2.18.0.0

Version 2.18.0.0 Release Notes

Compatible with OpenSearch 2.18.0

Enhancements

• Filter out remote model auto redeployment (#2976)[https://github.com//pull/2976]
• Allow llmQuestion to be optional when llmMessages is used. (#3072)[https://github.com//pull/3072]
• Enhance batch job task management by adding default action types (#3080)[https://github.com//pull/3080]
• use connector credential in offline batch ingestion (#2989)[https://github.com//pull/2989]
• change to model group access for batch job task APIs (#3098)[https://github.com//pull/3098]
• add rate limiting for offline batch jobs, set default bulk size to 500 (#3116)[https://github.com//pull/3116]
• Support ML Inference Search Processor Writing to Search Extension (#3061)[https://github.com//pull/3061]
• Enable pass query string to input_map in ml inference search response processor (#2899)[https://github.com//pull/2899]
• add config field in MLToolSpec for static parameters (#2977)[https://github.com//pull/2977]
• Add textract and comprehend url to trusted enpoints (#3154)[https://github.com//pull/3154]

Bug Fixes

• Fix ml inference ingest processor always return list using JsonPath (#2985)[https://github.com//pull/2985]
• populate time fields for connectors on return (#2922)[https://github.com//pull/2922]
• Fix for rag processor throwing NPE when optional parameters are not provided (#3057)[https://github.com//pull/3057]
• Fix PR #2976 bug due to missing adding function_name and algorithm in querying models (#3104)[https://github.com//pull/3104]
• Gracefully handle error when generative_qa_parameters is not provided (#3100)[https://github.com//pull/3100]
• Fix error log to show the right agent type (#2809)[https://github.com//pull/2809]
• fix model stuck in deploying state during node crash/cluster restart (#3137)[https://github.com//pull/3137]
• increase the wait timeout to fetch the master key (#3151)[https://github.com//pull/3151]
• Handle BWC for bedrock converse API (#3173)[https://github.com//pull/3173]

Maintenance

• Bump protobuf version to 3.25.5 to patch potential DOS (#3083)[https://github.com//pull/3083]
• removing api keys from the integ test log (#3112)[https://github.com//pull/3112]
• allowing backport prs to skip approval (#3132)[https://github.com//pull/3132]
• updating the approval requirement (#3148)[https://github.com//pull/3148]
• unblocking the integ test pipeline for release (#3159)[https://github.com//pull/3159]

Infrastructure

• Support index.auto_expand_replicas 0-all for .plugins-ml-config (#3017)[https://github.com//pull/3017]
• Add Test Env Require Approval Action (#3005)[https://github.com//pull/3005]
• upgrading upload artifact to v4 (#3162)[https://github.com//pull/3162]
• Bump actions/download-artifact from 3 to 4.1.7 in /.github/workflows (#2881)[https://github.com//pull/2881]

Documentation

• add tutorial for cross-account model invocation on amazon managed cluster (#3064)[https://github.com//pull/3064]
• support role temporary credential in connector tutorial (#3058)[https://github.com//pull/3058]
• connector blueprint for amazon bedrock converse (#2960)[https://github.com//pull/2960]
• Updates dev guide to inform the workflow approval step (#3062)[https://github.com//pull/3062]
• tune titan embedding model blueprint for v2 (#3094)[https://github.com//pull/3094]
• Add bedrock multimodal build-in function usage example in doc (#3073)[https://github.com//pull/3073]

2.17.0.0

Version 2.17.0.0 Release Notes

Compatible with OpenSearch 2.17.0

Features

• Offline batch ingestion API actions and data ingesters (#2844)[https://github.com//pull/2844]
• Support get batch transform job status in get task API (#2825)[https://github.com//pull/2825]

Enhancements

• Adding additional info for memory metadata (#2750)[https://github.com//pull/2750]
• Support skip_validating_missing_parameters in connector (#2830)[https://github.com//pull/2830]
• Support one_to_one in ML Inference Search Response Processor (#2801)[https://github.com//pull/2801]
• Expose ML Config API (#2850)[https://github.com//pull/2850]

