mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-08-23 16:12:25 +02:00
Sydney RunkleandGitHub
46fed9d161
Adding type safe streaming + more robust pydantic + dataclass support on graph outputs * type safe streaming via #6931 * type safe invoke via https://github.com/langchain-ai/langgraph/pull/6963 * actually thread through types via parametrization in https://github.com/langchain-ai/langgraph/pull/7009 * deprecation of backwards compatible accessor via https://github.com/langchain-ai/langgraph/pull/7011 full spec of changes: https://github.com/langchain-ai/langgraph/issues/7008 proving out that required changes are minimal even when we update the default to v2: https://github.com/langchain-ai/langchain/pull/35541
LangGraph Python SDK
This repository contains the Python SDK for interacting with the LangSmith Deployment REST API.
Quick Start
To get started with the Python SDK, install the package
pip install -U langgraph-sdk
You will need a running LangGraph API server. If you're running a server locally using langgraph-cli, SDK will automatically point at http://localhost:8123, otherwise
you would need to specify the server URL when creating a client.
from langgraph_sdk import get_client
# If you're using a remote server, initialize the client with `get_client(url=REMOTE_URL)`
client = get_client()
# List all assistants
assistants = await client.assistants.search()
# We auto-create an assistant for each graph you register in config.
agent = assistants[0]
# Start a new thread
thread = await client.threads.create()
# Start a streaming run
input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
async for chunk in client.runs.stream(thread['thread_id'], agent['assistant_id'], input=input):
print(chunk)