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

Create notebooks for creating cron jobs and stateless runs. (#797)

Browse Source
This commit is contained in:
Andrew Nguonly
2024-06-24 17:03:38 -07:00
committed by GitHub
parent 265f5012c1
commit 317664be63
4 changed files with 274 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/cloud/concepts/index.md
+3 -4
View File
@@ -26,7 +26,7 @@ It's often useful to run graphs on some schedule. LangGraph Cloud supports cron
- Create a new thread with the specified assistant
- Send the specified input to that thread
Note that this sends the same input to the thread every time.
Note that this sends the same input to the thread every time. See the [How-to Guide](../how-tos/cloud_examples/cron_jobs/) for creating cron jobs.
The LangGraph Cloud API provides several endpoints for creating and managing cron jobs. See the [API reference](../reference/api_ref.md) for more details.
@@ -57,8 +57,7 @@ Many times users might interact with your graph in unintended ways. For instance
- `interrupt`: This option interrupts the current execution but saves all the work done up until that point. It then inserts the user input and continues from there. If you enable this option, your graph should be able to handle weird edge cases that may arise.
- `rollback`: This option rolls back all work done up until that point. It then sends the user input in, basically as if it just followed the original run input.
### Stateless runs
### Stateless Runs
All runs use the built-in checkpointer to store checkpoints for runs. However, it can often be useful to just kick off a run without worrying about explicitly creating a thread and without wanting to keep those checkpointers around. Stateless runs allow you to do this by exposing an endpoint that:
@@ -73,4 +72,4 @@ The only difference is in stateless background runs, if the task worker dies hal
- whereas a stateful background run would retry from the last successful checkpoint
- a stateless background run would retry from the beginning
See the [How-to Guide](../how-tos/cloud_examples/stateless_runs/) for creating stateless runs.
docs/mkdocs.yml
+2
View File
@@ -196,6 +196,8 @@ nav:
- Replay and Branch from Prior States: 'cloud/how-tos/cloud_examples/human_in_the_loop_time_travel.ipynb'
- Create Agents with Configuration: 'cloud/how-tos/cloud_examples/configuration_cloud.ipynb'
- Convert LangGraph calls to LangGraph Cloud calls: 'cloud/how-tos/cloud_examples/langgraph_to_langgraph_cloud.ipynb'
- Create Cron Jobs: 'cloud/how-tos/cloud_examples/cron_jobs.ipynb'
- Create Stateless Runs: 'cloud/how-tos/cloud_examples/stateless_runs.ipynb'
- SDK:
- Python: 'cloud/sdk/python_sdk.ipynb'
- JS/TS: 'cloud/sdk/js_sdk.ipynb'
examples/cloud_examples/cron_jobs.ipynb
+122
View File
@@ -0,0 +1,122 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Cron Jobs\n",
"\n",
"Sometimes you don't want to run your graph based on user interaction, but rather you would like to schedule your graph to run on a schedule - for example if you wish for your graph to compose and send out a weekly email of to-dos for your team. LangGraph Cloud allows you to do this without having to write your own script by using the `Crons` client. To schedule a graph job, you need to pass a [cron expression](https://crontab.cronhub.io/) to inform the client when you want to run the graph. `Cron` jobs are run in the background and do not interfere with normal invocations of the graph.\n",
"\n",
"## Setup\n",
"\n",
"First, let's setup our SDK client, assistant, and thread:"
]
},
{
"cell_type": "code",
"execution_count": 110,
"metadata": {},
"outputs": [],
"source": [
"from langgraph_sdk import get_client\n",
"client = get_client()\n",
"assistants = await client.assistants.search()\n",
"assistants = [a for a in assistants if not a['config']]\n",
"assistant = assistants[0]\n",
"thread = await client.threads.create()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Cron job on a thread \n",
"\n",
"To create a cron job associated with a specific thread, you can write:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# This schedules a job to run at 15:27 (3:27PM) every day\n",
"cron_1 = await client.crons.create_for_thread(thread['thread_id'],assistant['assistant_id'],schedule=\"27 15 * * *\",input={'messages':[{\"role\":\"user\",\"content\":\"What time is it?\"}]})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note that it is **very** important to delete `Cron` jobs that are no longer useful. Otherwise you could rack up unwanted API charges to the LLM! You can delete a `Cron` job using the following code:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"await client.crons.delete(cron_1['cron_id'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Cron job threadless\n",
