pypi langchain 0.1.13
v0.1.13

latest releases: 0.3.1, 0.3.0, 0.3.0.dev2...
6 months ago

What's Changed

  • experimental[patch]: release 0.0.54 by @efriis in #19000
  • templates: bump lockfile deps by @efriis in #19001
  • template: bump more lockfiles by @efriis in #19003
  • templates, cli: more security deps by @efriis in #19006
  • templates: fix rag-lancedb dep by @efriis in #19010
  • core[minor]: Add Runnable.batch_as_completed by @nfcampos in #17603
  • Add graph construction docs by @tomasonjo in #18904
  • infra: update upload-artifact and download-artifact to v4 by @efriis in #19044
  • Updated index definition and reference to LangChain-MongoDB by @prakul in #19047
  • docs: deprecate old airbyte loader docs by @efriis in #19048
  • community[patch]: Fix NotionDBLoader 400 Error by conditionally adding filter parameter by @gunnzolder in #19075
  • docs: make links internal by @baskaryan in #19063
  • Add new beta StructuredPrompt by @nfcampos in #19080
  • core: Runnable pass kwargs to _astream_log_implementation in astream_log by @rere950303 in #19055
  • core[patch]: Release 0.1.32 by @baskaryan in #19088
  • docs:fixed typo in streaming document by @yangml103 in #19045
  • code[patch]: Add in code documentation to core Runnable assign method (docs only) by @liugddx in #18951
  • docs: ignore custom llm integration index (TEMP) by @baskaryan in #19090
  • community[minor]: Revamp PGVector Filtering by @eyurtsev in #18992
  • Updated security policy by @eyurtsev in #19089
  • core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict by @eyurtsev in #19051
  • community: Add support for cohere SDK v5 (keeps v4 backwards compatibility) by @billytrend-cohere in #19084
  • langchain_ibm[patch] add async tests, add tokenize support by @MateuszOssGit in #18898
  • ibm[patch]: release 0.1.3 by @efriis in #19094
  • Switch neo4j generation template to LLMGraphTransformer by @tomasonjo in #19024
  • partners: AI21 Labs Batch Support in Embeddings by @Josephasafg in #18633
  • docs[minor]ci[minor]: Add script & CI to check recurring links daily by @bracesproul in #19100
  • ci[patch]: Set root dir to ./docs by @bracesproul in #19102
  • voyageai[patch]: init package by @efriis in #19098
  • Change lc id to match what's possible in js by @nfcampos in #19099
  • core[patch]: rc release 0.1.33-rc.1 by @baskaryan in #19103
  • community, langchain, infra: store extended test deps outside of poetry by @efriis in #18995
  • docs: updated imports in the documentation by @lkuligin in #19131
  • community, langchain, infra: revert store extended test deps outside of poetry by @efriis in #19153
  • docs: voyageai as provider by @efriis in #19154
  • docs: update the list of providers by @sepiatone in #19012
  • Add Baidu VectorDB as vector store by @fengjial in #17997
  • Community: add args_schema to sql_database tools for langGraph integration by @juanfe88 in #18595
  • community [patch] : adds feedback and status for Fiddler callback handler events by @bhalder in #19157
  • infra: run min version ci before integration tests by @efriis in #18945
  • core: allow LLMs async streaming to fallback on sync streaming by @maximeperrindev in #18960
  • langchain: upgrade mypy by @eyurtsev in #19163
  • community [patch] : publishes duration as milliseconds to Fiddler by @bhalder in #19166
  • Fix source column xata.ipynb by @kostasb in #19137
  • community: implement qdrant _aembed_query and use it in other async funcs by @kaijietti in #19155
  • docs: fix API link for BaseLoader by @samanhappy in #19128
  • community: Fix sparkllm embeddings api bug. by @liugddx in #19122
  • code[patch]: Add in code documentation to core Runnable with_fallbacks method (docs only) by @liugddx in #19104
  • fix databricks document url by @case-k-git in #19096
  • docs: Fix execution results of docs/docs/modules/data_connection/indexing.ipynb by @g-votte in #19112
  • Fixed Grammar in Considerations of Model I/O Concepts documentation page - Update concepts.mdx by @AnubhavMadhav in #19091
