`.

## Acknowledgments

See `ACKNOWLEDMENTS.md`.

## License

MIT. See `LICENSE`.
