WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-17 21:25:46 +02:00
Code Issues Packages Projects Releases Wiki Activity

Simplify assistants

Browse Source
This commit is contained in:
Lauren Hirata Singh
2025-05-12 13:37:25 -07:00
parent f5423783f7
commit 7ea406648f
5 changed files with 111 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/_scripts/notebook_hooks.py
+3 -1
View File
@@ -94,7 +94,9 @@ REDIRECT_MAP = {
"tutorials/introduction.ipynb": "concepts/why-langgraph.md",
# deployment redirects
"how-tos/deploy-self-hosted.md": "cloud/deployment/self_hosted_data_plane.md",
"concepts/self_hosted.md": "concepts/langgraph_self_hosted_data_plane.md"
"concepts/self_hosted.md": "concepts/langgraph_self_hosted_data_plane.md",
# assistant redirects
"cloud/how-tos/assistant_versioning.md": "cloud/how-tos/configuration_cloud.md"
}
docs/docs/cloud/how-tos/assistant_versioning.md
-152
View File
@@ -1,152 +0,0 @@
# How to version Assistants
!!! info "Prerequisites"
- [Assistants Overview](../../concepts/assistants.md)
- [How to create an Assistant](./configuration_cloud.md)
In this guide we will show you how to create, manage and use multiple versions of an assistant. If you have not already, please first see [this](./configuration_cloud.md) guide on creating an assistant. For this example, assume you have a graph with the following configuration schema:
=== "Python"
```python
class Config(BaseModel):
model_name: Literal["anthropic", "openai"] = "anthropic"
system_prompt: str
builder = StateGraph(State, config_schema=Config)
```
=== "Javascript"
```js
const ConfigAnnotation = Annotation.Root({
modelName: Annotation<z.enum(["openai", "anthropic"])>({
default: () => "anthropic",
}),
systemPrompt: Annotation<String>
});
// the rest of your code
const builder = new StateGraph(StateAnnotation, ConfigAnnotation);
```
And that you have the following assistant already created:
{
"assistant_id": "62e209ca-9154-432a-b9e9-2d75c7a9219b",
"graph_id": "agent",
"name": "Open AI Assistant"
"config": {
"configurable": {
"model_name": "openai",
"system_prompt": "You are a helpful assistant."
}
},
"metadata": {}
"created_at": "2024-08-31T03:09:10.230718+00:00",
"updated_at": "2024-08-31T03:09:10.230718+00:00",
}
## Create a new version for your assistant
### LangGraph SDK
To edit the assistant, use the `update` method. This will create a new version of the assistant with the provided edits. See the [Python](../reference/sdk/python_sdk_ref.md#langgraph_sdk.client.AssistantsClient.update) and [JS](../reference/sdk/js_ts_sdk_ref.md#update) SDK reference docs for more information.
!!! 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 previously versions.
For example, to update your assistant's system prompt:
=== "Python"
```python
openai_assistant_v2 = await client.assistants.update(
openai_assistant["assistant_id"],
config={
"configurable": {
"model_name": "openai",
"system_prompt": "You are an unhelpful assistant!",
}
},
)
```
=== "Javascript"
```js
const openaiAssistantV2 = await client.assistants.update(
openai_assistant["assistant_id"],
{
config: {
configurable: {
model_name: 'openai',
system_prompt: 'You are an unhelpful assistant!',
},
},
});
```
=== "CURL"
```bash
curl --request PATCH \
--url <DEPOLYMENT_URL>/assistants/<ASSISTANT_ID> \
--header 'Content-Type: application/json' \
--data '{
"config": {"model_name": "openai", "system_prompt": "You are an unhelpful assistant!"}
}'
```
This will create a new version of the assistant with the updated parameters and set this as the active version of your assistant. If you now run your graph and pass in this assistant id, it will use this latest version.
### LangGraph Platform UI
You can also edit assistants from the LangGraph Platform UI.
Inside your deployment, select the "Assistants" tab. This will load a table of all of the assistants in your deployment, across all graphs.
To edit an existing assistant, select the "Edit" button for the specified assistant. This will open a form where you can edit the assistant's name, description, and configuration.
Additionally, if using LangGraph Studio, you can edit the assistants and create new versions via the "Manage Assistants" button.
## Use a previous assistant version
### LangGraph SDK
You can also change the active version of your assistant. To do so, use the `setLatest` method.
In the example above, to rollback to the first version of the assistant:
=== "Python"
```python
await client.assistants.set_latest(openai_assistant['assistant_id'], 1)
```
=== "Javascript"
```js
await client.assistants.setLatest(openaiAssistant['assistant_id'], 1);
```
=== "CURL"
```bash
curl --request POST \
--url <DEPLOYMENT_URL>/assistants/<ASSISTANT_ID>/latest \
--header 'Content-Type: application/json' \
--data '{
"version": 1
}'
```
If you now run your graph and pass in this assistant id, it will use the first version of the assistant.
### LangGraph Platform UI
If using LangGraph Studio, to set the active version of your asssistant, click the "Manage Assistants" button and locate the assistant you would like to use. Select the assistant and the version, and then click the "Active" toggle. This will update the assistant to make the selected version active.
!!! warning "Deleting Assistants"
Deleting as assistant will delete ALL of it's versions. There is currently no way to delete a single version, but by pointing your assistant to the correct version you can skip any versions that you don't wish to use.
docs/docs/cloud/how-tos/configuration_cloud.md
+106 -9
View File
@@ -1,11 +1,6 @@
# How to create Assistants
# Manage assistants
!!! info "Prerequisites"
- [Assistants Overview](../../concepts/assistants.md)
- [Configuration](../../concepts/low_level.md#configuration)
In this guide we will show how to create and configure an assistant.
