How to kick off background runs ↗
noOriginal Documentation
Documentation Index#
Fetch the complete documentation index at: https://docs.langchain.com/llms.txt Use this file to discover all available pages before exploring further.
This guide covers how to kick off background runs for your agent. This can be useful for long running jobs.
Setup#
First let’s set up our client and thread:
from langgraph_sdk import get_client
client = get_client(url=<DEPLOYMENT_URL>)
# Using the graph deployed with the name "agent"
assistant_id = "agent"
# create thread
thread = await client.threads.create()
print(thread)
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
import { Client } from "@langchain/langgraph-sdk";
const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
// Using the graph deployed with the name "agent"
const assistantID = "agent";
// create thread
const thread = await client.threads.create();
console.log(thread);
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request POST \
--url <DEPLOYMENT_URL>/threads \
--header 'Content-Type: application/json' \
--data '{}'
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
Output:{ ’thread_id’: ‘5cb1e8a1-34b3-4a61-a34e-71a9799bd00d’, ‘created_at’: ‘2024-08-30T20:35:52.062934+00:00’, ‘updated_at’: ‘2024-08-30T20:35:52.062934+00:00’, ‘metadata’: {}, ‘status’: ‘idle’, ‘config’: {}, ‘values’: None }
## Check runs on thread
If we list the current runs on this thread, we will see that it's empty:
<span class="tab-group-start"></span>
<span class="tab-start" data-tab-title="Python"></span>
```python
runs = await client.runs.list(thread["thread_id"])
print(runs)
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
let runs = await client.runs.list(thread['thread_id']);
console.log(runs);
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
Output:[]
## Start runs on thread
Now let's kick off a run:
<span class="tab-group-start"></span>
<span class="tab-start" data-tab-title="Python"></span>
```python
input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]}
run = await client.runs.create(thread["thread_id"], assistant_id, input=input)
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
let input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]};
let run = await client.runs.create(thread["thread_id"], assistantID, { input });
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request POST \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs \
--header 'Content-Type: application/json' \
--data '{
"assistant_id": <ASSISTANT_ID>
}'
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
The first time we poll it, we can see `status=pending`:
<span class="tab-group-start"></span>
<span class="tab-start" data-tab-title="Python"></span>
```python
print(await client.runs.get(thread["thread_id"], run["run_id"]))
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
console.log(await client.runs.get(thread["thread_id"], run["run_id"]));
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
Output:{ “run_id”: “1ef6a5f8-bd86-6763-bbd6-bff042db7b1b”, “thread_id”: “7885f0cf-94ad-4040-91d7-73f7ba007c8a”, “assistant_id”: “fe096781-5601-53d2-b2f6-0d3403f7e9ca”, “created_at”: “2024-09-04T01:46:47.244887+00:00”, “updated_at”: “2024-09-04T01:46:47.244887+00:00”, “metadata”: {}, “status”: “pending”, “kwargs”: { “input”: { “messages”: [ { “role”: “user”, “content”: “what’s the weather in sf” } ] }, “config”: { “metadata”: { “created_by”: “system” }, “configurable”: { “run_id”: “1ef6a5f8-bd86-6763-bbd6-bff042db7b1b”, “user_id”: “”, “graph_id”: “agent”, “thread_id”: “7885f0cf-94ad-4040-91d7-73f7ba007c8a”, “assistant_id”: “fe096781-5601-53d2-b2f6-0d3403f7e9ca”, “checkpoint_id”: null } }, “webhook”: null, “temporary”: false, “stream_mode”: [ “values” ], “feedback_keys”: null, “interrupt_after”: null, “interrupt_before”: null }, “multitask_strategy”: “reject” }
Now we can join the run, wait for it to finish and check that status again:
<span class="tab-group-start"></span>
<span class="tab-start" data-tab-title="Python"></span>
```python
await client.runs.join(thread["thread_id"], run["run_id"])
print(await client.runs.get(thread["thread_id"], run["run_id"]))
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
await client.runs.join(thread["thread_id"], run["run_id"]);
