LlamaAgents Server
HTTP server for deploying LlamaIndex Workflows as web services. Built on Starlette and Uvicorn.
Installation
pip install llama-agents-server
Quick Start
Create a server file (e.g., my_server.py):
import asyncio
from workflows import Workflow, step
from workflows.context import Context
from workflows.events import Event, StartEvent, StopEvent
from llama_agents.server import WorkflowServer
class StreamEvent(Event):
sequence: int
class GreetingWorkflow(Workflow):
@step
async def greet(self, ctx: Context, ev: StartEvent) -> StopEvent:
for i in range(3):
ctx.write_event_to_stream(StreamEvent(sequence=i))
name = ev.get("name", "World")
return StopEvent(result=f"Hello, {name}!")
server = WorkflowServer()
server.add_workflow("greet", GreetingWorkflow())
if __name__ == "__main__":
asyncio.run(server.serve("0.0.0.0", 8080))
Or run it with the CLI:
llama-agents-server my_server.py
Features
- REST API for running, streaming, and managing workflows
- Debugger UI automatically mounted at
/for visualizing and debugging workflows - Event streaming via newline-delimited JSON or Server-Sent Events
- Human-in-the-loop support for interactive workflows
- Persistence with built-in SQLite store (or bring your own via
AbstractWorkflowStore)
Client
Use llama-agents-client to interact with deployed servers programmatically.
Documentation
See the full deployment guide for API details, persistence configuration, and more.
Metadata
Release files for llama-agents-server 0.8.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| llama_agents_server-0.8.0.tar.gz | 57.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llama_agents_server-0.8.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 137.6 kB
Release files / llama_agents_server-0.8.0.tar.gz
| Download URL | llama_agents_server-0.8.0.tar.gz |
|---|---|
| Size | 57.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
57ffb5a6a939cd92c21658bf0428de23b454a2c80a9bdd8dec1fb6e2090fd824
|
|
BLAKE2b-256 checksum How to use checksums |
3bf0f2ed25f79b95e63a7cf3ec2862744018e2f7b06e1403fddd2421688763aa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.15 {"installer":{"name":"uv","version":"0.12.15","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / llama_agents_server-0.8.0-py3-none-any.whl
| Download URL | llama_agents_server-0.8.0-py3-none-any.whl |
|---|---|
| Size | 79.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9bed5fb4c7d497d4ae3ae5f0ad6b1c1d3ffe04efda447222897d121bb4ed5d4b
|
|
BLAKE2b-256 checksum How to use checksums |
6425bc90cdfe4d24e37a45c20e27696d7b05bb4db07ddc0c836546e22fd9fb03
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.15 {"installer":{"name":"uv","version":"0.12.15","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
