mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-09-11 04:07:52 +02:00
feat(docs): assistants and threads and faqs (#4642)
This commit is contained in:
lc-arjun
@@ -1,15 +1,19 @@
|
||||
# Invoke Assistant
|
||||
# How to manage Assistants
|
||||
|
||||
The LangGraph Studio lets you test different configurations and inputs to your graph. It also provides a nice visualization of your graph during execution so it is easy to see which nodes are being run and what the outputs of each individual node are.
|
||||
!!! info "Prerequisites"
|
||||
|
||||
1. The LangGraph Studio UI displays a visualization of the selected assistant.
|
||||
1. In the top-left dropdown menu of the left-hand pane, select an assistant.
|
||||
1. In the bottom of the left-hand pane, edit the `Input` and `Configure` the assistant.
|
||||
1. Select `Submit` to invoke the selected assistant.
|
||||
1. View output of the invocation in the right-hand pane.
|
||||
- [Assistants Overview](../../concepts/assistants.md)
|
||||
|
||||
The following video shows these exact steps being carried out:
|
||||
LangGraph Studio lets you view, edit, and update your assistants, and allows you to run your graph using these assistant configurations.
|
||||
|
||||
<video controls allowfullscreen="true" poster="../img/studio_input_poster.png">
|
||||
<source src="../img/studio_input.mp4" type="video/mp4">
|
||||
</video>
|
||||
## Graph mode
|
||||
|
||||
To view your assistants, click the "Manage Assistants" button in the bottom left corner.
|
||||
|
||||
This opens a modal for you to view all the assistants for the selected graph. Specify the assistant and its version you would like to mark as "Active", and this assistant will be used when submitting runs.
|
||||
|
||||
By default, the "Default configuration" option will be active. This option reflects the default configuration defined in your graph. Edits made to this configuration will be used to update the run-time configuration, but will not update or create a new assistant unless you click "Create new assistant".
|
||||
|
||||
## Chat mode
|
||||
|
||||
Chat mode enables you to switch through the different assistants in your graph via the dropdown selector at the top of the page. To create, edit, or delete assistants, use Graph mode.
|
||||
@@ -0,0 +1,50 @@
|
||||
# LangGraph Studio FAQs
|
||||
|
||||
## Why is my project failing to start?
|
||||
|
||||
A project may fail to start if the configuration file is defined incorrectly, or if required environment variables are missing. See [here](../../reference/cli.md#configuration-file) for how your configuration file should be defined.
|
||||
|
||||
## How does interrupt work?
|
||||
|
||||
When you select the `Interrupts` dropdown and select a node to interrupt the graph will pause execution before and after (unless the node goes straight to `END`) that node has run. This means that you will be able to both edit the state before the node is ran and the state after the node has ran. This is intended to allow developers more fine-grained control over the behavior of a node and make it easier to observe how the node is behaving. You will not be able to edit the state after the node has ran if the node is the final node in the graph.
|
||||
|
||||
For more information on interrupts and human in the loop, see [here](./human_in_the_loop.md).
|
||||
|
||||
## Why are extra edges showing up in my graph?
|
||||
|
||||
If you don't define your conditional edges carefully, you might notice extra edges appearing in your graph. This is because without proper definition, LangGraph Studio assumes the conditional edge could access all other nodes. In order for this to not be the case, you need to be explicit about how you define the nodes the conditional edge routes to. There are two ways you can do this:
|
||||
|
||||
### Solution 1: Include a path map
|
||||
|
||||
The first way to solve this is to add path maps to your conditional edges. A path map is just a dictionary or array that maps the possible outputs of your router function with the names of the nodes that each output corresponds to. The path map is passed as the third argument to the `add_conditional_edges` function like so:
|
||||
|
||||
=== "Python"
|
||||
|
||||
```python
|
||||
graph.add_conditional_edges("node_a", routing_function, {True: "node_b", False: "node_c"})
|
||||
```
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
```ts
|
||||
graph.addConditionalEdges("node_a", routingFunction, { true: "node_b", false: "node_c" });
|
||||
```
|
||||
|
||||
In this case, the routing function returns either True or False, which map to `node_b` and `node_c` respectively.
