v9.7.2

Packages Released

• Microsoft.Extensions.AI.Templates 9.7.2-preview.3.25366.2

What's Changed

• Target .NET 8 for more stable runtime requirement by @joelverhagen in #6617

Full Changelog: v9.7.1...v9.7.2

v9.7.1

Packages Released

• Microsoft.Extensions.AI 9.7.1
• Microsoft.Extensions.AI.Abstractions 9.7.1
• Microsoft.Extensions.AI.OpenAI 9.7.1-preview.1.25365.4
• Microsoft.Extensions.AI.AzureAIInference 9.7.1-preview.1.25365.4
• Microsoft.Extensions.AI.Templates 9.7.1-preview.3.25365.4

What's Changed

• Merging changes from internal by @joperezr in #6588
• Bump FunctionInvokingChatClient.MaximumIterationsPerRequest from 10 to 40 by @stephentoub in #6599
• Expose M.E.AI.OpenAI input message conversions by @stephentoub in #6601
• Add schema version to server.json in MCP template by @joelverhagen in #6606
• Update MCP server template readme to show both VS Code and Visual Studio notes by @jeffhandley in #6591
• Fix schema generation for Nullable function parameters. by @eiriktsarpalis in #6596
• Branding updates for 9.7.1 by @joperezr in #6611

Full Changelog: v9.7.0...v9.7.1

v9.7.0

What's Changed

• Branding updates for 9.7 by @joperezr in #6495
• Fix name of genai input/output tokens tag by @stephentoub in #6494
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6503
• Improve handling of RawRepresentation in OpenAI{Response}ChatClient by @stephentoub in #6500
• Bring back AsIChatClient for OpenAI AssistantClient by @stephentoub in #6501
• Add resiliency to Resource Monitoring in Linux by @amadeuszl in #6489
• Merging changes from the internal fork by @joperezr in #6508
• Workaround OpenAI assistant's RunCreationOption's tools override by @stephentoub in #6512
• Add ChatOptions.Instructions by @stephentoub in #6505
• Introduce evaluators for agentic workflows by @shyamnamboodiripad in #6514
• Allow a CachingChatClient to control per-request caching by @stephentoub in #6524
• Tweak OpenAI JSON schema transforms by @stephentoub in #6523
• Merging changes from release/9.6 branch by @joperezr in #6516
• Augment AIJsonUtilities.CreateJsonSchema for more types and annotations by @stephentoub in #6540
• Added conversions from AIFunction to various OpenAI tools by @KrzysztofCwalina in #6539
• Add SpeechToTextResponse.Usage by @stephentoub in #6546
• Implement BLEU score evaluation for NLP tests by @peterwald in #6537
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6553
• #5962 Change to early return of OS instead of throwing by @juliankock in #5963
• Mark log sampling & buffering API as stable by @evgenyfedorov2 in #6534
• Update GenAI otel impl for v1.35 by @stephentoub in #6557
• Implement GLEU and F1 NLP evaluators by @peterwald in #6555
• Update tokenizer algorithm to use is [..] by @peterwald in #6561
• Rename some constants to match convention by @shyamnamboodiripad in #6562
• Add DistributedCachingChatClient/EmbeddingGenerator.AdditionalCacheKeyValues by @stephentoub in #6558

New Contributors

• @KrzysztofCwalina made their first contribution in #6539
• @juliankock made their first contribution in #5963