In this guide we will show how to create, configure, and manage an [assistant](../../concepts/assistants.md).
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`.
@@ -51,7 +46,7 @@ First, as a brief refresher on the concept of configurations, consider the follo
For more information on configurations, [see here](../../concepts/low_level.md#configuration).
## Creating an Assistant
## Create an assistant
### LangGraph SDK
@@ -123,7 +118,7 @@ To create a new assistant, select the "+ New assistant" button. This will open a
To confirm, click "Create assistant". This will take you to [LangGraph Studio](../../concepts/langgraph_studio.md) where you can test the assistant. If you go back to the "Assistants" tab in the deployment, you will see the newly created assistant in the table.
## Using an Assistant
## Use an assistant
### LangGraph SDK
@@ -228,3 +223,105 @@ Output:
### LangGraph Platform UI
Inside your deployment, select the "Assistants" tab. For the assistant you would like to use, click the "Studio" button. This will open LangGraph Studio with the selected assistant. When you submit an input (either in Graph or Chat mode), the selected assistant and its configuration will be used.
## Create a new version for your assistant
### LangGraph SDK
To edit the assistant, use the `update` method. This will create a new version of the assistant with the provided edits. See the [Python](../reference/sdk/python_sdk_ref.md#langgraph_sdk.client.AssistantsClient.update) and [JS](../reference/sdk/js_ts_sdk_ref.md#update) SDK reference docs for more information.
!!! 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 previously versions.
For example, to update your assistant's system prompt:
=== "Python"
```python
openai_assistant_v2 = await client.assistants.update(
openai_assistant["assistant_id"],
config={
"configurable": {
"model_name": "openai",
"system_prompt": "You are an unhelpful assistant!",
}
},
)
```
=== "Javascript"
```js
const openaiAssistantV2 = await client.assistants.update(
openai_assistant["assistant_id"],
{
config: {
configurable: {
model_name: 'openai',
system_prompt: 'You are an unhelpful assistant!',
},
},
});
```
=== "CURL"
```bash
curl --request PATCH \
--url <DEPOLYMENT_URL>/assistants/<ASSISTANT_ID> \
--header 'Content-Type: application/json' \
--data '{
"config": {"model_name": "openai", "system_prompt": "You are an unhelpful assistant!"}
}'
```
This will create a new version of the assistant with the updated parameters and set this as the active version of your assistant. If you now run your graph and pass in this assistant id, it will use this latest version.
### LangGraph Platform UI
You can also edit assistants from the LangGraph Platform UI.
Inside your deployment, select the "Assistants" tab. This will load a table of all of the assistants in your deployment, across all graphs.
To edit an existing assistant, select the "Edit" button for the specified assistant. This will open a form where you can edit the assistant's name, description, and configuration.
Additionally, if using LangGraph Studio, you can edit the assistants and create new versions via the "Manage Assistants" button.
## Use a previous assistant version
### LangGraph SDK
You can also change the active version of your assistant. To do so, use the `setLatest` method.
In the example above, to rollback to the first version of the assistant:
=== "Python"
```python
await client.assistants.set_latest(openai_assistant['assistant_id'], 1)
```
=== "Javascript"
```js
await client.assistants.setLatest(openaiAssistant['assistant_id'], 1);
```
=== "CURL"
```bash
curl --request POST \
--url <DEPLOYMENT_URL>/assistants/<ASSISTANT_ID>/latest \
--header 'Content-Type: application/json' \
--data '{
"version": 1
}'
```
If you now run your graph and pass in this assistant id, it will use the first version of the assistant.
### LangGraph Platform UI
If using LangGraph Studio, to set the active version of your asssistant, click the "Manage Assistants" button and locate the assistant you would like to use. Select the assistant and the version, and then click the "Active" toggle. This will update the assistant to make the selected version active.
!!! warning "Deleting Assistants"
Deleting as assistant will delete ALL of it's versions. There is currently no way to delete a single version, but by pointing your assistant to the correct version you can skip any versions that you don't wish to use.
docs/docs/concepts/assistants.md
+2 -2
View File
@@ -11,7 +11,7 @@ Imagine a general-purpose writing agent built on a common graph architecture. Wh
![assistant versions](img/assistants.png)
## Configuring Assistants
## Configuring assistants
Assistants build on the LangGraph open source concept of [configuration](low_level.md#configuration).
While configuration is available in the open source LangGraph library, assistants are only present in [LangGraph Platform](langgraph_platform.md).
@@ -19,7 +19,7 @@ This is due to the fact that Assistants are tightly coupled to your deployed gra
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](../cloud/reference/api/api_ref.html) and [this how-to](../cloud/how-tos/configuration_cloud.md) for more details on how to create assistants.
## Versioning Assistants
## Versioning assistants
Assistants support versioning to track changes over time.
Once you've created an assistant, subsequent edits to that assistant will create new versions. See [this how-to](../cloud/how-tos/assistant_versioning.md) for more details on how to manage assistant versions.
docs/mkdocs.yml
-1
View File
@@ -194,7 +194,6 @@ nav:
- Assistants:
- Overview: concepts/assistants.md
- cloud/how-tos/configuration_cloud.md
- cloud/how-tos/assistant_versioning.md
- Threads:
- Overview: cloud/concepts/threads.md
- cloud/how-tos/copy_threads.md