|
||||
|
||||
### Solution 2: Update the typing of the router (Python only)
|
||||
|
||||
Instead of passing a path map, you can also be explicit about the typing of your routing function by specifying the nodes it can map to using the `Literal` python definition. Here is an example of how to define a routing function in that way:
|
||||
|
||||
```python
|
||||
def routing_function(state: GraphState) -> Literal["node_b","node_c"]:
|
||||
if state['some_condition'] == True:
|
||||
return "node_b"
|
||||
else:
|
||||
return "node_c"
|
||||
```
|
||||
|
||||
|
||||
## Why is my graph taking so long to startup?
|
||||
|
||||
The LangGraph Studio interacts with a local LangGraph API server. To stay aligned with ongoing updates, the LangGraph API requires regular rebuilding. As a result, you may occasionally experience slight delays when starting up your project.
|
||||
@@ -44,7 +44,15 @@ If successful, you will see the following logs:
|
||||
>
|
||||
> - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
|
||||
|
||||
Once running, you will automatically be directed to LangGraph Studio. You can manually access Studio by navigating to the following URL: `https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024`. If running your server at a different host or port, simply update the `baseUrl` to match.
|
||||
Once running, you will automatically be directed to LangGraph Studio.
|
||||
|
||||
|
||||
If your server is already running, to access Studio, either:
|
||||
|
||||
1. Directly navigate to the following URL: `https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024`.
|
||||
2. Within LangSmith, navigate to the LangGraph Platform Deployments tab, click the "LangGraph Studio" button, enter `http://127.0.0.1:2024` and click "Connect".
|
||||
|
||||
If running your server at a different host or port, simply update the `baseUrl` to match.
|
||||
|
||||
### (Optional) Attach a debugger
|
||||
|
||||
@@ -61,21 +69,27 @@ langgraph dev --debug-port 5678
|
||||
Then attach your preferred debugger:
|
||||
|
||||
=== "VS Code"
|
||||
Add this configuration to `launch.json`:
|
||||
`json
|
||||
{
|
||||
"name": "Attach to LangGraph",
|
||||
"type": "debugpy",
|
||||
"request": "attach",
|
||||
"connect": {
|
||||
"host": "0.0.0.0",
|
||||
"port": 5678
|
||||
Add this configuration to `launch.json`:
|
||||
```json
|
||||
{
|
||||
"name": "Attach to LangGraph",
|
||||
"type": "debugpy",
|
||||
"request": "attach",
|
||||
"connect": {
|
||||
"host": "0.0.0.0",
|
||||
"port": 5678
|
||||
}
|
||||
}
|
||||
}
|
||||
`
|
||||
Specify the port number you chose in the previous step.
|
||||
```
|
||||
Specify the port number you chose in the previous step.
|
||||
|
||||
=== "PyCharm"
|
||||
1. Go to Run → Edit Configurations
|
||||
2. Click + and select "Python Debug Server"
|
||||
3. Set IDE host name: `localhost`
|
||||
4. Set port: `5678` (or the port number you chose in the previous step)
|
||||
5. Click "OK" and start debugging
|
||||
|
||||
=== "PyCharm" 1. Go to Run → Edit Configurations 2. Click + and select "Python Debug Server" 3. Set IDE host name: `localhost` 4. Set port: `5678` (or the port number you chose in the previous step) 5. Click "OK" and start debugging
|
||||
|
||||
## Next steps
|
||||
|
||||
|
||||
@@ -1,23 +1,30 @@
|
||||
# Interacting with Threads in Studio
|
||||
# How to manage Threads
|
||||
|
||||
## View Thread
|
||||
!!! info "Prerequisites"
|
||||
|
||||
- [Threads Overview](../concepts/threads.md)
|
||||
|
||||
Studio allows you to view threads from the server and edit their state.
