Skip to content

chore: update LGP docs to use new context API #144

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

chore: update LGP docs to use new context API #144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
28814d8
use new context API
sydney-runkle Aug 10, 2025
fe2a15d
more notes
sydney-runkle Aug 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/langgraph-platform/assistants.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ The LangGraph Cloud API provides several endpoints for creating and managing ass

## Configuration

Assistants build on the LangGraph open source concept of [configuration](https://langchain-ai.github.io/langgraph/concepts/low_level/#configuration).
Assistants build on the LangGraph open source concept of [configuration](https://langchain-ai.github.io/langgraph/concepts/low_level/#runtime-context).
While configuration is available in the open source LangGraph library, assistants are only present in [LangGraph Platform](/langgraph-platform/index). This is due to the fact that assistants are tightly coupled to your deployed graph. Upon deployment, LangGraph Server will automatically create a default assistant for each graph using the graph's default configuration settings.

In practice, an assistant is just an _instance_ of a graph with a specific configuration. Therefore, multiple assistants can reference the same graph but can contain different configurations (e.g. prompts, models, tools). The LangGraph Server API provides several endpoints for creating and managing assistants. See the [API reference](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref/) and [this how-to](/langgraph-platform/configuration-cloud) for more details on how to create assistants.
Expand Down
57 changes: 25 additions & 32 deletions src/langgraph-platform/configuration-cloud.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,21 +4,20 @@ sidebarTitle: Manage assistants
---
In this guide we will show how to create, configure, and manage an [assistant](/langgraph-platform/assistants).

First, as a brief refresher on the concept of configurations, consider the following simple `call_model` node and configuration schema. Observe that this node tries to read and use the `model_name` as defined by the `config` object's `configurable`.
First, as a brief refresher on the concept of context, consider the following simple `call_model` node and context schema.
Observe that this node tries to read and use the `model_name` as defined by the `context` object's `model_name` field.

<Tabs>
<Tab title="Python">
```python

class ConfigSchema(TypedDict):
class ContextSchema(TypedDict):
model_name: str

builder = StateGraph(AgentState, config_schema=ConfigSchema)
builder = StateGraph(AgentState, context_schema=ContextSchema)

def call_model(state, config):
def call_model(state, runtime: Runtime[ContextSchema]):
messages = state["messages"]
model_name = config.get('configurable', {}).get("model_name", "anthropic")
model = _get_model(model_name)
model = _get_model(runtime.context.get("model_name", "anthropic"))
response = model.invoke(messages)
# We return a list, because this will get added to the existing list
return {"messages": [response]}
Expand All @@ -28,17 +27,16 @@ First, as a brief refresher on the concept of configurations, consider the follo
```js
import { Annotation } from "@langchain/langgraph";

const ConfigSchema = Annotation.Root({
const ContextSchema = Annotation.Root({
model_name: Annotation<string>,
system_prompt:
});

const builder = new StateGraph(AgentState, ConfigSchema)
const builder = new StateGraph(AgentState, ContextSchema)

function callModel(state: State, config: RunnableConfig) {
function callModel(state: State, runtime: Runtime[ContextSchema]) {
const messages = state.messages;
const modelName = config.configurable?.model_name ?? "anthropic";
const model = _getModel(modelName);
const model = _getModel(runtime.context.model_name ?? "anthropic");
const response = model.invoke(messages);
// We return a list, because this will get added to the existing list
return { messages: [response] };
Expand All @@ -55,7 +53,7 @@ For more information on configurations, [see here](/langgraph-platform/configura

To create an assistant, use the [LangGraph SDK](/langgraph-platform/sdk) `create` method. See the [Python](/langgraph-platform/python-sdk#langgraph_sdk.client.AssistantsClient.create) and [JS](/langgraph-platform/js-ts-sdk#create) SDK reference docs for more information.

This example uses the same configuration schema as above, and creates an assistant with `model_name` set to `openai`.
This example uses the same context schema as above, and creates an assistant with `model_name` set to `openai`.

<Tabs>
<Tab title="Python">
Expand All @@ -65,7 +63,7 @@ This example uses the same configuration schema as above, and creates an assista
client = get_client(url=<DEPLOYMENT_URL>)
openai_assistant = await client.assistants.create(
# "agent" is the name of a graph we deployed
"agent", config={"configurable": {"model_name": "openai"}}, name="Open AI Assistant"
"agent", context={"model_name": "openai"}, name="Open AI Assistant"
)

print(openai_assistant)
Expand All @@ -79,7 +77,7 @@ This example uses the same configuration schema as above, and creates an assista
const openAIAssistant = await client.assistants.create({
graphId: 'agent',
name: "Open AI Assistant",
config: { "configurable": { "model_name": "openai" } },
context: { "model_name": "openai" },
});

