js sdk walkthrough

docs/_scripts/copy_notebooks.py

@@ -9,7 +9,7 @@
 how_tos_dir = docs_dir / "how-tos"
 tutorials_dir = docs_dir / "tutorials"
 cloud_how_tos_dir = docs_dir / "cloud/how-tos"
-cloud_sdk_dir = docs_dir / "cloud"
+cloud_sdk_dir = docs_dir / "cloud/tutorials"
 
 _MANUAL = {
     "how-tos": [

docs/docs/cloud/api_concepts.md → docs/docs/cloud/conceptual_guides/api_concepts.md

@@ -2,23 +2,23 @@
 This page discusses high-level concepts of the LangGraph Cloud.
 
 ## Assistant
-An assistant is a configured instance of a [`CompiledGraph`](../reference/graphs/#compiledgraph). It abstracts the cognitive architecture of the graph and contains instance specific configuration and metadata. Multiple assistants can reference the same graph but can contain different configuration and metadata, which may differentiate the behavior of the assistants.
+An assistant is a configured instance of a [`CompiledGraph`](../../reference/graphs.md#compiledgraph). It abstracts the cognitive architecture of the graph and contains instance specific configuration and metadata. Multiple assistants can reference the same graph but can contain different configuration and metadata, which may differentiate the behavior of the assistants.
 
 An assistant (i.e. the graph) is invoked as part of a [run](#run).
 
 ## Thread
-A thread contains the accumulated state of a group of [runs](#run). If a run is executed on a thread, then the [state](../concepts/#state-management) of the underlying graph of the [assistant](#assistant) will be persisted to the thread. A thread's current and historical state can be retrieved.
+A thread contains the accumulated state of a group of [runs](#run). If a run is executed on a thread, then the [state](../../concepts/index.md#state-management) of the underlying graph of the [assistant](#assistant) will be persisted to the thread. A thread's current and historical state can be retrieved.
 
 To persist state, a thread must be created prior to executing a run.
 
 ## Run
 A run is an invocation of an [assistant](#assistant). Each run may have its own input, configuration, and metadata, which may affect execution and output of the underlying graph. A run can optionally be executed on a [thread](#thread).
 
 ## Streaming
-Streaming is critical in making applications based on LLMs feel responsive to end-users. There are three different ways to stream with graphs: by [values](../how_tos/cloud_examples/stream_values/), by [messages](../how_tos/cloud_examples/stream_messages/), and by [updates](../how_tos/cloud_examples/stream_updates/).
+Streaming is critical in making applications based on LLMs feel responsive to end-users. There are three different ways to stream with graphs: by [values](../how-tos/cloud_examples/stream_values.ipynb), by [messages](../how-tos/cloud_examples/stream_messages.ipynb), and by [updates](../how-tos/cloud_examples/stream_updates.ipynb).
 
 ## Human-in-the-Loop
-There are many occasions where the graph cannot run completely autonomously. For instance, the user might need to input some additional arguments to a function call, or select the next edge for the graph to continue on. In these instances, we need to insert some human in the loop interaction, which you can learn about in [this how-to](../how_tos/cloud_examples/human-in-the-loop_cloud).
+There are many occasions where the graph cannot run completely autonomously. For instance, the user might need to input some additional arguments to a function call, or select the next edge for the graph to continue on. In these instances, we need to insert some human in the loop interaction, which you can learn about in [this how-to](../how-tos/cloud_examples/human-in-the-loop_cloud.ipynb).
 
 ## Multi-Tasking
-Many times users might interact with your graph in unintended ways. For instance, a user interacting with a graph that has chat output could send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), Langgraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how_tos/cloud_examples/interrupt_concurrent/).
+Many times users might interact with your graph in unintended ways. For instance, a user interacting with a graph that has chat output could send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), Langgraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how-tos/cloud_examples/interrupt_concurrent.ipynb).

docs/docs/cloud/reference/sdk/python_sdk_ref.md

@@ -1,2 +1,4 @@
 # Python SDK Reference
-Coming soon
+
+::: langgraph_sdk.client
+handler: python

docs/docs/cloud/deployment/self_hosted.md → docs/docs/cloud/tutorials/deployment/self_hosted.md

@@ -6,4 +6,4 @@ First, make sure that Docker is up and running. Test that your server works by r
 langgraph up -c langgraph.json
 ```
 
-This will bring up a local server with your graph! Access the auto-generated server for your playground to confirm everything works as planned at [http://localhost:8124](http://localhost:8124) .
+This will bring up a local server with your graph! Access the auto-generated server for your playground to confirm everything works as planned at [http://localhost:8123](http://localhost:8123) .

docs/docs/cloud/quick_start.md → docs/docs/cloud/tutorials/quick_start.md

@@ -46,7 +46,7 @@ Alternatively, clone or fork the [`langgraph/example`](https://github.com/langch
     }
     ```
 
-    Learn more about the LangGraph CLI configuration file [here](./reference/cli.md#configuration-file).
+    Learn more about the LangGraph CLI configuration file [here](../reference/cli.md#configuration-file).
 
 5. The `.env` file should contain the environment variables:
 
@@ -57,7 +57,7 @@ Alternatively, clone or fork the [`langgraph/example`](https://github.com/langch
         When testing locally, set `LANGGRAPH_AUTH_TYPE` to `noop` to disable authentication.
 
 ## Run Locally
-1. Install the [LangGraph CLI](./reference/cli.md#installation).
+1. Install the [LangGraph CLI](../reference/cli.md#installation).
 
 2. Run the following command to start the API server in Docker:
 
@@ -67,4 +67,4 @@ Alternatively, clone or fork the [`langgraph/example`](https://github.com/langch
 
 ## Deploy to Cloud
 
-Follow [these instructions](./deployment/managed.md#deploy-from-github-with-hosted-langgraph) to deploy to LangGraph Cloud.
+Follow [these instructions](./deployment/managed.md) to deploy to LangGraph Cloud.

docs/mkdocs.yml

@@ -168,13 +168,13 @@ nav:
   - 'Cloud (alpha)':
       - 'cloud/index.md'
       - Tutorials:
-          - Quick Start: 'cloud/quick_start.md'
+          - Quick Start: 'cloud/tutorials/quick_start.md'
           - SDK:
-              - Python: 'cloud/sdk/python_sdk.ipynb'
-              - JS/TS: 'cloud/sdk/js_sdk.ipynb'
+              - Python: 'cloud/tutorials/sdk/python_sdk.ipynb'
+              - JS/TS: 'cloud/tutorials/sdk/js_sdk.ipynb'
           - Deployment:
-              - Self-Hosted: 'cloud/deployment/self_hosted.md'
-              - Managed: 'cloud/deployment/managed.md'
+              - Self-Hosted: 'cloud/tutorials/deployment/self_hosted.md'
+              - Managed: 'cloud/tutorials/deployment/managed.md'
       - How-to Guides:
           - Streaming:
               - Stream Messages: 'cloud/how-tos/cloud_examples/stream_messages.ipynb'
@@ -190,7 +190,7 @@ nav:
           - Human in the loop: 'cloud/how-tos/cloud_examples/human-in-the-loop_cloud.ipynb'
           - Create Agents with Configuration: 'cloud/how-tos/cloud_examples/configuration_cloud.ipynb'
       - Conceptual Guides:
-          - API Concepts: 'cloud/api_concepts.md'
+          - API Concepts: 'cloud/conceptual_guides/api_concepts.md'
       - Reference:
           - API: 'cloud/reference/api_ref.md'
           - SDK: