| Name | llama-deploy JSON |
| Version |
0.6.1
JSON |
| download |
| home_page | None |
| Summary | None |
| upload_time | 2025-02-13 14:42:36 |
| maintainer | Logan Markewich |
| docs_url | None |
| author | Logan Markewich |
| requires_python | <4.0,>=3.10 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
[](https://pypi.org/project/llama-deploy)
[](https://pypi.org/project/llama-deploy)
[](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/)
[](https://github.com/run-llama/llama_deploy/actions/workflows/unit_test.yml)
[](https://github.com/run-llama/llama_deploy/actions/workflows/e2e_test.yml)
[](https://coveralls.io/github/run-llama/llama_deploy?branch=main)
# 🦙 LlamaDeploy 🤖
LlamaDeploy (formerly `llama-agents`) is an async-first framework for deploying, scaling, and productionizing agentic
multi-service systems based on [workflows from `llama_index`](https://docs.llamaindex.ai/en/stable/understanding/workflows/).
With LlamaDeploy, you can build any number of workflows in `llama_index` and then run them as services, accessible
through a HTTP API by a user interface or other services part of your system.
The goal of LlamaDeploy is to easily transition something that you built in a notebook to something running on the
cloud with the minimum amount of changes to the original code, possibly zero. In order to make this transition a
pleasant one, you can interact with LlamaDeploy in two ways:
- Using the [`llamactl`](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/50_llamactl/) CLI from a shell.
- Through the [_LlamaDeploy SDK_](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/40_python_sdk/) from a Python application or script.
Both the SDK and the CLI are part of the LlamaDeploy Python package. To install, just run:
```bash
pip install llama_deploy
```
> [!TIP]
> For a comprehensive guide to LlamaDeploy's architecture and detailed descriptions of its components, visit our
[official documentation](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/).
## Why LlamaDeploy?
1. **Seamless Deployment**: It bridges the gap between development and production, allowing you to deploy `llama_index`
workflows with minimal changes to your code.
2. **Scalability**: The microservices architecture enables easy scaling of individual components as your system grows.
3. **Flexibility**: By using a hub-and-spoke architecture, you can easily swap out components (like message queues) or
add new services without disrupting the entire system.
4. **Fault Tolerance**: With built-in retry mechanisms and failure handling, LlamaDeploy adds robustness in
production environments.
5. **State Management**: The control plane manages state across services, simplifying complex multi-step processes.
6. **Async-First**: Designed for high-concurrency scenarios, making it suitable for real-time and high-throughput
applications.
> [!NOTE]
> This project was initially released under the name `llama-agents`, but the introduction of [Workflows](https://docs.llamaindex.ai/en/stable/module_guides/workflow/#workflows) in `llama_index` turned out to be the most intuitive way for our users to develop agentic applications. We then decided to add new agentic features in `llama_index` directly, and focus LlamaDeploy on closing the gap between local development and remote execution of agents as services.
## Getting Started
The fastest way to start using LlamaDeploy is playing with a practical example. This repository contains a few applications you can use as a reference:
- [Quick start](examples/quick_start)
- [Use a deployment from a web-based user interface](examples/python_fullstack)
- [Message queue examples](examples/message-queue-integrations)
We recommend to start from the [Quick start](examples/quick_start) example and move
to [Use a deployment from a web-based user interface](examples/python_fullstack)
immediately after. Each folder contains a README file that will guide you through
the process.