Full Changelog: v9.6.0...v9.7.0

v9.6.0

What's Changed

• Branding updates for 9.6.0 by @joperezr in #6399
• Add log buffering info to README.md by @evgenyfedorov2 in #6403
• Fix dynamic config update for log buffering by @evgenyfedorov2 in #6435
• Remove unused select param from CreateRecordsForDocumentAsync by @jongalloway in #6341
• Merge internal changes by @joperezr in #6437
• Reduce per-lookup overhead from key validation in HybridCache by @MihaZupan in #6441
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6443
• Merge release/9.5 into main by @joperezr in #6448
• Fix up comments in eval API json files by @shyamnamboodiripad in #6452
• Remove preview tag on Azure DevOps extension by @peterwald in #6456
• Bump PackageValidation against 9.5.0 and enable for stable MEAI packages by @joperezr in #6458
• Fix paramref tag by @gewarren in #6459
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6462
• Add a script to diff the contents of folders that match a specific pattern across two branches by @shyamnamboodiripad in #6453
• Remove title and description keywords from root-level schemas in AIFunctionFactory. by @eiriktsarpalis in #6465
• Replace JSON vector store with SQLite by @MackinnonBuck in #6438
• Update chat template Microsoft.SemanticKernel dependency to 1.53.0 by @MackinnonBuck in #6470
• Update chat template external dependencies by @MackinnonBuck in #6471
• Exclude provider URI from cache key computation by default by @shyamnamboodiripad in #6473
• Make hashing stable w.r.t. indentation settings and property ordering. by @eiriktsarpalis in #6476
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6481
• Add default value for namedArg in Microsoft.Gen.Metrics.parser by @BowenYang666 in #6238
• Update OpenTelemetryChatClient to 1.34 by @stephentoub in #6466
• Delete M.E.AI changelog files by @stephentoub in #6467
• Add comma to remarks by @gewarren in #6485
• Implement disk io metrics for linux by @makazeu in #6374
• Add AIFunction.ReturnJsonSchema by @eiriktsarpalis in #6447

New Contributors

• @MihaZupan made their first contribution in #6441
• @BowenYang666 made their first contribution in #6238

