## langchain-ai/langchain — v0.1.12…v0.1.13

_148 commits._

### Features
- **community[minor]: Add InMemoryVectorStore (#19326)** (00614f3)
- **docs[minor]: Add chat model selection tabs component (#19296)** (40f846e)
- **splitters: Add ensure_ascii parameter (#18485)** (e5d7e45)
- **community: add Couchbase Vector Store (#18994)** (7ad0a3f)
- **ci[minor]: Bump LC scripts package, add retry option (#19285)** (17c62e0)
- **community: Add `keep_alive` parameter to control how long the model w… (#19005)** (b826440)
- **Community: Add mistral oss model support to azureml endpoints, plus configurable timeout (#19123)** (044bc22)
- **Add docstrings for Clickhouse class methods (#19195)** (24a0a44)
- **[langchain_community] milvus vectorstores upsert: add **kwargs to make it use for other argument also (#19193)** (785f8ab)
- **experimental: add buffer_size hyperparameter to SemanticChunker as in source video (#19208)** (77868b1)
- **templates: Add rag lantern template (#16523)** (7c26ef8)
- **[Enhancement] Add support for directly providing a run_id (#18990)** (7803374)
- **community[minor]: Add support for translation in HuggingFacePipeline (#19190)** (635b337)
- **community: Add `partition` parameter to DashVector (#19023)** (7cd87d2)
- **community: Add model argument for maritalk models and better error handling (#19187)** (e64cf1a)
- **community[minor]: Add Baidu VectorDB as vector store (#17997)** (c922ea3)
- **docs[minor]ci[minor]: Add script & CI to check recurring links daily (#19100)** (98cd8f6)
- **community: Add support for cohere SDK v5 (keeps v4 backwards compatibility) (#19084)** (7253b81)
- **Add new beta StructuredPrompt (#19080)** (751fb7d)
- **core[minor]: Add Runnable.batch_as_completed (#17603)** (2b7c3c5)