console.log(await client.runs.get(thread["thread_id"], run["run_id"]));
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join &&
curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
Output:{ “run_id”: “1ef6a5f8-bd86-6763-bbd6-bff042db7b1b”, “thread_id”: “7885f0cf-94ad-4040-91d7-73f7ba007c8a”, “assistant_id”: “fe096781-5601-53d2-b2f6-0d3403f7e9ca”, “created_at”: “2024-09-04T01:46:47.244887+00:00”, “updated_at”: “2024-09-04T01:46:47.244887+00:00”, “metadata”: {}, “status”: “success”, “kwargs”: { “input”: { “messages”: [ { “role”: “user”, “content”: “what’s the weather in sf” } ] }, “config”: { “metadata”: { “created_by”: “system” }, “configurable”: { “run_id”: “1ef6a5f8-bd86-6763-bbd6-bff042db7b1b”, “user_id”: “”, “graph_id”: “agent”, “thread_id”: “7885f0cf-94ad-4040-91d7-73f7ba007c8a”, “assistant_id”: “fe096781-5601-53d2-b2f6-0d3403f7e9ca”, “checkpoint_id”: null } }, “webhook”: null, “temporary”: false, “stream_mode”: [ “values” ], “feedback_keys”: null, “interrupt_after”: null, “interrupt_before”: null }, “multitask_strategy”: “reject” }
Perfect! The run succeeded as we would expect. We can double check that the run worked as expected by printing out the final state:
<span class="tab-group-start"></span>
<span class="tab-start" data-tab-title="Python"></span>
```python
final_result = await client.threads.get_state(thread["thread_id"])
print(final_result)
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
let finalResult = await client.threads.getState(thread["thread_id"]);
console.log(finalResult);
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
Output:{ “values”: { “messages”: [ { “content”: “what’s the weather in sf”, “additional_kwargs”: {}, “response_metadata”: {}, “type”: “human”, “name”: null, “id”: “beba31bf-320d-4125-9c37-cadf526ac47a”, “example”: false }, { “content”: [ { “id”: “toolu_01AaNPSPzqia21v7aAKwbKYm”, “input”: {}, “name”: “tavily_search_results_json”, “type”: “tool_use”, “index”: 0, “partial_json”: “{"query": "weather in san francisco"}” } ], “additional_kwargs”: {}, “response_metadata”: { “stop_reason”: “tool_use”, “stop_sequence”: null }, “type”: “ai”, “name”: null, “id”: “run-f220faf8-1d27-4f73-ad91-6bb3f47e8639”, “example”: false, “tool_calls”: [ { “name”: “tavily_search_results_json”, “args”: { “query”: “weather in san francisco” }, “id”: “toolu_01AaNPSPzqia21v7aAKwbKYm”, “type”: “tool_call” } ], “invalid_tool_calls”: [], “usage_metadata”: { “input_tokens”: 273, “output_tokens”: 61, “total_tokens”: 334 } }, { “content”: “[{"url": "https://www.weatherapi.com/", "content": "{’location’: {’name’: ‘San Francisco’, ‘region’: ‘California’, ‘country’: ‘United States of America’, ’lat’: 37.78, ’lon’: -122.42, ’tz_id’: ‘America/Los_Angeles’, ’localtime_epoch’: 1725052131, ’localtime’: ‘2024-08-30 14:08’}, ‘current’: {’last_updated_epoch’: 1725051600, ’last_updated’: ‘2024-08-30 14:00’, ’temp_c’: 21.1, ’temp_f’: 70.0, ‘is_day’: 1, ‘condition’: {’text’: ‘Partly cloudy’, ‘icon’: ‘//cdn.weatherapi.com/weather/64x64/day/116.png’, ‘code’: 1003}, ‘wind_mph’: 11.9, ‘wind_kph’: 19.1, ‘wind_degree’: 290, ‘wind_dir’: ‘WNW’, ‘pressure_mb’: 1018.0, ‘pressure_in’: 30.07, ‘precip_mm’: 0.0, ‘precip_in’: 0.0, ‘humidity’: 59, ‘cloud’: 25, ‘feelslike_c’: 21.1, ‘feelslike_f’: 70.0, ‘windchill_c’: 18.6, ‘windchill_f’: 65.5, ‘heatindex_c’: 18.6, ‘heatindex_f’: 65.5, ‘dewpoint_c’: 12.2, ‘dewpoint_f’: 54.0, ‘vis_km’: 16.0, ‘vis_miles’: 9.0, ‘uv’: 5.0, ‘gust_mph’: 15.0, ‘gust_kph’: 24.2}}"}]”, “additional_kwargs”: {}, “response_metadata”: {}, “type”: “tool”, “name”: “tavily_search_results_json”, “id”: “686b2487-f332-4e58-9508-89b3a814cd81”, “tool_call_id”: “toolu_01AaNPSPzqia21v7aAKwbKYm”, “artifact”: { “query”: “weather in san francisco”, “follow_up_questions”: null, “answer”: null, “images”: [], “results”: [ { “title”: “Weather in San Francisco”, “url”: “https://www.weatherapi.com/”, “content”: “{’location’: {’name’: ‘San Francisco’, ‘region’: ‘California’, ‘country’: ‘United States of America’, ’lat’: 37.78, ’lon’: -122.42, ’tz_id’: ‘America/Los_Angeles’, ’localtime_epoch’: 1725052131, ’localtime’: ‘2024-08-30 14:08’}, ‘current’: {’last_updated_epoch’: 1725051600, ’last_updated’: ‘2024-08-30 14:00’, ’temp_c’: 21.1, ’temp_f’: 70.0, ‘is_day’: 1, ‘condition’: {’text’: ‘Partly cloudy’, ‘icon’: ‘//cdn.weatherapi.com/weather/64x64/day/116.png’, ‘code’: 