Full Changelog: v9.5.0...v9.6.0

v9.5.0

What's Changed

• Add TextReasoningContent by @stephentoub in #6222
• Use ErrorContent in OpenAIResponseChatClient by @stephentoub in #6231
• OpenAI: Parse detail additional property by @jozkee in #6225
• Branding updates for 9.5 by @joperezr in #6233
• In telemetry, treat AdditionalProperties as sensitive by @SteveSandersonMS in #6239
• Use SHA384 and make key more explicit by @SteveSandersonMS in #6237
• Disable STJ default reflection and fix a number of failing tests. by @eiriktsarpalis in #6241
• Add button to report to download dataset as JSON by @peterwald in #6243
• Introduce Content Safety evaluators by @shyamnamboodiripad in #6223
• Bump vite from 6.2.4 to 6.2.5 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6249
• Only display tags from the latest execution by @shyamnamboodiripad in #6251
• Avoid duplicate data in downloaded report file by @shyamnamboodiripad in #6252
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6253
• Remove use of ConfigureAwait from Microsoft.Extensions.AI.dll for AIFunction invocations by @stephentoub in #6250
• Update dev-server data import to reflect runtime import quirks by @peterwald in #6257
• [release/9.2] Merging internal changes by @joperezr in #6263
• Merging release/9.4 changes by @joperezr in #6264
• Add logging buffering by @evgenyfedorov2 in #5635
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6270
• Add test for optional parameters being required with RequireAllProperties by @jozkee in #6265
• Add fuzzy filtering to the evaluation reports by @peterwald in #6262
• Updating package validation version to 9.4.0 by @joperezr in #6272
• Adding reference to an unsupported built-in tool on OpenAI Chat API no longer throws by @artl93 in #6276
• Update M.E.AI changelogs by @stephentoub in #6269
• Add missing reference to M.E.AI.OpenAI in chat template by @MackinnonBuck in #6275
• Fix two paramref tags by @gewarren in #6281
• Support response caching for safety evaluators by @shyamnamboodiripad in #6277
• Bump vite from 6.2.5 to 6.2.6 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6287
• Display images in conversation for report by @shyamnamboodiripad in #6286
• Augment UseDistributedCache XML docs by @stephentoub in #6256
• Update README.md with keyless auth guidance by @jmatthiesen in #6261
• Augment AIFunctionFactory.Create XML docs by @stephentoub in #6255
• Rename EmbeddingGeneratorExtensions.GenerateEmbedding extension methods by @roji in #6295
• Augment FunctionInvokingChatClient's span with token counts by @stephentoub in #6296
• Rename ChatThreadId to ConversationId by @SteveSandersonMS in #6300
• Repackage azure-devops-extensions-api to fix Azure DevOps report plugin by @peterwald in #6299
• Fix build error by @shyamnamboodiripad in #6301
• Add note on extending timeout for Ollama client by @jongalloway in #6258
• Improve CPU metrics calculations for CgroupV2 by @nivebb8 in #6289
• Restore deleted members as obsolete by @jeffhandley in #6304
• move to AwesomeAssertions by @danmoseley in #6308
• Update chat template dependencies, fix OpenAI/Aspire config, and address build warnings by @MackinnonBuck in #6280
• Support [FromKeyedServices] in AIFunctionFactory by @stephentoub in #6310