  • Update azure_cosmos_db.ipynb by @wmwxwa in #19087
  • Update llm_caching.ipynb by @wmwxwa in #19085
  • langchain[patch]: make hub work with older langchainhub versions by @eyurtsev in #19076
  • community: Add Blended Search Support to GoogleVertexAISearchRetriever by @holtskinner in #19082
  • docs: providers update 8 by @leo-gan in #19053
  • community: Use langchain-astradb for AstraDB doc loader by @cbornet in #19071
  • Corrected error by @nithinv-27 in #19030
  • docs: update docs for yuan2 in LLMs and Chat models integration. by @cauwulixuan in #19028
  • community: Fixed bug in merging generation_info during chunk concatenation in Tongyi and ChatTongyi by @liushuaikobe in #19014
  • community: fix yuan2 chat model errors while invoke. by @cauwulixuan in #19015
  • add comment by @19374242 in #19016
  • partners[together]: update docstring of Together class by @sepiatone in #19008
  • docs: update stale links in Together AI documentation by @sepiatone in #19011
  • text-splitters:fix json split of RecursiveJsonSplitter which may cause memory of chunks by @six17 in #19119
  • community: support fastembed v1 and v2 by @skozlovf in #19125
  • docs: fix link to interface TextSplitter by @samanhappy in #19177
  • community: Add model argument for maritalk models and better error handling by @rodrigo-f-nogueira in #19187
  • community: Add partition parameter to DashVector by @wangcailin in #19023
  • docs: Remove duplicated line in Get Started section by @amorphius in #19182
  • docs: Update why.ipynb by @inpyeong in #19173
  • Update README.md by @songyi1999 in #19172
  • community: Fix all page numbers were the same for _BaseGoogleVertexAISearchRetriever by @eycjur in #19175
  • core: Add docs for RouterRunnable by @nikhilkmr300 in #19191
  • community: Add support for translation in HuggingFacePipeline by @nikhilkmr300 in #19190
  • openai[patch]: fix async http client by @baskaryan in #19164
  • community: Fix import path for StreamingStdOutCallbackHandler example by @primate88 in #19170
  • docs: provided hyperlinks to text and fixed grammar by @AnubhavMadhav in #19092
  • Example error by @htaoruan in #19013
  • community: add stop parameter support to volcengine maas by @joyme123 in #19052
  • moved fake llms and embeddings to core by @lkuligin in #19226
  • langchain-mongodb: Remove embedding retrieval from mongodb payload by @Jibola in #19035
  • langchain-mongodb: Remove in-memory cache from cache abstractions by @Jibola in #18987
  • deprecate community docugami loader by @kenzie28 in #19230
  • templates: update qdrant self query by @Anush008 in #19218
  • community: llms imports fixes by @leo-gan in #18943
  • mongodb[patch]: release 0.1.2 by @efriis in #19243
  • core[patch]: Add LLM output to message response_metadata by @jacoblee93 in #19158
  • [Enhancement] Add support for directly providing a run_id by @hinthornw in #18990
  • docs:Fix links to LangSmith docs on Evaluation page (#19210) by @EstephaniaCalvoC in #19216
  • langchain-mongodb: [test-fix] add explicit index_name setting on test vector creation by @Jibola in #19245
  • community: Add rag lantern template by @gustavo-yt in #16523
  • templates: Added template for JaguarDB by @DannyMang in #16757
  • partners: AI21 Labs bump SDK version by @Josephasafg in #19114
  • langchain[patch]: update base imports to core by @efriis in #19248
  • community: Fix Milvus got multiple values for keyword argument 'timeout' by @liugddx in #19232
  • text-splitters, infra: fix libs/langchain/dev.Dockerfile so that the text-splitter directory is copied before poetry installation by @g-votte in #19214
  • docs:Make url as a markdown link by @Howe829 in #19212
  • experimental: add buffer_size hyperparameter to SemanticChunker as in source video by @umbilnm in #19208
  • [langchain_community] milvus vectorstores upsert: add **kwargs to make it use for other argument also by @rgupta2508 in #19193
