langchain[patch]: Release 0.2.9 (#24327)
langchain: fix extended test (#24282)
community[patch]: use asyncio.sleep instead of sleep in OpenAI Assistant async (#24275)
retrievers: MultiVectorRetriever similarity_score_threshold search type (#23539)
langchain==0.2.8
Changes since langchain==0.2.7
docs: specify init_chat_model version (#24274)
langchain[patch]: Release 0.2.8 (#24273)
langchain[minor]: Generic configurable model (#23419)
langchain[minor]: add document_variable_name to create_stuff_documents_chain (#24083)
core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038)
multiple: use modern installer in poetry (#23998)
langchain-community==0.2.7
Release langchain-community==0.2.7
Changes since langchain-community==0.2.6
community: release 0.2.7 (prev was langchain) (#23997)
core[minor],community[patch],standard-tests[patch]: Move InMemoryImplementation to langchain-core (#23986)
community[patch]: Add constraint for pdfminer.six to unbreak CI (#23988)
core[minor],community[minor]: Upgrade all @root_validator() to @pre_init (#23841)
community[minor]: Support PGVector in PebbloRetrievalQA (#23874)
community[patch]: Fix source path mismatch in PebbloSafeLoader (#23857)
core[minor]: Add Graph Store component (#23092)
core[minor]: add upsert, streaming_upsert, aupsert, astreaming_upsert methods to the VectorStore abstraction (#23774)
community[patch]: Redis.delete should be a regular method not a static method (#23873)
docs: Arxiv docs update (#23871)
community: add support for 'cloud' parameter in JiraAPIWrapper (#23057)
community: add model_name param valid for GPT4AllEmbeddings (#23867)
community: add SingleStoreDB semantic cache (#23218)
feat(community): add bind_tools function for ChatLiteLLM (#23823)
huggingface: Fix huggingface tei support (#22653)
community: fix typo in unit tests for test_zenguard.py (#23819)
infra: update mypy 1.10, ruff 0.5 (#23721)
community[deepinfra]: fix tool call parsing. (#23162)
feat: Implement ChatBaichuan asynchronous interface (#23589)
community: make bing web search as the only option (#23523)
community[patch]: Fix MiniMaxChat validate_environment error (#23770)
community[patch]: Update @root_validators to use explicit pre=True or pre=False (#23737)
feat(community): add support for tool_calls response (#23765)
community[patch]: update @root_validator in utilities namespace (#23768)
Milvus vectorstore: fix pass ids as argument after upsert (#23761)
community[patch]: root validator set explicit pre=False or pre=True (#23764)
docs: updated PPLX model (#23723)
community[patch]: Fix requests alias for load_tools (#23734)
community: release 0.2.7 (prev was langchain) (#23997)
core[minor],community[patch],standard-tests[patch]: Move InMemoryImplementation to langchain-core (#23986)
community[patch]: Add constraint for pdfminer.six to unbreak CI (#23988)
core[minor],community[minor]: Upgrade all @root_validator() to @pre_init (#23841)
community[minor]: Support PGVector in PebbloRetrievalQA (#23874)
community[patch]: Fix source path mismatch in PebbloSafeLoader (#23857)
core[minor]: Add Graph Store component (#23092)
core[minor]: add upsert, streaming_upsert, aupsert, astreaming_upsert methods to the VectorStore abstraction (#23774)
community[patch]: Redis.delete should be a regular method not a static method (#23873)
docs: Arxiv docs update (#23871)
community: add support for 'cloud' parameter in JiraAPIWrapper (#23057)
community: add model_name param valid for GPT4AllEmbeddings (#23867)
community: add SingleStoreDB semantic cache (#23218)
feat(community): add bind_tools function for ChatLiteLLM (#23823)
huggingface: Fix huggingface tei support (#22653)
community: fix typo in unit tests for test_zenguard.py (#23819)
infra: update mypy 1.10, ruff 0.5 (#23721)
community[deepinfra]: fix tool call parsing. (#23162)
feat: Implement ChatBaichuan asynchronous interface (#23589)