• Introduce Context property on EvaluationMetric by @shyamnamboodiripad in #6316
• Utilize IServiceProviderIsService in AIFunctionFactory by @stephentoub in #6317
• Fix Process Metric calculation in CgroupsV2 by @nivebb8 in #6321
• Remove the abstraction for token counting from the main evaluation API by @shyamnamboodiripad in #6320
• Remove AsChatClient/AsEmbeddingGenerator APIs by @jeffhandley in #6327
• Add ChatOptions.AllowMultipleToolCalls by @SteveSandersonMS in #6326
• Disable default required property schema generation and OpenAI strict mode. by @eiriktsarpalis in #6285
• Accessibility fixes for the HTML report by @peterwald in #6329
• Add Windows disk I/O metrics to ResourceMonitoring by @makazeu in #6181
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6336
• Update prompts for quality evaluators by @shyamnamboodiripad in #6328
• Reduce allocations in LogSamplingRuleSelector by @evgenyfedorov2 in #6339
• A couple of minor fixes by @shyamnamboodiripad in #6340
• Update readmes by @shyamnamboodiripad in #6345
• Expose AIContent constructor by @stephentoub in #6346
• Add PDF support to OpenAI AsIChatClient by @stephentoub in #6344
• Make CreateJsonSchema tolerate JSO inputs that don't have a resolver set. by @eiriktsarpalis in #6348
• Skip messages that have no text when rendering conversations as part of evaluation prompts by @shyamnamboodiripad in #6349
• Enhance Function Invocation Extensibility for Microsoft.Extensions.AI by @rogerbarreto in #6325
• Upgrade to Issue Labeler v2.0.0 by @jeffhandley in #6357
• Issue Labeler - Predict PR labels for main and dev branches by @jeffhandley in #6358
• Update CHANGELOGS for M.E.AI libs by @stephentoub in #6359
• Add project template build tests + CG reporting by @MackinnonBuck in #6355
• Fix keys for EvaluationResult.Metrics dictionary to reflect the correct metric names for Safety evaluators by @shyamnamboodiripad in #6361
• Update branding for Azure service used by Safety evaluators by @shyamnamboodiripad in #6362
• Use ConversationId instead of ChatThreadId in README by @gewarren in #6367
• Add Disk IO time metric for Windows in ResourceMonitoring by @makazeu in #6338
• Fix an issue in OSFileSystem's ReadAllByLines method where last line may be dropped by @makazeu in #6373
• Update OpenTelemetryChatClient/EmbeddingGenerator to 1.33 by @stephentoub in #6366
• Add AsIEmbeddingGenerator for Azure.AI.Inference ImageEmbeddingsClient by @stephentoub in #6363
• Add DataContent.Base64Data by @stephentoub in #6365
• Fix AIFunctionFactory handling of default struct arguments by @eiriktsarpalis in #6381
• Add JS dependency update instructions to chat template README by @MackinnonBuck in #6376
• Add see also links to conceptual docs by @gewarren in #6368
• Using nr_periods from cpu.stat to get time elapsed by @nivebb8 in #6335
• Translate OpenAI refusals to ErrorContent by @stephentoub in #6393
• Rename useJsonSchema parameter by @stephentoub in #6394
• Add JSON schema transformation functionality to AIJsonUtilities by @eiriktsarpalis in #6383
• Remove CacheOptions from DiskBasedResponseCache by @shyamnamboodiripad in #6395
• Add back net9.0 version of the aieval dotnet tool by @shyamnamboodiripad i...