  • Updating format of pip install by @saurvkmr in #19198
  • docs: fix import path for FlashrankRerank example notebook by @Simon-Stone in #19146
  • Add docstrings for Clickhouse class methods by @hamza-m-farooqi in #19195
  • core: Fix Exception handling in XMLOutputParser by @KangmoonSeo in #19126
  • Community: Add mistral oss model support to azureml endpoints, plus configurable timeout by @tjaffri in #19123
  • core: Updated docstring for Context class by @aaronjimv in #19079
  • langchain: preserve document metadata in FlashrankRerank by @Simon-Stone in #19148
  • Josha91 fix docstring by @hwchase17 in #19249
  • core: update _rm_titles to account for title argument name bug by @rsk2327 in #19036
  • docs: Embellish article on splitting by tokens with more examples and missing details by @tonybaloney in #18997
  • community: Add keep_alive parameter to control how long the model w… by @gonvee in #19005
  • elasticsearch: check for deployed models by @maxjakob in #18973
  • community: VectorStore Infinispan, adding autoconfiguration by @rigazilla in #18967
  • langchain: creating assistants with file_ids by @fredericowu in #19199
  • experimental: update the notebook link of semantic chunk. by @1openwindow in #19253
  • docs: update slack toolkit ipynb in integration by @HatsuneMK00 in #19219
  • core[minor]: Enhance cache flexibility in BaseChatModel by @alhridoy in #17386
  • core[patch]: Move globals to a module instead of a package (non breaking change) by @leo-gan in #19159
  • core[patch]: Pass sync run manager for sync stream fallback in astream by @eyurtsev in #19280
  • code[patch]: Add in code documentation to core Runnable with_retry method (docs only) by @liugddx in #19192
  • docs: integration deprecation docs by @efriis in #19283
  • ci[minor]: Bump LC scripts package, add retry option by @bracesproul in #19285
  • community: Use langchain-astradb for AstraDB caches by @cbornet in #18419
  • langchain-mongodb: Added scoring threshold to caching by @Jibola in #19286
  • Permit function eval on llm data type by @hinthornw in #19287
  • core: implement a batch_size parameter for CacheBackedEmbeddings by @chrispy-snps in #18070
  • community: add Couchbase Vector Store by @nithishr in #18994
  • splitters: Add ensure_ascii parameter by @liugddx in #18485
  • openai[patch]: pass message name by @efriis in #17537
  • docs[minor]: Add chat model selection tabs component by @bracesproul in #19296
  • core[patch]: Simplify astream logic in BaseChatModel and BaseLLM by @cbornet in #19332
  • core: messages fix by @leo-gan in #19161
  • docs: contribute / integrations code examples update by @sepiatone in #19319
  • core: Updated docstring for RunnablePick by @devesh-2002 in #18832
  • community: Add InMemoryVectorStore by @cbornet in #19326
  • docs: Fix typo in infino.ipynb by @laoazhang in #18640
  • community[patch]: Invoke callback prior to yielding token (ollama) by @Lord-Haji in #18629
  • community[patch]: Invoke callback prior to yielding token (openai) by @Lord-Haji in #18628
  • community[patch]: Invoke callback prior to yielding token (pai_eas_endpoint) by @Lord-Haji in #18627
  • community[patch]: Invoke callback prior to yielding token (replicate) by @Lord-Haji in #18626
  • community[patch]: Invoke callback prior to yielding token (sparkllm) by @Lord-Haji in #18625
  • community[patch]: Invoke callback prior to yielding token (titan_takeoff_pro) by @Lord-Haji in #18624
  • langchain[patch]: add stop for various non-openai agents by @mackong in #19333
  • [Feat] Accept non-dict if only 1 prompt input variable by @hinthornw in #19156
  • langchain[patch]: Add tests for indexing by @eyurtsev in #19342
  • core[patch]: Release 0.1.33 by @baskaryan in #19348
  • community[patch]: Release 0.0.29 by @baskaryan in #19350
  • langchain[patch]: Release 0.1.13 by @baskaryan in #19351

New Contributors

Full Changelog: v0.1.12...v0.1.13

Don't miss a new langchain release

NewReleases is sending notifications on new releases.