Vadym Barda and GitHub
55f922cf2f
langgraph: release 0.3.23 ( #4141 )
2025-04-02 09:50:18 -04:00
Nuno Campos
6efeefe424
Maintain checkpoint LATEST_VERSION constant in langgraph lib
...
- This should be controlled by the langgraph version, not the version of langgraph-checkpoint installed
2025-04-01 21:46:38 -07:00
Vadym Barda and GitHub
e3d697620b
langgraph: support removing all messages with RemoveMessage ( #4117 )
2025-04-01 17:51:54 -04:00
Nuno Campos
30883729f0
0.3.22
2025-04-01 07:54:24 -07:00
Nuno Campos
e85b7e6cd9
Lint
2025-03-31 18:46:51 -07:00
Nuno Campos
94fa46f9fa
Avoid creating checkpoint unless we're saving it
...
- When checkpointing is disabled don't call create_checkpoint in PregelLoop
- In local_read apply writes directly to copies of updated channels
- Add BaseChannel.copy() method to create channel copies with less overhead
2025-03-31 18:37:13 -07:00
Nuno Campos
fd64ada9de
Avoid raise-catch strategy in BaseChannel.checkpoint()
...
- This mirrors the work done earlier on BaseChannel.get()
- Comparing to a sentinel value is significantly faster than raising and catching an exception
2025-03-31 17:48:19 -07:00
Nuno Campos
5e9e7b79fe
Lint
2025-03-31 17:36:00 -07:00
Nuno Campos
c49a077789
Lint
2025-03-31 17:24:26 -07:00
Nuno Campos
881b07cf7f
Lint
2025-03-31 16:36:16 -07:00
Nuno Campos
0425d4e65d
Update
2025-03-31 16:29:07 -07:00
Nuno Campos
118016a21c
Add fast path to serialize None values
2025-03-31 16:15:56 -07:00
Nuno Campos
067b99c789
Lazily create atomic counters in pregel scratchpad
...
- many times these aren't actually used, so makes sense to delay creation until needed
2025-03-31 15:19:53 -07:00
Nuno Campos
e9e9a96a0d
Reduce perf impact of pregel scratchpad creation
...
- make scratchpad class frozen now that its members are never reassigned
- replace next(gen expr) with for-loop to avoid allocating generator objects
2025-03-31 14:50:10 -07:00
Nuno Campos
d30da72f6e
Reduce the number of channels created for each node by 50%
...
- Used to be 2 channels per node, it is now one per node, which is the minimum
- Now both hard edges, conditional edges, entrypoint and conditional entrypoint all use the same channel to trigger a node
2025-03-27 17:47:11 -07:00
Nuno Campos and GitHub
522caa643f
In Python 3.12 or above, use asyncio eager task factory ( #4055 )
...
- This is a performance improvement when calling async functions that do
not use await, as they are run immediately and never scheduled in the
loop
2025-03-27 13:36:04 -07:00
Nuno Campos
ef71656f05
Fix
2025-03-27 13:14:39 -07:00
Nuno Campos and GitHub
f5fe7e5195
Remove internal frames from stack traces ( #4054 )
...
- For exceptions raised in user code (ie. nodes or edges) remove
internal frames from the stack trace
2025-03-27 12:41:54 -07:00
Nuno Campos
1c5a354a7d
In Python 3.12 or above, use asyncio eager task factory
...
- This is a performance improvement when calling async functions that do not use await, as they are run immediately and never scheduled in the loop
2025-03-27 11:00:37 -07:00
Nuno Campos
bfd271e00e
Remove internal frames from stack traces
...
- For exceptions raised in user code (ie. nodes or edges) remove internal frames from the stack trace
2025-03-27 10:58:13 -07:00
Vadym Barda and GitHub
9647b1e55f
langgraph: use correct type for node destination annotations ( #4053 )
...