v9.4.0

What's Changed

• Fix various build failures by @RussKie in #6039
• Proposal for tweaks to IChatClient contract by @stephentoub in #5998
• Onboard dotnet/issue-labeler workflows for automated area labels by @jeffhandley in #6047
• Only predict area labels for PRs into main and dev by @jeffhandley in #6049
• Upgrade workflows to issue-labeler v1.0.1 by @jeffhandley in #6050
• Fix evaluation report generation by @shyamnamboodiripad in #6061
• Automatically add 'untriaged' label to new issues without milestones by @jeffhandley in #6060
• Address M.E.VectorData feedback for IEmbeddingGenerator by @stephentoub in #6058
• Fix grouping of ChatResponseUpdate into ChatMessage by @SteveSandersonMS in #6074
• Fix handling of empty messages in AzureAIInferenceChatClient by @stephentoub in #6072
• Update OpenTelemetryChatClient/EmbeddingGenerator to v1.31 of genai standard convention by @stephentoub in #6073
• Merging internal changes by @joperezr in #6081
• Merging release/9.3 branch into main by @joperezr in #6082
• Update ordering in CODEOWNERS by @shyamnamboodiripad in #6085
• Bump Package Validation by @joperezr in #6084
• Add types from AIJsonUtilities.JsonContext to reporting JsonContext by @peterwald in #6078
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6097
• Introduce Reason property on EvaluationMetric by @shyamnamboodiripad in #6087
• [AI Evaluation] Add versioning to reporting and caching by @peterwald in #6070
• Add assignments for @dotnet/dotnet-extensions-ai-templates by @RussKie in #6105
• Test templates by @RussKie in #6086
• Add favicon for AiChatWeb template by @makazeu in #6104
• Move manual dependencies in correct group to reduce conflicts by @RussKie in #6108
• Memory usage in CG Slice path could be 0 by @makazeu in #6110
• Add an option to log unsupported route by @amadeuszl in #6077
• Fix tree expansion in evaluation report by @shyamnamboodiripad in #6107
• Use just-built packages in the AI chat template by default by @MackinnonBuck in #6096
• Avoid multiple enumerations of messages in FunctionInvokingChatClient by @stephentoub in #6119
• Add AsChatClient for OpenAIResponseClient by @stephentoub in #6103
• [AI extensions] Add jsonSchemaIsStrict option to OpenAI options mapping by @danielwinkler in #6064
• pin actions by @danmoseley in #6123
• Expose failed Verify asserts as CI artifacts by @RussKie in #6129
• Create a directory for the AIChatWeb template if name is specified by @makazeu in #6122
• Add AIJsonSchemaCreateOptions.IncludeParameter filter by @stephentoub in #6125
• Update html-reporting package dependencies by @peterwald in #6115
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6131
• Fix AIFunctionFactory functions to fail for missing required parameters by @stephentoub in #6135
• Update changelogs for M.E.AI by @stephentoub in #6079
• Fix chat template test version scrubbing by @MackinnonBuck in #6140
• [Telemetry, Logging] Emit {OriginalFormat} as the last property of the log record by @iliar-turdushev in #6111
• HybridCache: richer detection for field-only types (ref STJ) by @mgravell in #6118
• [Http Resilience] Update instructions how to fix a compatibility issue with App Insights by @iliar-turdushev in #6147
• Fix indentation in chat template readme by @SteveSandersonMS in #6134
• In chat template, display preformatted/code snippet outputs sensibly by @SteveSandersonMS in #6137
• Use only a single TFM for M.E.AI.Eval.Reporting.Console by @peterwald in #6148
• Update algorithm spelling in /// by @gewarren in #6149
• Fix to show AI template config options in VS Code - Update framework symbol casing in chat template by @timheuer in #6117
• Extend M.E.AI.Evaluation.Console to support Azure Storage options by @peterwald in #6152
• Add license info to the Azure DevOps package by @peterwald in #6160
• Change AIFunction.InvokeAsync to accept AIFunctionArguments by @stephentoub in #6158
• Add some comments clarifying model choice for quality evaluators by @shyamnamboodiripad in #6165
• Fix build failing when running ./build.cmd -vs AI multiple times by @MackinnonBuck in #6171
• Update tsaoptions.json by @danmoseley in #6170
• Add MessageId to ChatMessage and ChatResponseUpdate by @SteveSandersonMS in #6172
• Enable custom argument binding with AIFunctionFactory by @stephentoub in #6162
• Enable JSON-schema based structured output by default by @SteveSandersonMS in #6159
• Simplify function calling error handling by @SteveSandersonMS in #6169
• Update to latest OpenAI, Azure.AI.OpenAI, and Azure.AI.Inference packages by @stephentoub in #6178
• Add custom result marshaling support to AIFunctionFactory by @stephentoub in #6175
• Fix dynamic config update for Random probabilistic sampler by @evgenyfedorov2 in #6187
• Unit test to show how function calling already permits resumption by @SteveSandersonMS in #6186
• Add "see also" links to conceptual docs by @gewarren in #6177
• Fix chat template input form submission on Firefox by @MackinnonBuck in #6188
• Support adding tags to scenarios by @shyamnamboodiripad in #6189
• Couple of minor reporting layout fixes by @shyamnamboodiripad in #6192
• A couple more minor eval report fixes by @shyamnamboodiripad in #6197
• Bump vite from 6.2.2 to 6.2.3 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6190
• Enable AIFunctionFactory.Create to use Activator{Utilities}.Create by @stephentoub in #6193
• Remove experimental attribute from TagNameAttribute by @dariusclay in #6200
• Fix load order of ProjectStaging and restrict package version validation to only official builds by @RussKie in #6041
• Strip default keyword in generated schemas when RequireAllProperties is specified. by @eiriktsarpalis in #6204
• Template: Remove if'ed code for ollama by @jozkee in #6205
• Remove non-AsXx surface area from M.E.AI.OpenAI/AzureAIInference by @stephentoub in #6138
• Add Aspire support to chat template by @MackinnonBuck in #6102
• Add trending views for both leaf-level scenario runs and aggregated scenario groups. by @peterwald in #6207
• Update AI chat template dependencies by @MackinnonBuck in #6220
• Fix execution order when reporting from Azure by @peterwald in #6217
• Bump vite from 6.2.3 to 6.2.4 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6216
• Mirror integration tests for OllamaSharp by @jozkee in #6209
• Update otel semantic convention version in comment by @stephentoub in #6227
• Update README with Logging sampling information by @evgenyfedorov2 in #6226
• Lower M.E.AI ...