### Fixes
- **langchain[patch]: Release 0.1.13 (#19351)** (d95ea35)
- **community[patch]: Release 0.0.29 (#19350)** (b58b387)
- **core[patch]: Release 0.1.33 (#19348)** (5d22097)
- **langchain[patch]: Add tests for indexing (#19342)** (aa9ccca)
- **langchain[patch]: add stop for various non-openai agents (#19333)** (d9396bd)
- **community[patch]: Invoke callback prior to yielding token (titan_takeoff_pro) (#18624)** (7d216ad)
- **community[patch]: Invoke callback prior to yielding token (sparkllm) (#18625)** (455a744)
- **community[patch]: Invoke callback prior to yielding token (replicate) (#18626)** (5ac1860)
- **community[patch]: Invoke callback prior to yielding token (pai_eas_endpoint) (#18627)** (9525e39)
- **community[patch]: Invoke callback prior to yielding token (openai) (#18628)** (140f06e)
- **community[patch]: Invoke callback prior to yielding token (ollama) (#18629)** (280a914)
- **core[patch]: Update `messages` namespace to fix API reference docs (#19161)** (8609afb)
- **openai[patch]: pass message name (#17537)** (69e9610)
- **mongodb[patch]: Added scoring threshold to caching (#19286)** (f8078e4)
- **code[patch]: Add in code documentation to core Runnable with_retry method (docs only)  (#19192)** (2c835ba)
- **core[patch]: Pass sync run manager for sync stream fallback in astream (#19280)** (4b3dd34)
- **core[patch]: Move `globals` to a module instead of a package (non breaking change) (#19159)** (d314acb)
- **core: update _rm_titles to account for title argument name bug (#19036)** (7afecec)
- **Josha91 fix docstring (#19249)** (efcdf54)
- **core: Fix Exception handling in XMLOutputParser (#19126)** (07de4ab)
- **text-splitters, infra: fix `libs/langchain/dev.Dockerfile` so that the `text-splitter` directory is copied before poetry installation (#19214)** (ca9c8c5)
- **community: Fix Milvus got multiple values for keyword argument 'timeout' (#19232)** (c3310c5)
- **langchain[patch]: update base imports to core (#19248)** (95904fe)
- **ai21[patch]: AI21 Labs bump SDK version (#19114)** (21c4547)
- **langchain-mongodb: [test-fix] add explicit index_name setting on test vector creation (#19245)** (516cc44)
- **core[patch]: Add LLM output to message response_metadata (#19158)** (bd329e9)
- **mongodb[patch]: release 0.1.2 (#19243)** (6fa1438)
- **mongodb[patch]: Remove in-memory cache from cache abstractions (#18987)** (ec02600)
- **mongodb[patch]: Remove embedding retrieval from mongodb payload (#19035)** (866d640)
- **community[patch]: add stop parameter support to volcengine maas (#19052)** (514fe80)
- **community: Fix import path for StreamingStdOutCallbackHandler example (#19170)** (5aa6893)
- **openai[patch]: fix async http client (#19164)** (611d5a1)
- **community: Fix all page numbers were the same for _BaseGoogleVertexAISearchRetriever (#19175)** (8d2c34e)
- **community[patch]: support fastembed v1 and v2 (#19125)** (1a55e95)
- **text-splitters[patch]: fix json split of RecursiveJsonSplitter (#19119)** (fd4f536)
- **community[patch]: fix yuan2 chat model errors while invoke. (#19015)** (0e0030f)
- **community[patch]: Fixed bug in merging `generation_info` during chunk concatenation in Tongyi and ChatTongyi  (#19014)** (c244e1a)
- **community[patch]: Use langchain-astradb for AstraDB doc loader (#19071)** (f2a7dda)
- **community[patch]: Add Blended Search Support to `GoogleVertexAISearchRetriever` (#19082)** (cee0363)
- **langchain[patch]: make hub work with older langchainhub versions (#19076)** (0ddfe7f)
- **community[patch]: Fix sparkllm embeddings api bug. (#19122)** (cced3eb)
- **community[patch]: implement qdrant _aembed_query and use it in other async funcs (#19155)** (c20aeef)
- **community[patch] : publishes duration as milliseconds to Fiddler (#19166)** (34d6f05)
- **community[patch] : adds feedback and status for Fiddler callback handler events (#19157)** (b551d49)
- **community[patch]: add args_schema to sql_database tools for langGraph integration (#18595)** (f5b9aed)
- **core[patch]: rc release 0.1.33-rc.1 (#19103)** (191ddbc)
- **core[patch]: Change structured prompt lc id to match js (#19099)** (508f758)
- **voyageai[patch]: init package (#19098)** (7ce81eb)
- **ci[patch]: Set root dir to ./docs (#19102)** (5157b15)
- **ai21[patch]: AI21 Labs Batch Support in Embeddings (#18633)** (4d7f6fa)
- **ibm[patch]: release 0.1.3 (#19094)** (d5cf360)
- **ibm[patch]: add async tests, add tokenize support (#18898)** (b15d150)
- **core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051)** (06165ef)
- **code[patch]: Add in code documentation to core Runnable assign method (docs only) (#18951)** (d4b025c)
- **core[patch]: Release 0.1.32 (#19088)** (573f48e)
- **community[patch]: Fix NotionDBLoader 400 Error by conditionally adding filter parameter (#19075)** (ae73b9d)
- **templates: fix rag-lancedb dep (#19010)** (71d0981)
- **experimental[patch]: release 0.0.54 (#19000)** (2ffb214)

