Skip to content

Releases: langchain-ai/langchain

langchain-core==0.3.72

24 Jul 00:40
bd3d649
Compare
Choose a tag to compare

Changes since langchain-core==0.3.71

release(core): 0.3.72 (#32214)
fix(core): Dereference Refs for pydantic schema fails in tool schema generation (#32203)
docs: formatting cleanup (#32188)

langchain-xai==0.2.5

22 Jul 17:22
116b758
Compare
Choose a tag to compare

Changes since langchain-xai==0.2.4

fix: bump deps for release (#32179)
release(xai): 0.2.5 (#32174)
docs(xai): update for Grok 4 (#31953)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
langchain-xai[patch]: Add ruff bandit rules to linter (#31816)
openai[patch]: allow specification of output format for Responses API (#31686)
standard-tests: add benchmarks (#31302)
docs: update xai docs (#31382)
xai: document live search feature (#31381)

langchain-perplexity==0.1.2

22 Jul 20:30
ca137bf
Compare
Choose a tag to compare

Changes since langchain-perplexity==0.1.1

.
fix(perplexity): temp xfail int tests (#32191)
fix: bump deps for release (#32179)
release(perplexity): 0.1.2 (#32176)
feat(perplexity): expose search_results in chat model (#31468)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
langchain-perplexity[patch]: Add ruff bandit rules to linter (#31812)
[Doc] Improve api doc for perplexity (#31636)
packaging: remove Python upper bound for langchain and co libs (#31025)

langchain-ollama==0.3.6

22 Jul 17:27
a689679
Compare
Choose a tag to compare

Changes since langchain-ollama==0.3.5

release(ollama): 0.3.6 (#32180)
feat(ollama): warn on empty load responses (#32161)
docs(ollama): add validate_model_on_init note, bump lock (#32172)
fix(ollama): robustly parse single-quoted JSON in tool calls (#32109)

langchain-huggingface==0.3.1

22 Jul 17:22
116b758
Compare
Choose a tag to compare

Changes since langchain-huggingface==0.3.0

fix: bump deps for release (#32179)
release(huggingface): 0.3.1 (#32177)
fix(huggingface): update model used in standard tests (#32116)
fix: bump lockfiles (#31923)
ruff: restore stacklevels, disable autofixing (#31919)
ruff: add bugbear across packages (#31917)
huggingface[patch]: ruff fixes and rules (#31912)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
huggingface: fix HuggingFaceEndpoint._astream() got multiple values for argument 'stop' (#31385)
langchain-huggingface[patch]: Add ruff bandit rules to linter (#31798)
huggingface: handle image-text-to-text pipeline task (#31611)

langchain-deepseek==0.1.4

22 Jul 17:38
af3789b
Compare
Choose a tag to compare

Changes since langchain-deepseek==0.1.3

fix(deepseek): release openai version (#32181)
fix: bump deps for release (#32179)
release(deepseek): 0.1.4 (#32178)
fix(deepseek): convert tool output arrays to strings (#31913)
fix: bump lockfiles (#31923)
ruff: restore stacklevels, disable autofixing (#31919)
deepseek[patch]: ruff fixes and rules (#31901)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
langchain-deepseek[patch]: add ruff bandit rules (#31792)
[Doc] Improve api doc for DeepSeek (#31655)
standard-tests: add benchmarks (#31302)
partners: (langchain-deepseek) fix deepseek-r1 always returns an empty reasoning_content when reasoning (#31065)
packaging: remove Python upper bound for langchain and co libs (#31025)
partners[lint]: run pyupgrade to get code in line with 3.9 standards (#30781)
Fix deepseek release tag, as it is update name. (#30717)
Revert "deepseek: temporarily bypass tests" (#30424)

langchain-core==0.3.71

22 Jul 19:56
0c4054a
Compare
Choose a tag to compare

Changes since langchain-core==0.3.70

release(core): 0.3.71 (#32186)
fix(core): exclude api_key from tracing metadata (#32184)
fix(core): add type key when tracing in some cases (#31825)
feat(core): add sanitize_for_postgres utility to fix PostgreSQL NUL byte DataError (#32157)

langchain-chroma==0.2.5

22 Jul 19:27
e41e6ec
Compare
Choose a tag to compare

Changes since langchain-chroma==0.2.4

release(chroma): 0.2.5 (#32183)
feat(chroma): Add Chroma Cloud support (#32125)
chroma[nit]: descriptions in pyproject.toml (#31925)
fix: bump lockfiles (#31923)
ruff: restore stacklevels, disable autofixing (#31919)
ruff: add bugbear across packages (#31917)
chroma[patch]: ruff fixes and rules (#31900)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
chroma: add ruff bandit rules (#31790)
infra: relax types-requests version range (#31504)

langchain-core==0.3.70

21 Jul 19:22
6426144
Compare
Choose a tag to compare

Changes since langchain-core==0.3.69

fix(core): fix parse_resultin case of self.first_tool_only with multiple keys matching for JsonOutputKeyToolsParser (#32106)
release(core): 0.3.70 (#32144)
docs(core): move incorrect arg limitation in rate limiter's docstring (#32118)
fix(core): fix docstrings and add sleep to FakeListChatModel._call (#32108)
fix(core): better error message for empty var names (#32073)
fix(core): implement sleep delay in FakeMessagesListChatModel _generate (#32014)
fix(core): JSON Schema reference resolution for list indices (#32088)
feat(core): update _import_utils.py to not mask the thrown exception (#32071)
fix: fixing missing Docstring Bug if no Docstring is provided in BaseModel class (#31608)
fix: issue a warning if np.nan or np.inf are in _cosine_similarity argument Matrices (#31532)

langchain-ollama==0.3.5

16 Jul 22:51
491f63c
Compare
Choose a tag to compare

Changes since langchain-ollama==0.3.4

release(ollama): release 0.3.5 (#32076)
fix(ollama): num_gpu parameter not working in async OllamaEmbeddings method (#32074)