v9.3.0

What's Changed

• Move ResourceUtilizationInstruments to Shared project by @amadeuszl in #5844
• Remove Tailwind and NPM dependency from chat template by @MackinnonBuck in #5846
• Branding updates for 9.3 by @joperezr in #5847
• Use an environment variable for configuring Ollama integration tests by @eiriktsarpalis in #5851
• Use unsafe relaxed escaping in AIJsonUtilities.DefaultOptions. by @eiriktsarpalis in #5850
• Move AIFunction parameter schematization from parameter level to function level. by @eiriktsarpalis in #5826
• Fix IChatClient integration tests after relaxed JSON update by @stephentoub in #5859
• Automate chat template JS dependency updates by @MackinnonBuck in #5853
• Address M.E.AI API feedback by @stephentoub in #5860
• Add AsChatClient for OpenAI's AssistantClient by @stephentoub in #5852
• Some docs fixes by @gewarren in #5861
• AI Templates - Fixes for Ollama and OpenAI scenarios by @jmatthiesen in #5855
• Update CODEOWNERS in preparation for upcoming MEAI.Evaluation libraries by @shyamnamboodiripad in #5872
• Update to {Azure.AI.}OpenAI 2.2.0-beta.1 by @stephentoub in #5869
• Rename IChatClient members and corresponding types by @stephentoub in #5870
• Fix up a few more stale references to Complete{Streaming}Async (mainly tests) by @stephentoub in #5876
• Update test app for OpenAI NativeAOT support by @stephentoub in #5877
• Make IEmbeddingGenerator contravariant on TInput by @stephentoub in #5879
• Fix a few more straggler "Complete" references by @stephentoub in #5881
• Add .npmrc file by @wtgodbe in #5878
• Merge internal changes by @RussKie in #5883
• Enable API compat validation by @RussKie in #5871
• Generalise how package version isn't stabilized for dev/preview stages by @RussKie in #5864
• Use UseZeroToOneRangeForMetrics in Health Checks by @evgenyfedorov2 in #5849
• Add service lifetime support to DI helpers. by @eiriktsarpalis in #5880
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #5890
• Add MEAI.Evaluation libraries by @shyamnamboodiripad in #5873
• Remove the ref int parameter from ChatConversationEvaluator.CanRenderAsync() by @peterwald in #5896
• Replace AIFunctionParameterMetadata with MethodInfo by @eiriktsarpalis in #5886
• Fix propagation of ChatThreadId in ToChatResponse{Async} by @stephentoub in #5899
• Couple of minor changes around doc comments by @shyamnamboodiripad in #5902
• Build evaluation report in CI and when enabled by @peterwald in #5903
• Rename AIFunctionFactoryOptions and make all properties nullable. by @eiriktsarpalis in #5906
• Update Azure.AI.Inference to 1.0.0-beta.3 by @stephentoub in #5904
• Add marker AITool for enabling code interpreters by @stephentoub in #5898
• Fix analyzer reference in AuditReports package by @dariusclay in #5894
• Pre-Build TypeScript packages before CI builds by @peterwald in #5907
• Reset code coverage baselines by @stephentoub in #5912
• Update CHANGELOGs for next release by @stephentoub in #5911
• Use Environment.WorkingSet in WindowsSnapshotProvider by @evgenyfedorov2 in #5874
• Tweak a comment in FunctionInvokingChatClient by @stephentoub in #5910
• Remove unnecessary compilations causing duplicate metric generators by @dariusclay in #5916
• Update baseline by @RussKie in #5918
• Make MetadataExtractor & MetricsReports in Microsoft.Extensions.AuditReports create directories [Same as ComplianceReport] by @IbrahimMNada in #5919
• Update template to newest M.E.AI version by @stephentoub in #5923
• Introduce type converter for DataClassification by @dariusclay in #5887
• Reinstate caching in schema generation by @eiriktsarpalis in #5908
• Add GetRequiredService extension for IChatClient/EmbeddingGenerator by @stephentoub in #5930
• Update M.E.AI READMEs by @stephentoub in #5925
• Use structured output for RTC evaluator by @shyamnamboodiripad in #5945
• Upgrade slngen to avoid crash with newer versions of VS by @peterwald in #5932
• Update coverage baseline by @shyamnamboodiripad in #5948
• Make sure npm build tasks happen reliably and only once. by @peterwald in #5926
• Address API feedback on M.E.AI by @stephentoub in #5954
• Template updates - Added an Overview/README, support of managed identity by @jmatthiesen in #5897
• Chat template updates following threat model review by @SteveSandersonMS in #5961
• Finalizing template name and sample data by @jmatthiesen in #5966
• Chat template static files layout update by @SteveSandersonMS in #5968
• Enable building and signing VSIX for extension by @peterwald in #5969
• Fix RTC evaluator by @shyamnamboodiripad in #5971
• Move Azure DevOps extension build until after the transport package build by @peterwald in #5973
• HybridCache: release to GA for 9.3 by @mgravell in #5931
• Automate chat template .NET dependency updates by @MackinnonBuck in #5946
• Explicitly specify VSIX file to sign to fix internal official build. by @peterwald in #5978
• Remove gitignore from AI chat template by @halter73 in #5972
• Addressing dogfooding feedback, adding GitHub Models support by @jmatthiesen in #5974
• Add Microsoft.Extensions.AI.Templates third party notices by @MackinnonBuck in #5949
• Move example PDFs into wwwroot/Data by @jeffhandley in #5982
• Remove unnecessary type from the source generator by @eiriktsarpalis in #5985
• HybridCache JSON serialization improvements by @mgravell in #5979
• Improve debugger display for ChatMessage by @stephentoub in #5988
• Address missing reference to Microsoft.Extensions.AI.OpenAI by @artl93 in #5984
• Add logging sampling by @evgenyfedorov2 in #5574
• Fix chat template content generation build flakiness by @MackinnonBuck in #5990
• Re-enabled forward main->dev merges by @RussKie in #5991
• Add context to getting started with using Azure AI Search by @artl93 in #5993
• Remove API key comment when using managed identity by @artl93 in #5996
• Touch-up to template readme.md by @artl93 in #6006
• Address vector dimension mismatch when using ollama with Azure AI Search by @artl93 in #6001
• Make AnonymousDelegatingEmbeddingGenerator internal by @stephentoub in #6000
• AI Template Preview 1 - ID cleanup & link to survey by @jmatthiesen in #5994
• Expose default cache key use by DistributedCachingCacheClient by @stephentoub in #6002
• Only show real citations by @SteveSandersonMS in #6012
• Add missing Maestro registrations by @RussKie in #5995
• Fix flow for new dependencies by @MackinnonBuck in #6017
• Ad...