|
||||
|
||||
## View Threads
|
||||
|
||||
### Graph mode
|
||||
|
||||
1. In the top of the right-hand pane, select the `New Thread` dropdown menu to view existing threads.
|
||||
1. View the state of the thread (i.e. the output) in the right-hand pane.
|
||||
1. Select the desired thread, and the thread history will populate in the right-hand side of the page.
|
||||
1. To create a new thread, select `+ New Thread`.
|
||||
|
||||
The following video shows these exact steps being carried out:
|
||||
### Chat mode
|
||||
|
||||
<video controls="true" allowfullscreen="true" poster="../img/studio_threads_poster.png">
|
||||
<source src="../img/studio_threads.mp4" type="video/mp4">
|
||||
</video>
|
||||
1. View all threads in the right-hand pane of the page.
|
||||
2. Click the plus button to create a new thread.
|
||||
|
||||
## Edit Thread State
|
||||
|
||||
The LangGraph Studio UI contains features for editing thread state. Explore these features in the right-hand pane. Select the `Edit` icon, modify the desired state, and then select `Fork` to invoke the assistant with the updated state.
|
||||
### Graph mode
|
||||
|
||||
The following video shows how to edit a thread in the studio:
|
||||
To edit the state of the thread, select "edit node state" next to the desired node. This enables you to edit the node's output and create a new fork of the thread history. For more information about time travel, [see here](../../concepts/time-travel.md).
|
||||
|
||||
<video controls allowfullscreen="true" poster="../img/studio_forks_poster.png">
|
||||
<source src="../img/studio_forks.mp4" type="video/mp4">
|
||||
</video>
|
||||
### Chat mode
|
||||
|
||||
To edit a human message in the thread, click the edit button below the human message. Edit the message as desired and submit. This will create a new fork of the conversation history. To re-generate an AI message, click the retry icon below the AI message.
|
||||
|
||||
@@ -20,7 +20,7 @@ LangGraph Studio is a specialized agent IDE that enables visualization, interact
|
||||
The key features of LangGraph Studio are:
|
||||
|
||||
- Visualize your graph architecture
|
||||
- Run and interact with your graph in a GUI
|
||||
- Run and interact with your agent in a GUI
|
||||
- Create and manage [assistants](assistants.md)
|
||||
- View and manage [threads](../cloud/concepts/threads.md)
|
||||
- View and manage [long term memory](memory.md)
|
||||
@@ -29,67 +29,11 @@ The key features of LangGraph Studio are:
|
||||
|
||||
LangGraph Studio works for graphs that are deployed on [LangGraph Platform](../cloud/quick_start.md) or for graphs that are running locally via the [LangGraph Server](../tutorials/langgraph-platform/local-server.md).
|
||||
|
||||
LangGraph Studio supports two modes:
|
||||
|
||||
1. Graph
|
||||
2. Chat
|
||||
|
||||
## LangGraph Studio FAQs
|
||||
Graph mode exposes the full feature-set of Studio and is useful when you would like as many details about the execution of your agent, including the nodes traversed, intermediate states, and LangSmith integrations (such as adding to datasets an playground).
|
||||
|
||||
### Why is my project failing to start?
|
||||
|
||||
A project may fail to start if the configuration file is defined incorrectly, or if required environment variables are missing. See [here](../cloud/reference/cli.md#configuration-file) for how your configuration file should be defined.
|
||||
|
||||
### How does interrupt work?
|
||||
|
||||
When you select the `Interrupts` dropdown and select a node to interrupt the graph will pause execution before and after (unless the node goes straight to `END`) that node has run. This means that you will be able to both edit the state before the node is ran and the state after the node has ran. This is intended to allow developers more fine-grained control over the behavior of a node and make it easier to observe how the node is behaving. You will not be able to edit the state after the node has ran if the node is the final node in the graph.