community: make bing web search as the only option (#23523)
community[patch]: Fix MiniMaxChat validate_environment error (#23770)
community[patch]: Update @root_validators to use explicit pre=True or pre=False (#23737)
feat(community): add support for tool_calls response (#23765)
community[patch]: update @root_validator in utilities namespace (#23768)
Milvus vectorstore: fix pass ids as argument after upsert (#23761)
community[patch]: root validator set explicit pre=False or pre=True (#23764)
docs: updated PPLX model (#23723)
community[patch]: Fix requests alias for load_tools (#23734)
community[patch]: Update root_validators to use explicit pre=True or pre=False (#23736)
community[patch]: Update root_validators to use pre=True or pre=False (#23731)
community[patch]: Invoke callback prior to yielding token (#23638)
community: Fix LanceDB similarity search bug (#23591)
Jira: Allow Jira access using only the token (#23708)
community: Register pandas df in duckdb when creating vector_store (#23690)
openai, anthropic, ...: with_structured_output to pass in explicit tool choice (#23645)
docs: standardize azure openai page (#23642)
core: add RemoveMessage (#23636)
community: fix extended tests (#23640)
docs[patch]: Update diagrams (#23613)
community:perplexity[patch]: standardize init args (#21794)
community[patch]: set tool name for tongyi&qianfan llm (#22889)
community: docstrings toolkits (#23616)
community: fix lint (#23611)
community[patch]: Test InMemoryVectorStore with RWAPI test suite (#23603)
community: Standardise tool import for arxiv & semantic scholar (#23578)
fix(community): allow support for disabling max_tokens args (#21534)
... (truncated)
Commits
007c5a8 multiple: use modern installer in poetry (#23998)
e80c150 community: release 0.2.7 (prev was langchain) (#23997)
core[patch]: Release 0.2.21 (#24372)
core[patch]: add InjectedToolArg annotation (#24279)
core[patch]: Fix regression requiring input_variables in few chat prompt templates (#24360)
core[patch]: Fix one unit test for chat prompt template (#24362)
langchain-core==0.2.20
Changes since langchain-core==0.2.19
core[patch]: Release 0.2.20 (#24322)
Docs: Add how to dispatch custom callback events (#24278)
core: docstrings vectorstores update (#24281)
core[patch]: fix Typing.cast import (#24313)
core: docstrings documents (#23506)
core[patch]: Add encoding options when create prompt template from a file (#24054)
core[patch]: docstrings langchain_core/ files update (#24285)
core[patch]: Update typing for template format to include jinja2 as a Literal (#24144)
core[patch]: allow message utils to work with lcel (#23743)
docs: Spell check fixes (#24217)
core docstrings tracers update (#24211)
core: docstrings utils update (#24213)
langchain-core==0.2.19
Changes since langchain-core==0.2.18
core[patch]: Release 0.2.19 (#24272)
core[patch]: support passing args_schema through as_tool (#24269)
langchain[minor]: Generic configurable model (#23419)
core[patch]: add tool name to tool message (#24243)
openai: release 0.1.17 (#24361)
openai[patch]: fix key collision and _astream (#24345)
openai: raw response headers (#24150)
openai: remove some params from default serialization (#24280)
openai[patch]: update openai params (#23691)
langchain-openai==0.1.16
Changes since langchain-openai==0.1.15
openai[patch]: Release 0.1.16 (#24202)
integrations[patch]: require core >=0.2.17 (#24207)
standard-tests[patch]: add tests for runnables as tools and streaming usage metadata (#24153)
core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038)
NumPy 2.0.0 is the first major release since 2006. It is the result of
11 months of development since the last feature release and is the work
of 212 contributors spread over 1078 pull requests. It contains a large
number of exciting new features as well as changes to both the Python
and C APIs.