console.log(openAIAssistant);
Expand All @@ -90,7 +88,7 @@ This example uses the same configuration schema as above, and creates an assista
curl --request POST \
--url <DEPLOYMENT_URL>/assistants \
--header 'Content-Type: application/json' \
--data '{"graph_id":"agent", "config":{"configurable":{"model_name":"openai"}}, "name": "Open AI Assistant"}'
--data '{"graph_id":"agent", "context":{"model_name":"openai"}, "name": "Open AI Assistant"}'
```
</Tab>
</Tabs>
Expand All @@ -102,11 +100,9 @@ Output:
"assistant_id": "62e209ca-9154-432a-b9e9-2d75c7a9219b",
"graph_id": "agent",
"name": "Open AI Assistant"
"config": {
"configurable": {
"context": {
"model_name": "openai"
}
},
"metadata": {}
"created_at": "2024-08-31T03:09:10.230718+00:00",
"updated_at": "2024-08-31T03:09:10.230718+00:00",
Expand Down Expand Up @@ -239,7 +235,7 @@ To edit the assistant, use the `update` method. This will create a new version o

<Note>
**Note**
You must pass in the ENTIRE config (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.
You must pass in the ENTIRE context (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.
</Note>

For example, to update your assistant's system prompt:
Expand All @@ -249,11 +245,9 @@ For example, to update your assistant's system prompt:
```python
openai_assistant_v2 = await client.assistants.update(
openai_assistant["assistant_id"],
config={
"configurable": {
"model_name": "openai",
"system_prompt": "You are an unhelpful assistant!",
}
context={
"model_name": "openai",
"system_prompt": "You are an unhelpful assistant!",
},
)
```
Expand All @@ -263,13 +257,12 @@ For example, to update your assistant's system prompt:
const openaiAssistantV2 = await client.assistants.update(
openai_assistant["assistant_id"],
{
config: {
configurable: {
model_name: 'openai',
system_prompt: 'You are an unhelpful assistant!',
},
context: {
model_name: 'openai',
system_prompt: 'You are an unhelpful assistant!',
},
},
});
);
```
</Tab>
<Tab title="CURL">
Expand All @@ -278,7 +271,7 @@ For example, to update your assistant's system prompt:
--url <DEPOLYMENT_URL>/assistants/<ASSISTANT_ID> \
--header 'Content-Type: application/json' \
--data '{
"config": {"model_name": "openai", "system_prompt": "You are an unhelpful assistant!"}
"context": {"model_name": "openai", "system_prompt": "You are an unhelpful assistant!"}
}'
```
</Tab>
Expand Down
8 changes: 4 additions & 4 deletions src/langgraph-platform/setup-app-requirements-txt.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ Dependencies can optionally be specified in one of the following files: `pyproje
The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:

```
langgraph>=0.3.27
langgraph>=0.6.0
langgraph-sdk>=0.1.66
langgraph-checkpoint>=2.0.23
langchain-core>=0.2.38
Expand Down Expand Up @@ -114,11 +114,11 @@ from langgraph.graph import StateGraph, END, START
from my_agent.utils.nodes import call_model, should_continue, tool_node # import nodes
from my_agent.utils.state import AgentState # import state

# Define the config
class GraphConfig(TypedDict):
# Define the runtime context
class GraphContext(TypedDict):
model_name: Literal["anthropic", "openai"]

workflow = StateGraph(AgentState, config_schema=GraphConfig)
workflow = StateGraph(AgentState, context_schema=GraphContext)
workflow.add_node("agent", call_model)
workflow.add_node("action", tool_node)
workflow.add_edge(START, "agent")
Expand Down
10 changes: 5 additions & 5 deletions src/langgraph-platform/setup-pyproject.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ Dependencies can optionally be specified in one of the following files: `pyproje
The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:

```
langgraph>=0.3.27
langgraph>=0.6.0
langgraph-sdk>=0.1.66
langgraph-checkpoint>=2.0.23
langchain-core>=0.2.38
Expand Down Expand Up @@ -77,7 +77,7 @@ license = {text = "MIT"}
readme = "README.md"
requires-python = ">=3.9"
dependencies = [
"langgraph>=0.2.0",
"langgraph>=0.6.0",
"langchain-fireworks>=0.1.3"
]

Expand Down Expand Up @@ -127,11 +127,11 @@ from langgraph.graph import StateGraph, END, START
from my_agent.utils.nodes import call_model, should_continue, tool_node # import nodes
from my_agent.utils.state import AgentState # import state

# Define the config
class GraphConfig(TypedDict):
# Define the runtime context
class GraphContext(TypedDict):
model_name: Literal["anthropic", "openai"]

workflow = StateGraph(AgentState, config_schema=GraphConfig)
workflow = StateGraph(AgentState, context_schema=GraphContext)
workflow.add_node("agent", call_model)
workflow.add_node("action", tool_node)
workflow.add_edge(START, "agent")
Expand Down