1003}, ‘wind_mph’: 11.9, ‘wind_kph’: 19.1, ‘wind_degree’: 290, ‘wind_dir’: ‘WNW’, ‘pressure_mb’: 1018.0, ‘pressure_in’: 30.07, ‘precip_mm’: 0.0, ‘precip_in’: 0.0, ‘humidity’: 59, ‘cloud’: 25, ‘feelslike_c’: 21.1, ‘feelslike_f’: 70.0, ‘windchill_c’: 18.6, ‘windchill_f’: 65.5, ‘heatindex_c’: 18.6, ‘heatindex_f’: 65.5, ‘dewpoint_c’: 12.2, ‘dewpoint_f’: 54.0, ‘vis_km’: 16.0, ‘vis_miles’: 9.0, ‘uv’: 5.0, ‘gust_mph’: 15.0, ‘gust_kph’: 24.2}}”, “score”: 0.976148, “raw_content”: null } ], “response_time”: 3.07 }, “status”: “success” }, { “content”: [ { “text”: “\n\nThe search results provide the current weather conditions in San Francisco. According to the data, as of 2:00 PM on August 30, 2024, the temperature in San Francisco is 70\u00b0F (21.1\u00b0C) with partly cloudy skies. The wind is blowing from the west-northwest at around 12 mph (19 km/h). The humidity is 59% and visibility is 9 miles (16 km). Overall, it looks like a nice late summer day in San Francisco with comfortable temperatures and partly sunny conditions.”, “type”: “text”, “index”: 0 } ], “additional_kwargs”: {}, “response_metadata”: { “stop_reason”: “end_turn”, “stop_sequence”: null }, “type”: “ai”, “name”: null, “id”: “run-8fecc61d-3d9f-4e16-8e8a-92f702be498a”, “example”: false, “tool_calls”: [], “invalid_tool_calls”: [], “usage_metadata”: { “input_tokens”: 837, “output_tokens”: 124, “total_tokens”: 961 } } ] }, “next”: [], “tasks”: [], “metadata”: { “step”: 3, “run_id”: “1ef67140-eb23-684b-8253-91d4c90bb05e”, “source”: “loop”, “writes”: { “agent”: { “messages”: [ { “id”: “run-8fecc61d-3d9f-4e16-8e8a-92f702be498a”, “name”: null, “type”: “ai”, “content”: [ { “text”: “\n\nThe search results provide the current weather conditions in San Francisco. According to the data, as of 2:00 PM on August 30, 2024, the temperature in San Francisco is 70\u00b0F (21.1\u00b0C) with partly cloudy skies. The wind is blowing from the west-northwest at around 12 mph (19 km/h). The humidity is 59% and visibility is 9 miles (16 km). Overall, it looks like a nice late summer day in San Francisco with comfortable temperatures and partly sunny conditions.”, “type”: “text”, “index”: 0 } ], “example”: false, “tool_calls”: [], “usage_metadata”: { “input_tokens”: 837, “total_tokens”: 961, “output_tokens”: 124 }, “additional_kwargs”: {}, “response_metadata”: { “stop_reason”: “end_turn”, “stop_sequence”: null }, “invalid_tool_calls”: [] } ] } }, “user_id”: “”, “graph_id”: “agent”, “thread_id”: “5cb1e8a1-34b3-4a61-a34e-71a9799bd00d”, “created_by”: “system”, “assistant_id”: “fe096781-5601-53d2-b2f6-0d3403f7e9ca” }, “created_at”: “2024-08-30T21:09:00.079909+00:00”, “checkpoint_id”: “1ef67141-3ca2-6fae-8003-fe96832e57d6”, “parent_checkpoint_id”: “1ef67141-2129-6b37-8002-61fc3bf69cb5” }
We can also just print the content of the last AIMessage:
<span class="tab-group-start"></span>
<span class="tab-start" data-tab-title="Python"></span>
```python
print(final_result['values']['messages'][-1]['content'][0]['text'])
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="Javascript"></span>
```js
console.log(finalResult['values']['messages'][finalResult['values']['messages'].length-1]['content'][0]['text']);
```
<span class="tab-end"></span>
<span class="tab-start" data-tab-title="CURL"></span>
```bash
curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | jq -r '.values.messages[-1].content.[0].text'
```
<span class="tab-end"></span>
<span class="tab-group-end"></span>
Output:The search results provide the current weather conditions in San Francisco. According to the data, as of 2:00 PM on August 30, 2024, the temperature in San Francisco is 70°F (21.1°C) with partly cloudy skies. The wind is blowing from the west-northwest at around 12 mph (19 km/h). The humidity is 59% and visibility is 9 miles (16 km). Overall, it looks like a nice late summer day in San Francisco with comfortable temperatures and partly sunny conditions.
***
<span class="callout-start" data-callout-type="note"></span>
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/background-run.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
<span class="callout-end"></span>
<span class="callout-start" data-callout-type="note"></span>
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
<span class="callout-end"></span>