This major release includes breaking changes that could not happen in a
regular minor (feature) release - including an ABI break, changes to
type promotion rules, and API changes which may not have been emitting
deprecation warnings in 1.26.x. Key documents related to how to adapt to
changes in NumPy 2.0, in addition to these release notes, include:
A new variable-length string dtype, numpy.dtypes.StringDType and a new
numpy.strings namespace with performant ufuncs for string operations,
Support for float32 and longdouble in all
numpy.fft functions,
Support for the array API standard in the main numpy
namespace.
Performance improvements:
Sorting functions sort, argsort,
partition, argpartition have been
accelerated through the use of the Intel x86-simd-sort and
Google Highway libraries, and may see large (hardware-specific)
speedups,
macOS Accelerate support and binary wheels for macOS >=14, with
significant performance improvements for linear algebra
operations on macOS, and wheels that are about 3 times smaller,
numpy.char fixed-length string operations have
been accelerated by implementing ufuncs that also support
numpy.dtypes.StringDType in addition to the
fixed-length string dtypes,
A new tracing and introspection API,
numpy.lib.introspect.opt_func_info, to determine
which hardware-specific kernels are available and will be
dispatched to.
numpy.save now uses pickle protocol version 4 for saving
arrays with object dtype, which allows for pickle objects larger
than 4GB and improves saving speed by about 5% for large arrays.
Python API improvements:
... (truncated)
Commits
1d49c7f Merge pull request #26698 from charris/prepare-2.0.0
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
- `@dependabot show ignore conditions` will show all of the ignore conditions of the specified dependency
- `@dependabot ignore major version` will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
- `@dependabot ignore minor version` will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
- `@dependabot ignore ` will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore ` will remove all of the ignore conditions of the specified dependency
- `@dependabot unignore ` will remove the ignore condition of the specified dependency and ignore conditions
Bumps the python-requirements group with 7 updates in the / directory:
0.2.6
0.2.9
0.2.6
0.2.7
0.2.11
0.2.21
0.1.14
0.1.17
0.1.84
0.1.92
1.26.4
2.0.0
1.35.10
1.35.15
Updates
langchain
from 0.2.6 to 0.2.9Release notes
Sourced from langchain's releases.
... (truncated)
Commits
24e9b48
langchain[patch]: Release 0.2.9 (#24327)cf28708
Neo4j: Update with non-deprecated cypher methods, and new method to associate...2a3288b
docs: Add ChatBaichuan docstrings (#24348)1792684
removed deprecated classes from pipelineai.ipynb, added support for LangChain...e60ad12
docs(infobip.ipynb): fix typo (#24328)fc41730
neo4j: Fix test for order-insensitive comparison and floating-point precision...47ed7f7
infra: fix release prerelease deps bug (#24323)80e7cd6
core[patch]: Release 0.2.20 (#24322)6c3e65a
infra: prerelease dep checking on release (#23269)616196c
Docs: Add how to dispatch custom callback events (#24278)Updates
langchain-community
from 0.2.6 to 0.2.7Release notes
Sourced from langchain-community's releases.
... (truncated)
Commits
007c5a8
multiple: use modern installer in poetry (#23998)e80c150
community: release 0.2.7 (prev was langchain) (#23997)9f8fd08
community: release 0.2.7 (#23993)5d78b34
[Docs] typo Update in azureopenai.ipynb (#23945)bedd893
core: release 0.2.12 (#23991)1e957c0
docs: rm discord (#23985)f765e8f
core[minor],community[patch],standard-tests[patch]: Move InMemoryImplementati...aa8c9bb
community[patch]: Add constraint for pdfminer.six to unbreak CI (#23988)2c180d6
core[minor],community[minor]: Upgrade all@root
_validator() to@pre
_init (#23...f152d6e
docs(llamacpp): fix copy paste error (#23983)Updates
langchain-core
from 0.2.11 to 0.2.21Release notes
Sourced from langchain-core's releases.