Bug Fixes

• Fix delete local model twice quickly get 500 response issue (#2806)[https://github.com//pull/2806]
• Fix cohere model input interface cannot validate cohere input issue (#2847)[https://github.com//pull/2847]
• Add processed function for remote inference input dataset parameters to convert it back to its original datatype (#2852)[https://github.com//pull/2852]
• Use local_regex as default type for guardrails (#2853)[https://github.com//pull/2853]
• Agent execution error in json format (#2858)[https://github.com//pull/2858]
• Fix custom prompt substitute with List issue in ml inference search response processor (#2871)[https://github.com//pull/2871]
• Fix breaking changes in config index fields (#2882)[https://github.com//pull/2882]
• Output only old fields in get config API (#2892)[https://github.com//pull/2892]
• Fix http dependency in CancelBatchJobTransportAction (#2898)[https://github.com//pull/2898]

Maintenance

• Applying spotless to common module (#2815)[https://github.com//pull/2815]
• Fix Cohere test (#2831)[https://github.com//pull/2831]

Infrastructure

• Test: recover search index tool it in multi node cluster (#2407)[https://github.com//pull/2407]

Documentation

• Add tutorial for Bedrock Guardrails (#2695)[https://github.com//pull/2695]

Refactoring

• Code refactor not to occur nullpointer exception (#2816)[https://github.com//pull/2816]

2.16.0.0

Version 2.16.0.0 Release Notes

Compatible with OpenSearch 2.16.0

Features

• Add initial MLInferenceSearchResponseProcessor (#2688)[https://github.com//pull/2688]
• Add initial search request inference processor (#2731)[https://github.com//pull/2731]
• Add Batch Prediction Mode in the Connector Framework for batch inference (#2661)[https://github.com//pull/2661]

Enhancements

• Automated model interface generation on aws llms (#2689)[https://github.com//pull/2689]
• Increase execute thread pool size (#2691)[https://github.com//pull/2691]
• Add multi modal default preprocess function (#2500)[https://github.com//pull/2500]
• Add model input validation for local models in ml processor (#2610)[https://github.com//pull/2610]
• Removing experimental from the Conversation memory feature(#2592)[https://github.com//pull/2592]
• Pass all parameters including chat_history to run tools (#2714)[https://github.com//pull/2714]
• Feat: add bedrock runtime agent for knowledge base (#2651)[https://github.com//pull/2651]
• change disk circuit breaker to cluster settings (#2634)[https://github.com//pull/2634]

Bug Fixes

• Add stashcontext to connector getter (#2742)[https://github.com//pull/2742]
• Excluding remote models from max node per node setting (#2732)[https://github.com//pull/2732]
• Add logging for throttling and guardrail in connector (#2725)[https://github.com//pull/2725]
• Add acknowledge check for index creation in missing places (#2715)[https://github.com//pull/2715]
• Update config index mappings to use correct field types (#2710)[https://github.com//pull/2710]
• Fix yaml test issue (#2700)[https://github.com//pull/2700]
• Fix MLModelTool returns null if the response of LLM is a pure json object (#2675)[https://github.com//pull/2675]
• Bump ml config index schema version (#2656)[https://github.com//pull/2656]
• Fix final answer with extra meaningless symbol (#2676)[https://github.com//pull/2676]
• Add XContentType to wrap the CreateIndexRequest mappings in _doc key to fix v1 templates issue (#2759)[https://github.com//pull/2759]
• Remove ignoreFailure and fix JsonArray Parsing Issue (#2770)[https://github.com//pull/2770]
• Merge the existing parameters when updating connectors (#2784)[https://github.com//pull/2784]

Maintenance

• Upgrade djl version to 0.28.0 (#2578)[https://github.com//pull/2578]
• Register system index descriptors through SystemIndexPlugin.getSystemIndexDescriptors (#2586)[https://github.com//pull/2586]

Infrastructure

• Enable tests with mockStatic in MLEngineTest (#2582)[https://github.com//pull/2582]
• Fix GA workflow that publishes Apache Maven artifacts (#2625)[https://github.com//pull/2625]
• Temp use of older nodejs version before moving to Almalinux8 (#2628)[https://github.com//pull/2628]
• Add more logs for automated model interface creation (#2778)[https://github.com//pull/2778]

Documentation

• Add amazon textract blueprint (#2562)[https://github.com//pull/2562]
• Make all Bedrock model blueprints in a tidier format (#2642)[https://github.com//pull/2642]
• Fix remote inference blueprints (#2692)[https://github.com//pull/2692]
• Add connector blueprint for cohere embedding models in bedrock (#2667)[https://github.com//pull/2667]
• Update tutorials for caching secrets for non-aws models (#2637)[https://github.com//pull/2637]
• Add tutuorial for cross-encoder model on sagemaker (#2607)[https://github.com//pull/2607]
• Add offline batch inference connector blueprints (#2768)[https://github.com//pull/2768]

