David Duong and GitHub
fb5a1c4028
feat(cli): add packageManager and devEngines detection ( #4024 )
cli==0.1.80
2025-03-25 23:43:36 +01:00
Tat Dat Duong
39d85466f8
Bump to 0.1.80
2025-03-25 23:36:33 +01:00
Tat Dat Duong
3c797529bb
Avoid frozen lockfile
2025-03-25 23:32:40 +01:00
Tat Dat Duong
0d185d43ed
feat(cli): add packageManager and devEngines detection
2025-03-25 23:26:04 +01:00
Eugene Yurtsev and GitHub
70b8391a89
ci: use fast benchmark ( #4017 )
sdk==0.1.59
2025-03-25 17:59:18 -04:00
Eugene Yurtsev and GitHub
1a37f2d5a2
sdk-py: release 0.1.59 ( #4018 )
2025-03-25 17:58:51 -04:00
Really Him and GitHub
949af8abe5
docs(pregel): One-line markdown formatting quick-fix ( #4023 )
...
## Description
I noticed a very minor issue in the formatting of the Concepts > Pregel
doc:
(https://langchain-ai.github.io/langgraph/concepts/pregel/#high-level-api )
(https://github.com/langchain-ai/langgraph/blob/main/docs/docs/concepts/pregel.md )
You can see in the image below that there is a python codeblock, then a
pycon block, and inside that block there is an extra
triple-backtick/code fence, and then text at the bottom, which it
appears like it is supposed to be a separate python block, like the one
above it. I.e., clearly:
```
```python
print(graph.channels)
```
is intended to be:
```python
print(graph.channels)
```
I'm pretty sure this is due to an extra whitespace character before the preceding closing code fence, which is throwing off the formatting.

My VS-Code/extensions can't really render the Markdown the way it appears on the Website, I think because of the tabs (Graph API vs. Functional API), but I noticed that if I remove the extra whitespace, the highlighting on the python codeblock is corrected:
BEFORE:
<img width="605" alt="Screenshot 2025-03-25 at 5 02 41 PM" src="https://github.com/user-attachments/assets/8474f103-c5ab-4c02-b22f-3d54b3363331 " />
AFTER:
<img width="277" alt="Screenshot 2025-03-25 at 5 02 50 PM" src="https://github.com/user-attachments/assets/a311b87b-859c-4aba-a4d8-6b063a155d90 " />
## Fix
* Remove one whitespace character that was throwing off markdown rendering
2025-03-25 17:58:37 -04:00
Eugene Yurtsev and GitHub
094255c3fe
docs: remove langmanus temporarily ( #4022 )
...
there's no pypi package
2025-03-25 16:46:07 -04:00
Nuno Campos and GitHub
b6055ff3fe
Warn when get_graph tries to draw edge that doesn't exist ( #4021 )
2025-03-25 12:57:31 -07:00
Nuno Campos
e082ba4f85
Warn when get_graph tries to draw edge that doesn't exist
2025-03-25 12:50:47 -07:00
Vadym Barda and GitHub
f36b7f61fb
prebuilt: release 0.1.6 ( #4020 )
prebuilt==0.1.6
2025-03-25 15:49:02 -04:00
Vadym Barda and GitHub
4095f0a927
prebuilt: only combine Command.PARENT for Send gotos in ToolNode ( #4019 )
2025-03-25 15:47:46 -04:00
8af09714ff
docs: remove unused imports from guide ( #4014 )
...
Not included in index page, and currently re-directs:
https://github.com/langchain-ai/langgraph/blob/01fed0fae27a8d71490a7f94a74942af5626da97/docs/_scripts/notebook_hooks.py#L24
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com >
2025-03-25 15:35:54 -04:00
Eugene Yurtsev and GitHub
5d7e818882
sdk: Add headers to sync client ( #4012 )
...
Add ability to pass run time headers to the sync client.
2025-03-25 14:58:33 -04:00
Eugene Yurtsev and GitHub
37429ff73b
docs: remove old code from workflow ( #4016 )
2025-03-25 14:20:04 -04:00
Vadym Barda and GitHub
af7515c37a
prebuilt: release 0.1.5 ( #4015 )
prebuilt==0.1.5
2025-03-25 13:52:35 -04:00
Vadym Barda and GitHub
b97cda4290
prebuilt: add support for multiple Command(graph=Command.PARENT) returned by tools ( #4003 )
2025-03-25 13:51:05 -04:00
Ykoh and GitHub
01fed0fae2
Docs fix example docs ( #3971 )
2025-03-25 11:02:20 -04:00
Nuno Campos
2ac22f8246
0.3.20
0.3.20
2025-03-24 18:09:56 -07:00
William FH and GitHub
ae2e8d7e5e
Use 128bit hash for task ids ( #4005 )
2025-03-24 18:09:25 -07:00
Nuno Campos
5526486a0b
Use 128bit hash for task ids
2025-03-24 18:04:26 -07:00
William FH and GitHub
0f8fc4fe68
Handle Sends ( #4004 )
...