... (truncated)
Commits
a4c101a
core[patch]: Release 0.2.21 (#24372)c5a07e2
core[patch]: add InjectedToolArg annotation (#24279)80f3d48
openai: release 0.1.18 (#24369)7d83189
openai[patch]: use model_name in AzureOpenAI.ls_model_name (#24366)eb26b55
couchbase: Add chat message history (#24356)96bac8e
core[patch]: Fix regression requiring input_variables in few chat prompt temp...034a8c7
community: support advanced text extraction options for pdf documents (#20265)a402de3
langchain[patch]: fix wrongdict
key inOutputFixingParser
, `RetryOutputP...a47f69a
partners/mongodb : Significant MongoDBVectorSearch ID enhancements (#23535)cc2cbfa
milvus: release 0.1.2 (#24365)Updates
langchain-openai
from 0.1.14 to 0.1.17Release notes
Sourced from langchain-openai's releases.
Commits
9e4a0e7
core[patch]: Fix one unit test for chat prompt template (#24362)8163924
openai: release 0.1.17 (#24361)61976a4
pinecone: release 0.1.2 (#24355)b5360e2
community[patch]: Release 0.2.8 (#24354)4cf6708
openai[patch]: fix key collision and _astream (#24345)bcb5f35
community: Fix SQLDatabse.from_databricks issue when ran from Job (#24346)24e9b48
langchain[patch]: Release 0.2.9 (#24327)cf28708
Neo4j: Update with non-deprecated cypher methods, and new method to associate...2a3288b
docs: Add ChatBaichuan docstrings (#24348)1792684
removed deprecated classes from pipelineai.ipynb, added support for LangChain...Updates
langsmith
from 0.1.84 to 0.1.92Release notes
Sourced from langsmith's releases.
... (truncated)
Commits
5cd607b
fix return value of update_examples (#885)a6a01c4
fix(js): keep traceable wrappedFunc returnValue props (#787)c249862
Update pyproject.toml3be2b9a
feat(js): automatic handoff from Langchain RunnableLambda to traceable (#874)9020072
fix(datasets): fix return value of update_examplesfa06b91
feat(datasets): add support for bulk updating examples (#884)5a04c37
Merge branch 'main' into sam/bulk-update-examplesa502116
fix readme79f2bc5
chore: add EU API URl to docs & infer web URLa048677
Avoid reexportingUpdates
numpy
from 1.26.4 to 2.0.0Release notes
Sourced from numpy's releases.
... (truncated)
Commits
1d49c7f
Merge pull request #26698 from charris/prepare-2.0.02103511
DOC: Remove duplicate in author list.db8030e
BUG: Change cibuildwheel version [wheel build]1a68264
REL: Prepare for the NumPy 2.0.0 release [wheel build]c8665ba
Merge pull request #26696 from charris/backport-26582103f4dd
Merge pull request #26697 from charris/backport-25963c193dcd
Merge pull request #26695 from charris/backport-266678fa8191
BUG: Fix bug in numpy.pad() (#25963)ece3559
BUG: weighted nanpercentile, nanquantile and multi-dim q (#26582)b31e195
BUG: Adds asanyarray to start of linalg.cross (#26667)Updates
openai
from 1.35.10 to 1.35.15Release notes
Sourced from openai's releases.
... (truncated)
Changelog
Sourced from openai's changelog.
Commits
0de7419
release: 1.35.15f8f01a6
chore(docs): document how to do per-request http client customization (#1560)8ce46fe
chore(internal): update formatting (#1553)435a580
release: 1.35.142e8ea52
chore(docs): minor update to formatting of API link in README (#1550)83ebf66
chore(internal): minor options / compat functions updates (#1549)f14f859
chore(internal): minor formatting changesec4511a
release: 1.35.132df8aa3
chore(internal): add helper function (#1538)c80fe33
fix(threads/runs/create_and_run_stream): correct tool_resources paramDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting
@dependabot rebase
.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show