|
||||
|
||||
For more information on interrupts and human in the loop, see [here](./human_in_the_loop.md).
|
||||
|
||||
### Why are extra edges showing up in my graph?
|
||||
|
||||
If you don't define your conditional edges carefully, you might notice extra edges appearing in your graph. This is because without proper definition, LangGraph Studio assumes the conditional edge could access all other nodes. In order for this to not be the case, you need to be explicit about how you define the nodes the conditional edge routes to. There are two ways you can do this:
|
||||
|
||||
#### Solution 1: Include a path map
|
||||
|
||||
The first way to solve this is to add path maps to your conditional edges. A path map is just a dictionary or array that maps the possible outputs of your router function with the names of the nodes that each output corresponds to. The path map is passed as the third argument to the `add_conditional_edges` function like so:
|
||||
|
||||
=== "Python"
|
||||
|
||||
```python
|
||||
graph.add_conditional_edges("node_a", routing_function, {True: "node_b", False: "node_c"})
|
||||
```
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
```ts
|
||||
graph.addConditionalEdges("node_a", routingFunction, { true: "node_b", false: "node_c" });
|
||||
```
|
||||
|
||||
In this case, the routing function returns either True or False, which map to `node_b` and `node_c` respectively.
|
||||
|
||||
#### Solution 2: Update the typing of the router (Python only)
|
||||
|
||||
Instead of passing a path map, you can also be explicit about the typing of your routing function by specifying the nodes it can map to using the `Literal` python definition. Here is an example of how to define a routing function in that way:
|
||||
|
||||
```python
|
||||
def routing_function(state: GraphState) -> Literal["node_b","node_c"]:
|
||||
if state['some_condition'] == True:
|
||||
return "node_b"
|
||||
else:
|
||||
return "node_c"
|
||||
```
|
||||
|
||||
|
||||
### How does automatic rebuilding work?
|
||||
|
||||
One of the key features of LangGraph Studio is that it automatically rebuilds your image when you change the source code. This allows for a super fast development and testing cycle which makes it easy to iterate on your graph. There are two different ways that LangGraph rebuilds your image: either by editing the image or completely rebuilding it.
|
||||
|
||||
#### Rebuilds from source code changes
|
||||
|
||||
If you modified the source code only (no configuration or dependency changes!) then the image does not require a full rebuild, and LangGraph Studio will only update the relevant parts. The UI status in the bottom left will switch from `Online` to `Stopping` temporarily while the image gets edited. The logs will be shown as this process is happening, and after the image has been edited the status will change back to `Online` and you will be able to run your graph with the modified code!
|
||||
|
||||
#### Rebuilds from configuration or dependency changes
|
||||
|
||||
If you edit your graph configuration file (`langgraph.json`) or the dependencies (either `pyproject.toml` or `requirements.txt`) then the entire image will be rebuilt. This will cause the UI to switch away from the graph view and start showing the logs of the new image building process. This can take a minute or two, and once it is done your updated image will be ready to use!
|
||||
|
||||
### Why is my graph taking so long to startup?
|
||||
|
||||
The LangGraph Studio interacts with a local LangGraph API server. To stay aligned with ongoing updates, the LangGraph API requires regular rebuilding. As a result, you may occasionally experience slight delays when starting up your project.
|
||||
Chat mode is a simpler UI for iterating on and testing chat-specific agents. It is useful for business users and those who want to test overall agent behavior.
|
||||
@@ -188,6 +188,7 @@ nav:
|
||||
- cloud/how-tos/datasets_studio.md
|
||||
- cloud/how-tos/iterate_graph_studio.md
|
||||
- cloud/how-tos/clone_traces_studio.md
|
||||
- cloud/how-tos/studio/faqs.md
|
||||
- LangGraph SDK: concepts/sdk.md
|
||||
- Data management:
|
||||
- cloud/deployment/semantic_search.md
|
||||
|
||||
Reference in New Issue
Block a user