"\n",
"You can also create threadless cron jobs by using the following code:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# This schedules a job to run at 15:27 (3:27PM) every day\n",
"cron_2 = await client.crons.create(assistant['assistant_id'],schedule=\"27 15 * * *\",input={'messages':[{\"role\":\"user\",\"content\":\"What time is it?\"}]})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Again, remember to delete your job once you are done with it!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"await client.crons.delete(cron_2['cron_id'])"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
examples/cloud_examples/stateless_runs.ipynb
+147
View File
@@ -0,0 +1,147 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Stateless Runs\n",
"\n",
"Most of the time, you provide a `thread_id` to your client when you run your graph in order to keep track of prior runs through the persistent state implemented in LangGraph Cloud. However, if you have your own database to save runs and don't need to use the built in persistent state, you can create stateless runs.\n",
"\n",
"## Setup\n",
"\n",
"First, let's setup our client"
]
},
{
"cell_type": "code",
"execution_count": 106,
"metadata": {},
"outputs": [],
"source": [
"from langgraph_sdk import get_client\n",
"client = get_client()\n",
"assistants = await client.assistants.search()\n",
"assistants = [a for a in assistants if not a['config']]\n",
"assistant = assistants[0]\n",
"thread = await client.threads.create()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Stateless streaming\n",
"\n",
"We can stream the results of a stateless run in an almost identical fashion to how we stream from a run with the state attribute, but instead of passing a value to the `thread_id` parameter, we pass `None`:"
]
},
{
"cell_type": "code",
"execution_count": 107,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'agent': {'messages': [{'content': \"Hello Bagatur! It's nice to meet you. Thank you for introducing yourself and sharing your age. Is there anything specific you'd like to know or discuss? I'm here to help with any questions or topics you're interested in.\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-489ec573-1645-4ce2-a3b8-91b391d50a71', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
]
}
],
"source": [
"input = {\"messages\":[{\"role\": \"user\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}]}\n",
"\n",
"\n",
"async for chunk in client.runs.stream(\n",
" # Don't pass in a thread_id and the stream will be stateless\n",
" None,\n",
" assistant[\"assistant_id\"], # graph_id\n",
" input=input,\n",
" stream_mode=\"updates\",\n",
"):\n",
" if chunk.data and \"run_id\" not in chunk.data:\n",
" print(chunk.data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Waiting for stateless results\n",
"\n",
"In addition to streaming, you can also wait for a stateless result by using the `.wait` function like follows:"
]
},
{
"cell_type": "code",
"execution_count": 108,
"metadata": {},
"outputs": [],
"source": [
"stateless_run_result = await client.runs.wait(\n",
" None,\n",
" assistant[\"assistant_id\"], # graph_id\n",
" input=input,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 109,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'messages': [{'content': 'Hello! My name is Bagatur and I am 26 years old.',\n",
" 'additional_kwargs': {},\n",
" 'response_metadata': {},\n",
" 'type': 'human',\n",
" 'name': None,\n",
" 'id': '5e088543-62c2-43de-9d95-6086ad7f8b48',\n",
" 'example': False},\n",
" {'content': \"Hello Bagatur! It's nice to meet you. Thank you for introducing yourself and sharing your age. Is there anything specific you'd like to know or discuss? I'm here to help with any questions or topics you'd like to explore.\",\n",
" 'additional_kwargs': {},\n",
" 'response_metadata': {},\n",
" 'type': 'ai',\n",
" 'name': None,\n",
" 'id': 'run-d6361e8d-4d4c-45bd-ba47-39520257f773',\n",
" 'example': False,\n",
" 'tool_calls': [],\n",
" 'invalid_tool_calls': [],\n",
" 'usage_metadata': None}]}"
]
},
"execution_count": 109,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stateless_run_result"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}