Fixes https://github.com/langchain-ai/langgraph/issues/4051
2025-03-27 16:57:39 +00:00
Vadym Barda and GitHub
2c29edadec
langgraph: release 0.3.21 ( #4050 )
2025-03-27 11:38:37 -04:00
Vadym Barda and GitHub
96847e644b
langgraph: add tests for remote graph interrupts ( #4048 )
2025-03-27 15:17:29 +00:00
7021ce3742
patch: fix return type of Topic.update ( #4029 )
...
This PR fixes the return type annotation of the `update` method from
`None` to `bool`, as the method returns a boolean value indicating
whether self.values has changed
Co-authored-by: kakaogames <kakaogames@Justin-MacBook-Pro.local >
2025-03-26 16:57:35 -04:00
Nuno Campos and GitHub
d0c0aa9697
benchmark: remove some benchmarks ( #4039 )
...
Remove some benchmarks temporarily so we can fit more stuff into the
annotation
2025-03-26 13:50:53 -07:00
Vadym Barda and GitHub
520de30350
langgraph: fix interrupt deserialization in RemoteGraph ( #4040 )
2025-03-26 16:42:21 -04:00
Eugene Yurtsev
81c0d47363
x
2025-03-26 15:16:44 -04:00
87603d8a00
docs: add version admonitions for Interrupt and RetryPolicy ( #3988 )
...
This pull request includes changes to add version admonitions to the
documentation and update the styling for these admonitions. The most
important changes include the addition of version information to the
documentation, updates to the CSS for version admonitions, and
modifications to the `mkdocs.yml` configuration file to include the new
stylesheets.
this should solve this #3991
---------
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev >
2025-03-26 13:48:54 -04:00
Nuno Campos
e082ba4f85
Warn when get_graph tries to draw edge that doesn't exist
2025-03-25 12:50:47 -07:00
Nuno Campos
2ac22f8246
0.3.20
2025-03-24 18:09:56 -07:00
Nuno Campos
5526486a0b
Use 128bit hash for task ids
2025-03-24 18:04:26 -07:00
Nuno Campos and GitHub
b285a118a7
Log and continue for subgraph schema issues ( #3997 )
2025-03-24 16:31:42 -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
William FH and GitHub
6da6c4443a
Merge branch 'main' into wfh/log_and_continue
2025-03-24 12:25:47 -07:00
Nuno Campos
3f4d1c66c2
0.3.19
2025-03-24 09:45:54 -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 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
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
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
Eugene Yurtsev
8be0fb675a
x
2025-03-21 15:25:28 -04:00
Eugene Yurtsev
d166dea4f0
Merge branch 'main' into eugene/add_latency
2025-03-21 12:55:37 -04:00
Vadym Barda and GitHub
8e922b859c
prebuilt: release 0.1.4 ( #3977 )
2025-03-21 12:05:15 -04:00
Nuno Campos and GitHub
85b81371f7
Use incremental storage in memory checkpointer ( #3960 )
...
- This makes our checkpoint benchmarks more closely resemble the
behavior of our prod checkpointers
- Also found and fixed a bug w multiple subgraphs in same node
accidentally sharing checkpoints
2025-03-20 16:33:47 -07:00
Nuno Campos
46b652a74c
Use incremental storage in memory checkpointer
...
- This makes our checkpoint benchmarks more closely resemble the behavior of our prod checkpointers
- Also found and fixed a bug w multiple subgraphs in same node accidentally sharing checkpoints
2025-03-20 16:11:36 -07:00
Vadym Barda and GitHub
7013ca9a3f
docs: use hosted logo ( #3959 )
2025-03-20 18:17:22 -04:00
William FH and GitHub
0c04aec664
Include enum in check for pydantic state ( #3955 )
2025-03-20 12:03:22 -07:00
Eugene Yurtsev and GitHub
1650c8508e
benchmark: Add compilation only ( #3932 )
...
Add compilation benchmark alone
2025-03-20 14:51:31 -04:00
William Fu-Hinthorn
eb1e1aa010
Include enum in check for pydantic state
2025-03-20 10:29:16 -07:00