### Backend
- **[Feat] Accept non-dict if only 1 prompt input variable (#19156)** (68298cd)
- **core: Updated docstring for RunnablePick (#18832)** (3c4529a)
- **core: Simplify astream logic in BaseChatModel and BaseLLM (#19332)** (4c2e887)
- **core: implement a batch_size parameter for CacheBackedEmbeddings (#18070)** (305d74c)
- **Permit function eval on llm data type (#19287)** (89af308)
- **community: Use langchain-astradb for AstraDB caches (#18419)** (30e4a35)
- **core[minor]: Enhance cache flexibility in BaseChatModel (#17386)** (50f93d8)
- **experimental: update the notebook link of semantic chunk. (#19253)** (ff31cc1)
- **langchain: creating assistants with file_ids (#19199)** (f36418a)
- **community:  VectorStore Infinispan, adding autoconfiguration (#18967)** (9b2f9ee)
- **elasticsearch: check for deployed models (#18973)** (6f544a6)
- **langchain: preserve document metadata in `FlashrankRerank` (#19148)** (58c7687)
- **core: Updated docstring for Context class (#19079)** (bc648f6)
- **Updating format of pip install (#19198)** (bde199d)
- **templates: Added template for JaguarDB  (#16757)** (edf9d1c)
- **community: `llms` imports fixes (#18943)** (7de1d9a)
- **templates: update qdrant self query (#19218)** (aee5138)
- **deprecate community docugami loader (#19230)** (21f7599)
- **core[minor]: moved fake llms and embeddings to core (#19226)** (366ba77)
- **Update README.md (#19172)** (160a707)
- **docsUpdate azure_cosmos_db.ipynb (#19087)** (6327be9)
- **langchain: upgrade mypy (#19163)** (745d247)
- **core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960)** (aa785fa)
- **infra: run min version ci before integration tests (#18945)** (caf47ab)
- **community, langchain, infra: revert store extended test deps outside of poetry (#19153)** (781aee0)
- **community, langchain, infra: store extended test deps outside of poetry (#18995)** (9e569d8)
- **templates: Switch neo4j generation template to LLMGraphTransformer (#19024)** (321db89)
- **Updated security policy (#19089)** (41e2f60)
- **community[minor]: Revamp PGVector Filtering (#18992)** (6cdca43)
- **core: Runnable pass kwargs to _astream_log_implementation in astream_log (#19055)** (69a8ef2)
- **infra: update upload-artifact and download-artifact to v4 (#19044)** (5e0c58f)
- **templates, cli: more security deps (#19006)** (74b2c0a)
- **template: bump more lockfiles (#19003)** (9052d05)
- **templates: bump lockfile deps (#19001)** (49f3cc0)

### Docs
- **docs: Fix typo in infino.ipynb (#18640)** (9dfce56)
- **docs: contribute / integrations code examples update (#19319)** (e46419c)
- **docs: integration deprecation docs (#19283)** (7eb376d)
- **docs: update slack toolkit ipynb in integration (#19219)** (4761c09)
- **docs: Embellish article on splitting by tokens with more examples and missing details (#18997)** (bb0dd8f)
- **docs: fix import path for `FlashrankRerank` example notebook (#19146)** (dc4ce82)
- **docs:Make url as a markdown link (#19212)** (ae3c7f7)
- **docs:Fix links to LangSmith docs on Evaluation page (#19210) (#19216)** (94e58dd)
- **docs: ChatTongyi example error (#19013)** (bcc771e)
- **docs: provided hyperlinks to text and fixed grammar (#19092)** (9235dad)
- **docs: Add docs for RouterRunnable (#19191)** (a1b26dd)
- **docs: Update why.ipynb (#19173)** (7c092f4)
- **docs: Remove duplicated line in Get Started section (#19182)** (d96e0b2)
- **docs: fix link to interface TextSplitter (#19177)** (ff94f86)
- **docs: update stale links in Together AI documentation (#19011)** (05008c4)
- **docs: update docstring of Together class (#19008)** (80eb510)
- **docs: add vikingdb docstrings(#19016)** (ef9813d)
- **docs: update docs for yuan2 in LLMs and Chat models integration. (#19028)** (f79d0cb)
- **docs: Corrected error (#19030)** (eec0237)
- **docs: `providers` update 8 (#19053)** (a49ac55)
- **docs: Update llm_caching.ipynb (#19085)** (0a78407)
- **docs: Fixed Grammar in Considerations of Model I/O Concepts (#19091)** (553a520)
- **docs: Fix execution results of `docs/docs/modules/data_connection/indexing.ipynb` (#19112)** (d647ff1)
- **docs: fix databricks document url (#19096)** (ebc4a64)
- **docs: Add in code documentation to core Runnable with_fallbacks method (docs only) (#19104)** (4468e5b)
- **docs: fix API link for BaseLoader (#19128)** (b9c62fb)
- **docs: Fix source column xata.ipynb (#19137)** (527676a)
- **docs: update the list of providers (#19012)** (190887c)
- **docs: voyageai as provider (#19154)** (bbe164a)
- **docs: updated google integration related imports in the documentation (#19131)** (e3ff107)
- **docs: fix vercel build script (#19090)** (e276817)
- **docs:fixed typo in streaming document (#19045)** (688a5bd)
- **docs: make links internal (#19063)** (0ae39ab)
- **docs: deprecate old airbyte loader docs (#19048)** (2999d06)
- **docs: Updated index definition and reference to LangChain-MongoDB (#19047)** (4c53e31)
- **docs: Add graph construction docs (#18904)** (e5e15c8)

_Recap by [Repo Wrapped](https://repowrapped.com/gh/langchain-ai/langchain?utm_source=github-action)._