WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-21 23:22:27 +02:00
Code Issues Packages Projects Releases Wiki Activity
4,722 Commits 321 Branches 571 Tags
10859da99af731a575aec3e5976bde514b25ca96
Commit Graph
4722 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
William Fu-Hinthorn 10859da99a Handle sneds 2025-03-24 17:12:50 -07:00
Nuno CamposandGitHub b285a118a7 Log and continue for subgraph schema issues (#3997) 2025-03-24 16:31:42 -07:00
William FHandGitHub 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 CamposandGitHub 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 YurtsevandGitHub 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 FHandGitHub 6da6c4443a Merge branch 'main' into wfh/log_and_continue 2025-03-24 12:25:47 -07:00
Eugene YurtsevandGitHub 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 YurtsevandGitHub c84f35eff5 add langmanus to prebuilt (#3999) 2025-03-24 13:26:53 -04:00
Eugene YurtsevandGitHub 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 CamposandGitHub 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 CamposandGitHub 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 MartinandGitHub 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 MartinandGitHub d6856131b6 Fix broken links in ntbks (#3993) 
A number of Anthropic links recently changed
 2025-03-23 17:59:14 -07:00
Lance MartinandGitHub 7d90440035 Update llms.txt for langgraph (#3987) 2025-03-23 15:39:09 -07:00
alxdr3kandGitHub fed785eabd docs: fix typo in low_level.md (#3968) 
- Fix typo
 2025-03-21 16:40:41 -04:00
YkohandGitHub 765b04adfd Docs: fix example (#3972) 2025-03-21 16:39:39 -04:00
Movina MosesGitHubEugene Yurtsev
 		7085b149e5 fix(docs): Update deprecated methods and add validator (#3920) 
- Added a validator to sanitize 'name' fields and prevent
string_pattern_mismatch errors.
- Replaced deprecated `dict` method with `model_dump` in line with
Pydantic v2.0 migration guidelines.
- Updated gen_perspectives_chain and gen_queries_chain to ensure
compatibility with structured output and include raw data where needed.
This allows use of fast_llm across the notebook.

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
 2025-03-21 15:51:13 -04:00
ArrayPDGitHubEugene Yurtsev
 		11c71fef89 chore(docs): Improve documentation for AsyncSqliteSaver (#3858) 
**Description:**
Make AsyncSqliteSaver examples workable.

**Issue:**
For "Usage within StateGraph" example,
SyntaxError: 'async with' outside async function

For "Raw usage" example
KeyError: 'checkpoint_ns' and KeyError: 'id'

**Dependencies:**
N/A

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
 2025-03-21 15:50:51 -04:00
Eugene Yurtsev 8be0fb675a x 2025-03-21 15:25:28 -04:00
William FHandGitHub 1b4f335ffe Add studio URL flag (#3980) cli==0.1.79 2025-03-21 11:23:05 -07:00
William Fu-Hinthorn 9c36a7de85 Add studio URL flag 2025-03-21 11:20:29 -07:00
Eugene Yurtsev d166dea4f0 Merge branch 'main' into eugene/add_latency 2025-03-21 12:55:37 -04:00
Vadym BardaandGitHub 8e922b859c prebuilt: release 0.1.4 (#3977) cli==0.1.78 prebuilt==0.1.4 2025-03-21 12:05:15 -04:00
Vadym BardaandGitHub 9a4c30135f prebuilt: pass last message to structured response model in create_react_agent (#3976) 2025-03-21 11:58:27 -04:00
William FHandGitHub bc6651f34c Studio cli command (#3962) 2025-03-20 17:57:56 -07:00
William Fu-Hinthorn 23bb5369b9 Studio cli command 2025-03-20 17:51:08 -07:00
Nuno CamposandGitHub 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 54ab833b74 Lint 2025-03-20 16:26:52 -07:00
Nuno Campos 4ea936eaf4 Lint 2025-03-20 16:24:57 -07:00
Nuno Campos 9d81ec9ffd Lint 2025-03-20 16:22:24 -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 BardaandGitHub 7013ca9a3f docs: use hosted logo (#3959) 2025-03-20 18:17:22 -04:00
William FHandGitHub 0c04aec664 Include enum in check for pydantic state (#3955) 2025-03-20 12:03:22 -07:00
Eugene YurtsevandGitHub 1650c8508e benchmark: Add compilation only (#3932) 
Add compilation benchmark alone
 2025-03-20 14:51:31 -04:00
Eugene YurtsevandGitHub e176b98fe7 Add llms-txt resources (#3935) 2025-03-20 14:44:21 -04:00
William Fu-Hinthorn eb1e1aa010 Include enum in check for pydantic state 2025-03-20 10:29:16 -07:00
Nuno CamposandGitHub 77c833e1e5 Use fast path for prepare_next_tasks on input (#3931) 
- When there are no values in checkpoint no need to run through all the
PULL candidates
- When there are input writes save updated_channels to use on the next
call to prepare_next_tasks
 2025-03-20 08:46:48 -07:00