Refactoring

• Change multimodal connector name to bedrock multimodal connector (#2672)[https://github.com//pull/2672]

2.15.0.0

Version 2.15.0.0 Release Notes

Compatible with OpenSearch 2.15.0.0

Features

• Add connector tool (#2516)
• guardrails model support (#2491)

Enhancements

• hanlde the throttling error in the response header (#2442)
• Implementing retry for remote connector to mitigate throttling issue (#2462)
• ml inference ingest processor support for local models (#2508)
• add setting to allow private IP (#2534)
• add IMMEDIATE refresh policy (#2541)

Bug Fixes

• fix memory CB bugs and upgrade UTs to compatible with core changes (#2469)
• fix error of ML inference processor in foreach processor (#2474)
• fix error message with unwrapping the root cause (#2458)
• adding immediate refresh to delete model group request (#2514)
• Fix model still deployed after calling undeploy API (#2510)
• Fix bedrock embedding generation issue (#2495)
• Fix init encryption master key (#2554)

Documentation

• add a connector blueprint for Amazon Comprehend APIs (#2470)
• add titan embeeding v2 to blueprint (#2480)
• tutorial: generate embedding for arrays of object (#2477)
• Small fix in blueprint docs (#2501)
• Titan Embedding Connector Blueprint content referenced by users of OpenSearch 2.11 version (#2519)

Infrastructure

• add IT for flow agent with CatIndexTool (#2425)
• Remove strict version dependency to compile minimum compatible version (#2486)
• add IT flow agent with search index tool (#2460)
• fix flaky IT (#2530)
• disable jvm memory circuit breaker for IT (#2540)
• fix flaky test of PredictionITTests and RestConnectorToolIT (#2437)

Maintenance

• Updating security reachout email (#2445)

2.14.0.0

Version 2.14.0.0 Release Notes

Compatible with OpenSearch 2.14.0.0

Features

• Initiate MLInferencelngestProcessor (#2205)
• Add TTL to un-deploy model automatically (#2365)
• ML Model Interface (#2357)

Enhancements

• Change httpclient to async (#1958)
• Migrate RAG pipeline to async processing. (#2345)
• Filtering hidden model info from model profiling for users other than superadmin (#2332)
• check model auto deploy (#2288)
• restrict stash context only for stop words system index (#2283)
• Add a flag to control auto-deploy behavior (#2276)

Bug Fixes

• fix stopwords npe (#2311)
• guardrails npe (#2304)
• not sending failure message when model index isn't present (#2351)
• fix guardrails mapping (#2279)
• fix no model group index issue in connector helper notebook (#2336)
• Fixes #2317 predict api not working with asymmetric models (#2318)
• fixing isHidden null issue (#2337)
• fix remote register model / circuit breaker 500(#2264)
• guardrails bug fixes and IT for creating guardrails (#2269)
• Added missing result filter to inference (#2367)
• making Boolean type for isHidden (#2341
• Clear planningWorkerNodes when model auto-deploys again after undeploy (#2396)
• Avoid race condition in syncup model state refresh (#2405)
• Add a flag to distinguish remote model auto deploy and transport deploy (#2410)
• Add deploySetting in registering local models (#2415)

Refactoring

• feat: Add search index tool (#2356)
• Move visualization tool to ml-commons (#2363)

Documentation

• Add connector blueprint for VertexAI Embedding endpoint (#2268)

Infrastructure

• remove checkstyle (#2312)
• Increase rounding delta from 0.005% to 0.5% on RestMLInferenceIngestProcessorIT (#2372)
• add agent framework security it tests by (#2266)
• Add IT for interface (#2394)
• Fix local build failure for RestMLInferenceIngestProcessorIT (#2402)

Maintenance

• fix CVE for org.eclipse.core.runtime (#2378)

2.13.0.0

Version 2.13.0.0 Release Notes

Compatible with OpenSearch 2.13.0

Features

• hidden agent (#2204)
• auto deployment for remote models (#2206)
• support question answering model (#2208)
• Guardrails for remote model input and output (#2209)

Enhancements

• Adding connector http timeout in the connector level (#1835)
• enable auto redeploy for hidden model (#2102)
• Add verification to rate limiter number field (#2113)
• asymmetric embeddings (#2123)
• Set the number of ml system index primary shards to 1 (#2137)
• prevent exposing internal ip when an agent gets an internal OpenSearch exception (#2154)
• Change the index update settings to make it only contain dynamic settings (#2156)
• add remote predict thread pool (#2207)
• add local inference enabling/disabling setting (#2232)
• Add request level parameters for system_prompt and user_instructions (#2236)
• Add support for Cohere and other chat model input/outputs in the RAG pipeline (#2238)