In the json-mode deserializer
checkpoint==2.0.23
2025-03-24 17:17:52 -07:00
William Fu-Hinthorn
10859da99a
Handle sneds
2025-03-24 17:12:50 -07:00
Nuno Campos and GitHub
b285a118a7
Log and continue for subgraph schema issues ( #3997 )
2025-03-24 16:31:42 -07:00
William FH and GitHub
6853d045b6
Add HTTP deserialization option ( #4002 )
checkpoint==2.0.22
2025-03-24 16:28:53 -07:00
William Fu-Hinthorn
d8cc9c9680
merge with ormsgpack
2025-03-24 16:21:59 -07:00
William Fu-Hinthorn
723d6f8a84
Add json mode msgpack unpacker
2025-03-24 16:15:48 -07:00
Nuno Campos and GitHub
696a922241
Switch serialization lib to ormsgpack ( #3953 )
...
- faster for large states
- supports tuples as dict keys
2025-03-24 16:08:57 -07:00
Eugene Yurtsev and GitHub
c598fee7d6
sdk-py: Propagate headers in the async client ( #4001 )
...
Propagate headers in the async client
2025-03-24 16:30:40 -04:00
William FH and GitHub
6da6c4443a
Merge branch 'main' into wfh/log_and_continue
2025-03-24 12:25:47 -07:00
Eugene Yurtsev and GitHub
addb491cfd
sdk: allow specifying run time headers in http client ( #4000 )
...
This PR only allows this in the HTTP client.
I can follow up with a PR to allow throughout the entire API.
The use case is to allow instantiating the client once (w/ a single connection pool), but allowing changing api keys and any other headers at run time
2025-03-24 14:47:35 -04:00
Eugene Yurtsev and GitHub
c84f35eff5
add langmanus to prebuilt ( #3999 )
2025-03-24 13:26:53 -04:00
Eugene Yurtsev and GitHub
f178e4205f
docs: add xxhash explicitly to docs pyproject.toml ( #3998 )
...
It's not getting picked up from the dev requirements for some reason.
2025-03-24 12:58:33 -04:00
Nuno Campos
3f4d1c66c2
0.3.19
0.3.19
2025-03-24 09:45:54 -07:00
Nuno Campos
2ee5b8e9d1
Bump
2025-03-24 09:03:23 -07:00
Nuno Campos
aadbcb443a
Bump
2025-03-24 09:03:23 -07:00
Nuno Campos
a88794b74e
Update ormsgpack
2025-03-24 09:03:23 -07:00
Nuno Campos
556733c77c
Bump
2025-03-24 09:01:55 -07:00
Nuno Campos
3d16acf3f5
Switch serialization lib to ormsgpack
...
- faster for large states
- supports tuples as dict keys
2025-03-24 09:01:55 -07:00
Nuno Campos and GitHub
87cbc4942d
Switch task ids to use xxhash3 ( #3954 )
...
- much faster / less memory allocations
- backwards compat by applying only to checkpoint versions 2 or above
2025-03-24 08:42:50 -07:00
Nuno Campos and GitHub
6d63300c9a
benchmarks: Add 1st event latency ( #3909 )
2025-03-24 07:58:47 -07:00
Nuno Campos
a5dd181138
Update
2025-03-24 07:57:02 -07:00
William Fu-Hinthorn
ad63b730b3
Log and continue for subgraph schema issues
2025-03-24 07:50:25 -07:00
Nuno Campos
528d3946c6
Lock
2025-03-24 07:49:24 -07:00
Nuno Campos
037d9d1402
Lock
2025-03-24 07:49:24 -07:00
Nuno Campos
6aee213f3c
Switch task ids to use xxhash3
...
- much faster / less memory allocations
- backwards compat by applying only to checkpoint versions 2 or above
2025-03-24 07:49:24 -07:00
Lance Martin and GitHub
f690f4244e
Remove failing links ( #3994 )
...
Anthropic links for blog post and docs are failing CI --
https://github.com/langchain-ai/langgraph/actions/runs/14024926642/job/39261981682
Remove to unblock docs build; we may add back to ignore later.
2025-03-23 19:53:11 -07:00
Lance Martin and GitHub
d6856131b6
Fix broken links in ntbks ( #3993 )
...
A number of Anthropic links recently changed
2025-03-23 17:59:14 -07:00
Lance Martin and GitHub
7d90440035
Update llms.txt for langgraph ( #3987 )
2025-03-23 15:39:09 -07:00
alxdr3k and GitHub
fed785eabd
docs: fix typo in low_level.md ( #3968 )
...
- Fix typo
2025-03-21 16:40:41 -04:00