v9.2.0

What's Changed

• Add FunctionInvokingChatClient.CurrentContext by @MackinnonBuck in #5786
• Fix schema generation for floating point types by @eiriktsarpalis in #5788
• Add an extension method for registering custom AIContent types by @eiriktsarpalis in #5789
• Fix XML comment by @gewarren in #5790
• Update HybridCacheOptions.cs (minor typo) by @jodydonetti in #5757
• Ensure Ollama streaming updates specify a CompletionId. by @eiriktsarpalis in #5795
• Update CHANGELOG.mds for 9.1.0-preview.1.25064.3 by @stephentoub in #5797
• Add Obsolete attribute on IResourceMonitor and its friends by @evgenyfedorov2 in #5774
• Make a number of improvements to the OpenAI serialization helpers. by @eiriktsarpalis in #5799
• Add note and sample for the case of using Azure OpenAI by @joperezr in #5802
• API that allows to remove all resilience handlers from the HTTP client by @rainsxng in #5801
• Update OpenTelemtryChatClient/EmbeddingGenerator for 1.30 by @stephentoub in #5815
• Metadata reports generator (Issue #3999) by @IbrahimMNada in #5531
• Ensure the Ollama clients validate HTTP status codes. by @eiriktsarpalis in #5821
• Fix poor wording in CA2253 error message by @evgenyfedorov2 in #5822
• Inheritdoc fixes by @gewarren in #5823
• Remove ImageContent and AudioContent by @MackinnonBuck in #5814
• Make HealthChecks.ResourceUtilization use observable instruments by @evgenyfedorov2 in #5798
• Resource Monitoring metrics on Windows - remove multiplication by 100 by @evgenyfedorov2 in #5473
• Initial chat template by @SteveSandersonMS in #5837
• The tested logic uses invariant culture, but unit tests assert against current culture by @Demo30 in #5841
• Fix links in CONTRIBUTING.md by @Demo30 in #5840
• Chat template CR feedback by @SteveSandersonMS in #5845
• Chat template: PDF citation viewer by @SteveSandersonMS in #5843
• Small fixes for chat template by @MackinnonBuck in #5839
• HybridCache : implement the tag expiration feature by @mgravell in #5785

New Contributors

• @IbrahimMNada made their first contribution in #5531
• @Demo30 made their first contribution in #5841

Full Changelog: v9.1.0...v9.2.0

.NET Extensions 9.1.0

9.1.0 packages are all pushed now to NuGet.org!