Infrastructure

• Add integration tests for the RAG pipeline covering OpenAI and Bedrock (#2213)

Bug Fixes

• fix error code when executing agent (#2120)
• fix npe when executing agent with empty parameter (#2145)
• fix delete model cache on macOS causing model deploy fail with model (#2180)
• adding BWC for connector config field (#2184)
• Fix onnx dep (#2198)
• update the response code to 404 when deleting a memory (#2212)
• Fix model enable flag not loading (#2221)
• updating ml_connector schema version (#2228)
• fix json error (#2234)
• update remote model auto deploy tests in predict runner (#2237)

Documentation

• Add Cohere Chat blueprint with RAG (#1991)
• add tutorial for semantic search with byte quantized vector and Cohere embedding model (#2127)
• add tutorial for rerank pipeline with Cohere rerank model (#2134)
• add tutorial for chatbot with rag (#2141)
• add tutorial for building your own chatbot (#2144)
• add tutorial for CFN template integration (#2161)
• fix cohere chat blueprint (#2167)
• add demo notebook for creating connector (#2192)
• enhance connector helper notebook to support 2.9 (#2202)

Maintenance

• Updates sample cert and admin keystore (#2143)
• Bump common-compress package to fix CVE (#2186)
• Suppress removal AccessController in java.security has been deprecated and marked for removal (#2195)

Refactoring

• refactor memory logs (#2121)
• parse tool input to map (#2131)

2.12.0.0

Version 2.12.0.0 Release Notes

Compatible with OpenSearch 2.12.0

Maintenance

• Add Austin and Henry as maintainer (#1579)
• Updated version of awssdk (#1607)
• Update Gradle to 8.4 (#1697)
• Address CVE-2023-42503 (#1727)
• Fix CVE-2023-2976 and upgrade guava to be consistent (#2013)
• Fix CVE-2023-42503 due to djl models (#2016)
• Add maintainer (#1952)
• Updating maintainers list (#1938)
• Bump Mockito dependencies (#1868)
• Updated OpenSearch Lucene snapshot location (#1834)
• Add kotlin stblib dependency for SearchAlertTool (#1861)
• Update dependency com.jayway.jsonpath:json-path to v2.9.0 (#1956)
• Update http package import for 2.x (#1957)
• Update the lucene snapshot url (#2082)
• removing skills first (#2089)

Infrastructure

• Onboarding Jenkins prod docker images to github ci check (#1566)
• Add code coverage report for commons and memory modules (#1585)
• Adding UT coverage for in-cache update and fine-tuning throttling feature (#1913)
• Add tests for MLAgent Get and Delete (#1794)
• Fix race confition in index initialization and RestUpdateConnector UT (#1857)
• Fix failing flaky tests due to pytorch library not available for dependency plugins (#1886)
• Adding tests for all the agent runners (#1792)
• Update deprecated openAI mode in integration test and fix flaky tests (#1858)

Documentation

• Updated developer guide to include links for getting started with git (#1409)
• Add triaging doc (#1250)
• Add bedrock blueprint doc (#1501)
• Add bedrock titan embedding model blueprint (#1527)
• Fix bedrock embedding model blueprint (#1563)
• Add openai embedding model blueprint (#1602)
• Added Connector Blueprint for AI21 Labs Jurassic-2 Mid (#1617)
• Update default model_access_mode for model group (#1677)
• Add cohere version 3 embedding model (#1721)
• Blueprint for multi-model titan model (#1729)
• AI connector blueprint for the Aleph Alpha Luminous-Base Embedding Model (#2003)
• Add tutorial doc for semantic search on amazon opensearch (#1928)
• Add tutorial doc for semantic search with OpenAI embedding model (#1936)
• Add connector blueprint for Azure OpenAI Embedding and Chat model (#2062)
• Add updated Cohere Embedding blueprint (#2063)
• add tutorial for conversational search (#2075)
• Add Cohere Chat blueprint with RAG (#1991)