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-deploy",
"maintainer": "Logan Markewich",
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": "logan@llamaindex.ai",
"keywords": null,
"author": "Logan Markewich",
"author_email": "logan.markewich@live.com",
"download_url": "https://files.pythonhosted.org/packages/dc/78/c3c5973a0d619fb650b152eb581d33897584cb32e6f1972df7bd2badba2b/llama_deploy-0.6.1.tar.gz",
"platform": null,
"description": "[](https://pypi.org/project/llama-deploy)\n[](https://pypi.org/project/llama-deploy)\n[](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/)\n\n\n[](https://github.com/run-llama/llama_deploy/actions/workflows/unit_test.yml)\n[](https://github.com/run-llama/llama_deploy/actions/workflows/e2e_test.yml)\n[](https://coveralls.io/github/run-llama/llama_deploy?branch=main)\n\n\n# \ud83e\udd99 LlamaDeploy \ud83e\udd16\n\nLlamaDeploy (formerly `llama-agents`) is an async-first framework for deploying, scaling, and productionizing agentic\nmulti-service systems based on [workflows from `llama_index`](https://docs.llamaindex.ai/en/stable/understanding/workflows/).\nWith LlamaDeploy, you can build any number of workflows in `llama_index` and then run them as services, accessible\nthrough a HTTP API by a user interface or other services part of your system.\n\nThe goal of LlamaDeploy is to easily transition something that you built in a notebook to something running on the\ncloud with the minimum amount of changes to the original code, possibly zero. In order to make this transition a\npleasant one, you can interact with LlamaDeploy in two ways:\n\n- Using the [`llamactl`](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/50_llamactl/) CLI from a shell.\n- Through the [_LlamaDeploy SDK_](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/40_python_sdk/) from a Python application or script.\n\nBoth the SDK and the CLI are part of the LlamaDeploy Python package. To install, just run:\n\n```bash\npip install llama_deploy\n```\n> [!TIP]\n> For a comprehensive guide to LlamaDeploy's architecture and detailed descriptions of its components, visit our\n[official documentation](https://docs.llamaindex.ai/en/latest/module_guides/llama_deploy/).\n\n## Why LlamaDeploy?\n\n1. **Seamless Deployment**: It bridges the gap between development and production, allowing you to deploy `llama_index`\n workflows with minimal changes to your code.\n2. **Scalability**: The microservices architecture enables easy scaling of individual components as your system grows.\n3. **Flexibility**: By using a hub-and-spoke architecture, you can easily swap out components (like message queues) or\n add new services without disrupting the entire system.\n4. **Fault Tolerance**: With built-in retry mechanisms and failure handling, LlamaDeploy adds robustness in\n production environments.\n5. **State Management**: The control plane manages state across services, simplifying complex multi-step processes.\n6. **Async-First**: Designed for high-concurrency scenarios, making it suitable for real-time and high-throughput\n applications.\n\n> [!NOTE]\n> This project was initially released under the name `llama-agents`, but the introduction of [Workflows](https://docs.llamaindex.ai/en/stable/module_guides/workflow/#workflows) in `llama_index` turned out to be the most intuitive way for our users to develop agentic applications. We then decided to add new agentic features in `llama_index` directly, and focus LlamaDeploy on closing the gap between local development and remote execution of agents as services.\n\n## Getting Started\n\nThe fastest way to start using LlamaDeploy is playing with a practical example. This repository contains a few applications you can use as a reference:\n\n- [Quick start](examples/quick_start)\n- [Use a deployment from a web-based user interface](examples/python_fullstack)\n- [Message queue examples](examples/message-queue-integrations)\n\nWe recommend to start from the [Quick start](examples/quick_start) example and move\nto [Use a deployment from a web-based user interface](examples/python_fullstack)\nimmediately after. Each folder contains a README file that will guide you through\nthe process.\n",
"bugtrack_url": null,
"license": null,
"summary": null,
"version": "0.6.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "cfa7514f2604acbcc8992cb3c81c3ecd3daad80099c7e7cdff8b5c6e8ff0be94",
"md5": "0f02ee4f2e55a0aacf2abb1641878553",
"sha256": "35e683c56448ccfcc7cee3627afbea7895b0b10448c4d21a881c118906505a8b"
},
"downloads": -1,
"filename": "llama_deploy-0.6.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0f02ee4f2e55a0aacf2abb1641878553",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 82302,
"upload_time": "2025-02-13T14:42:35",
"upload_time_iso_8601": "2025-02-13T14:42:35.382998Z",
"url": "https://files.pythonhosted.org/packages/cf/a7/514f2604acbcc8992cb3c81c3ecd3daad80099c7e7cdff8b5c6e8ff0be94/llama_deploy-0.6.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "dc78c3c5973a0d619fb650b152eb581d33897584cb32e6f1972df7bd2badba2b",
"md5": "eacca79ec17cd360cfab2fc16028a6c4",
"sha256": "2b4a6235a34190912091c64331af2c3ba05f3080ea7110e10c1b3a41d7d60dd4"
},
"downloads": -1,
"filename": "llama_deploy-0.6.1.tar.gz",
"has_sig": false,
"md5_digest": "eacca79ec17cd360cfab2fc16028a6c4",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 53364,
"upload_time": "2025-02-13T14:42:36",
"upload_time_iso_8601": "2025-02-13T14:42:36.624894Z",
"url": "https://files.pythonhosted.org/packages/dc/78/c3c5973a0d619fb650b152eb581d33897584cb32e6f1972df7bd2badba2b/llama_deploy-0.6.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-13 14:42:36",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-deploy"
}
