Revise README for Agent Stack Server SDK #1711
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||||
|---|---|---|---|---|---|---|---|---|
| @@ -1,45 +1,120 @@ | ||||||||
| # Agent Stack Server SDK | ||||||||
|
|
||||||||
| Python SDK for deploying agents to Agent Stack infrastructure. | ||||||||
|
|
||||||||
| [](https://pypi.org/project/agentstack-sdk/) | ||||||||
| [](https://opensource.org/licenses/Apache-2.0) | ||||||||
| [](https://lfaidata.foundation/projects/) | ||||||||
|
|
||||||||
| ## Overview | ||||||||
|
|
||||||||
| The `agentstack-sdk` provides Python utilities for wrapping agents built with any framework (LangChain, CrewAI, BeeAI Framework, etc.) for deployment on Agent Stack. It handles the A2A (Agent-to-Agent) protocol implementation, platform service integration, and runtime requirements so you can focus on agent logic. | ||||||||
|
|
||||||||
| ## Key Features | ||||||||
|
|
||||||||
| - **Framework-Agnostic Deployment** - Wrap agents from any framework for Agent Stack deployment | ||||||||
| - **A2A Protocol Support** - Automatic handling of Agent-to-Agent communication | ||||||||
| - **Platform Service Integration** - Connect to Agent Stack's managed LLM, embedding, file storage, and vector store services | ||||||||
| - **Agent Wrapper** - Opinionated utilities with `yield` semantics and autowired services | ||||||||
| - **Context Storage** - Manage data associated with conversation contexts | ||||||||
|
|
||||||||
| ## Installation | ||||||||
|
|
||||||||
| ```bash | ||||||||
| uv add agentstack-sdk | ||||||||
| ``` | ||||||||
|
|
||||||||
| ## Quickstart | ||||||||
|
|
||||||||
| ```python | ||||||||
| import os | ||||||||
| from a2a.types import AgentSkill, Message | ||||||||
| from agentstack_sdk.server import Server | ||||||||
| from agentstack_sdk.server.context import RunContext | ||||||||
| from agentstack_sdk.server.store.platform_context_store import PlatformContextStore | ||||||||
|
|
||||||||
| # Initialize server | ||||||||
| server = Server() | ||||||||
|
|
||||||||
| # Define your agent | ||||||||
| @server.agent( | ||||||||
| name="My Agent", | ||||||||
| skills=[ | ||||||||
| AgentSkill( | ||||||||
| id="my-agent-skill", | ||||||||
| name="My Agent", | ||||||||
| description="Agent description here", | ||||||||
| tags=["Chat"], | ||||||||
| examples=["Example query 1", "Example query 2"] | ||||||||
| ) | ||||||||
| ], | ||||||||
| ) | ||||||||
| async def my_agent( | ||||||||
| input: Message, | ||||||||
| context: RunContext, | ||||||||
| ): | ||||||||
| """Your agent logic here""" | ||||||||
|
|
||||||||
| # Store incoming message | ||||||||
| await context.store(input) | ||||||||
|
|
||||||||
| # Extract user message | ||||||||
| user_msg = "".join( | ||||||||
| part.root.text for part in input.parts | ||||||||
| if part.root.kind == "text" | ||||||||
| ) | ||||||||
|
|
||||||||
| # Process and yield response | ||||||||
| response_text = f"You said: {user_msg}" | ||||||||
| yield response_text | ||||||||
|
|
||||||||
| # Store response in context | ||||||||
| from agentstack_sdk.a2a.types import AgentMessage | ||||||||
| await context.store(AgentMessage(text=response_text)) | ||||||||
|
||||||||
| from agentstack_sdk.a2a.types import AgentMessage | |
| await context.store(AgentMessage(text=response_text)) | |
| await context.store(AgentMessage(text=response_text)) |
Outdated
Contributor
There was a problem hiding this comment.
The os.getenv function's default value must be a string. Providing an integer 8000 will cause a TypeError if the PORT environment variable is not set. The default value should be a string, "8000", which is then converted to an integer.
Suggested change
| port=int(os.getenv("PORT", 8000)), | |
| port=int(os.getenv("PORT", "8000")), |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The
my_agentfunction is an async generator, but it lacks a return type hint. Adding a type hint makes the function's contract explicit, improving readability and enabling better static analysis. You'll need to importAsyncGeneratorfromcollections.abcat the top of the file.