Bug Fixes

• Fix missing lombok version compilation failure issue (#1278)
• Fix update connector API (#1484)
• Fixes bugs in the Cohere Blueprint (#1505)
• Fix register client API (#1561)
• Fixing MachineLearningNodeClient create connector, deploy model, register model group actions (#1584)
• Fix model/connector update API to address security concern (#1595)
• Fixing class casting exception for MachineLearningNodeClient GetMLTask API (#1618)
• Fix for controller error stack trace and tokenbucket (#1985)
• Fix internal connector (#1992)
• Fix argument pass (#1993)
• Fix error code when failed to delete model (#2037)
• Fix edge case for validate json method (#2045)
• Fix long pending issue when deleting model (#2046)
• Add escape method for process function (#2055)
• Fix bug in delete empty memory (#1966)
• Fix dup last trace (#1975)
• Add a version filter to enable bwc in 2.12 (#1944)
• Fix error message (#1976)
• Fix string.format wrong parameter position (#1960)
• Fix null taskId causing model undeploy issue (#1945)
• Fix updating plugins.ml_commons.jvm_heap_memory_threshold takes no effect (#1946)
• Fix compilation when backport (#1798)
• Fix duplicate node if node has both data and ml role (#1830)
• Fix partially response issue in profile API result (#1775)
• Fix: RestStatus 500 returned ml validation (#1811)
• Fix the hardcode password in IT (#1856)
• Fix model not deploy issue under intensive prediction tasks (#1930)
• Fix bug - not found agent index (#1867)
• Issue #1787: Fixing connector endpoint returns index not found (#1885)
• Issue #1878/#1879/#1880: Fixing index not found for model group/model/tasks (#1895)
• Change searchResponse method to fix breaking change in managed service (#1917)
• Adjust ListTool response format (#1912)
• Issue #844: Add accessUserInformation to the plugin security policy (#1959)
• Escape input data (#1974)
• flow agent suggestions missing (#2064)
• bug fix - tool parameters missing (#2065)
• fix empty tool parameter issue (#2067)
• tool uses original input (#2068)
• update Unthrotized error code to 401 (#2076)
• handle null value exceptions when arguments are missing or Null in caling RAG pipeline (#2079)
• changing error message and error code (#2073) (#2086)
• Fix bwc issue in remote prediction (#2085)

Experimental Feature

• Update Model API (#1350)
• Hidden model implementation (#1755)
• Model & user level throttling (#1814)
• Search agent api (#1826)
• Add GetTool API and ListTools API (#1850)
• Enable in-place update model (#1796)
• Memory Manager and Update Memory Actions/APIs (#1776)
• Add CatIndexTool (#1770)
• Add search and singular APIs to conversation memory (#1720)
• Memory interface in spi (#1771)
• Tool interface (#1772)
• Add get config api to retrieve root agent id (#1995)
• Register agent rest and transport actions (#1801)
• IndicesHandler and conversationIndexMemory (#1777)
• Adding mlmodeltool and agent tool with tests (#1778)
• Get and delete agent APIs (#1779)
• Add register action request/response (#1780)
• Add execute agent api; add load extension (#1810)
• Add IndexMapping Tool (#1934)
• Agent meta classes in common (#1759)
• Agent framework disable/enable flag (#1994)
• Do not allow non super admin users to undeploy hidden models (#1981)
• System error handling (#2051)
• Handling tool errors (#1881)
• Changes to hidden model code to use OPENDISTRO_SECURITY_USER instad of ssl principal (#1897) (#1900)
• Support regenerate for chatbot (#1823)
• Update IndexMappingTool Description (#1998)
• Add more user based permission check in Memory (#1935)
• Update memory index name and add updated_time (#1793)
• fine tune prompt;refactor conversational agent code (#2094)

Feature

• Add cross encoder support (#1739)
• Enable conversation memory feature flags (#2095)

Enhancements

• Add register and deploy api in client (#1502)
• Added create connector API for MLClient (#1506)
• Added register model group API for MLClient (#1519)
• Expose execute api for MLClient (#1541)
• Add prefix to show the error is from remote service (#1515)
• Fine tune predict API: read model from index directly (#1559)
• Removed empty host check, inherently within httpHost object generation (#1599)
• Cluster restart model auto redeploy (#1627)
• Add new data fields in the memory layer and update tests (#1753)
• Check if model id is null when undeploy (#2015)
• Adds inputs validation for create memory (#2040)
• Make response_field customizable in MLModelTool (#2043)
• Add memory id and interation id for non-verbose (#2005)
• Issue #1965: Remove logging of sensitive chat history (#2012)
• Update memory if tool output needs to be included in response (#2018)
• Disable dynamic mapping for config index (#2027)
• Move allow model setting from rest to transport (#1977)
• Fine tune connector process function (#1963)
• Change model auto redeploy enabled to true (#1809)
• Add auto expand replica settings to memories (#1824)
• Add interaction id into execute response (#1825)
• Add more methods to client (#1782)
• Support charset input params and change default charset as utf8 (#1828)
• Fine tune log message based on error type (#1842)
• Stash thread context before running forward action (#1906)
• Refine the error message on cluster status not ready scenario (#1931)
• Add Request-Source header (#1892)
• Add process function for bedrock (#1554)
• send agent execution response after saving memory (#2066)
• add conversational flow agent (#2069)

REFACTOR

• Rename memory field names in responses (#2020)
• Refactor memory layer APIs (#1890)

2.11.1.0

Version 2.11.1.0 Release Notes

Compatible with OpenSearch 2.11.1

Bug Fixes

• fix multiple docs support (#1516)
• support step size for embedding model which outputs less embeddings (#1586)
• validate step size (#1587)

CVE Fixes

• Bump json version to address CVE-2023-5072 (#1551)

2.11.0.0

Version 2.11.0.0 Release Notes

Compatible with OpenSearch 2.11.0

Experimental Features

• Update Connector API (#1227)

Enhancements

• Add neural search default processor for non OpenAI/Cohere scenario (#1274)
• Add tokenizer and sparse encoding (#1301)
• allow input null for text docs input (#1402)
• Add support for context_size and include 'interaction_id' in SearchRequest (#1385)
• adding model level metric in node level (#1330)
• add status code to model tensor (#1443)
• add bedrockURL to trusted connector regex list (#1461)
• Performance enhacement for predict action by caching model info (#1472)

Infrastructure

Bug Fixes

• fix parameter name in preprocess function (#1362)
• fix spelling in Readme.md (#1363)
• Fix error message in TransportDeplpoyModelAction class (#1368)
• fix null exception in text docs data set (#1403)
• fix text docs input unescaped error; enable deploy remote model (#1407)
• restore thread context before running action listener (#1418)
• fix more places where thread context not restored (#1421)
• Fix BWC test suite (#1426)
• support bwc for process function (#1427)
• fix model group auto-deletion when last version is deleted (#1444)
• fixing metrics correlation algorithm (#1448)
• throw exception if remote model doesn't return 2xx status code; fix predict runner (#1477)
• fix no worker node exception for remote embedding model (#1482)
• fix for delete model group API throwing incorrect error when model index not created (#1485)
• fix no worker node error on multi-node cluster (#1487)
• Fix prompt passing for Bedrock by passing a single string prompt for Bedrock models. (#1490)

Documentation

Maintenance

• Ignoring Redeploy test on MacOS due to known failures (#1414)
• throw exception when model group not found during update request (#1447)
• Add a setting to control the update connector API (#1274)

Refactoring

• register new versions to a model group based on the name provided (#1452)
• if model version fails to register, update model group accordingly (#1463)

2.10.0.0

Version 2.10.0.0 Release Notes

Compatible with OpenSearch 2.10.0

Experimental Features

• Conversations and Generative AI in OpenSearch (#1150)

Enhancements

• Add feature flags for remote inference (#1223)
• Add eligible node role settings (#1197)
• Add more stats: connector count, connector/config index status (#1180)

Infrastructure

• Updates demo certs used in integ tests (#1291)
• Add Auto Release Workflow (#1306)

Bug Fixes

• Fixing metrics (#1194)
• Fix null pointer exception when input parameter is null. (#1192)
• Fix admin with no backend role on AOS unable to create restricted model group (#1188)
• Fix parameter parsing bug for create connector input (#1185)
• Handle escaping string parameters explicitly (#1174)
• Fix model count bug (#1180)
• Fix core package name to address compilation errors (#1157)

Documentation

• Updating cohere blueprint doc (#1213)
• Fixing docs (#1193)
• Add model auto redeploy tutorial (#1175)
• Add remote inference tutorial (#1158)
• Adding blueprint examples for remote inference (#1155)
• Updating developer guide for CCI contributors (#1049)

Maintenance

• Bump checkstyle version for CVE fix (#1216)
• Correct imports for new location with regard to core refactoring (#1206)
• Fix breaking change caused by opensearch core (#1187)
• Bump OpenSearch snapshot version to 2.10 (#1157)
• Bump aws-encryption-sdk-java to fix CVE-2023-33201 (#1309)

Refactoring

• Renaming metrics (#1224)
• Changing messaging for IllegalArgumentException on duplicate model groups (#1294)
• Fixing some error message handeling (#1222)