What's Changed

• Add NativeAOT testapp project for M.E.AI by @stephentoub in #5573
• Add changelogs for M.E.AI projects by @stephentoub in #5577
• Explicitly reference System.Memory.Data in OpenAI/AzureAIInference projects by @stephentoub in #5576
• Fix AzureAIInferenceEmbeddingGenerator to respect EmbeddingGenerationOptions.Dimensions by @stephentoub in #5575
• Merge ResourceMonitoringOptions.Linux.cs into ResourceMonitoringOptions.cs by @makazeu in #5580
• Fix exception when generating boolean schemas by @eiriktsarpalis in #5585
• Add ImageContent integration test by @stephentoub in #5586
• Add ChatOptions.Seed by @stephentoub in #5587
• Lower AIJsonUtilities to STJv8 and move to Abstractions library. by @eiriktsarpalis in #5582
• Plug JsonSchemaExporter test data to the AIJsonUtilities tests by @eiriktsarpalis in #5590
• Improve JsonSchemaExporter trimmer safety. by @eiriktsarpalis in #5591
• Improve AdditionalPropertiesDictionary by @stephentoub in #5593
• Add UseEmbeddingGenerationOptions by @stephentoub in #5594
• HybridCache stability and logging improvements by @mgravell in #5467
• Assign ownership by @RussKie in #5600
• HybridCache: don't log cancellation as failure event by @mgravell in #5601
• Set DisableNETStandardCompatErrors for M.E.AI projects by @stephentoub in #5603
• HttpRouteParser: Handle catch-all parameters by @dariusclay in #5604
• Rework UseChatOptions as ConfigureOptions by @stephentoub in #5606
• Make IChatClient/IEmbeddingGenerator.GetService non-generic by @stephentoub in #5608
• Add logging/activities to FunctionInvokingChatClient by @stephentoub in #5596
• Update M.E.AI CHANGELOG.mds by @stephentoub in #5609
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #5610
• Add ToChatCompletion{Async} methods for combining StreamingChatCompletionUpdates by @stephentoub in #5605
• Docs improvements by @gewarren in #5613
• Use ToChatCompletion in OpenTelemetryChatClient by @stephentoub in #5614
• Use ToChatCompletion / ToStreamingChatCompletionUpdates in CachingChatClient by @stephentoub in #5616
• Add DebuggerDisplay for DataContent by @stephentoub in #5618
• Tweak ChatMessage/StreamingChatCompletionUpdate.ToString by @stephentoub in #5617
• Expose options for making schema generation conformant with the subset accepted by OpenAI. by @eiriktsarpalis in #5619
• Cache current process object to avoid performance hit by @haipz in #5597
• Fix namespace for IServiceCollection extensions by @stephentoub in #5620
• Fix linker warning. by @eiriktsarpalis in #5627
• Merge internal changes by @joperezr in #5631
• Publish the AotCompatibility.TestApp project as part of PR validation by @eerhardt in #5622
• Merge branch release/9.0 into main by @joperezr in #5632
• Replace STJ boilerplate in the leaf clients with AIJsonUtilities calls. by @eiriktsarpalis in #5630
• Rework cache key handling in caching client / generator by @stephentoub in #5641
• Docs updates by @gewarren in #5643
• Change ChatClientBuilder to register singletons and support lambda-less chaining by @SteveSandersonMS in #5642
• [main] Update dependencies from dotnet/aspnetcore by @dotnet-maestro in #5645
• EmbeddingGeneratorBuilder API updates by @SteveSandersonMS in #5647
• Update WaiterRemovedAfterDispose to check waitersCount first by @amadeuszl in #5646
• Allow logging of body without modifying the actual response by @dariusclay in #5628
• Make ActivityBaggageLogScopeWrapper implements IEnumerable<KeyValuePair<string, object?>> by @NatMarchand in #5589
• Add a [DebuggerDisplay] to GeneratedEmbeddings by @stephentoub in #5657
• Annotate private DebuggerDisplay props as DebuggerBrowsableState.Never by @stephentoub in #5656
• Fix M.E.AI argument tests to validate argument names by @stephentoub in #5653
• Remove duplicate GetCacheKey methods by @stephentoub in #5651
• Augment XML comments for AIFunctionFactory.Create by @stephentoub in #5658
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #5662
• Add AsBuilder extensions for IChatClient and IEmbeddingGenerator by @stephentoub in #5652
• Reduce a bit of LINQ in M.E.AI by @stephentoub in #5663
• Reverse order of services/inner in Use methods by @stephentoub in #5664
• Add anonymous chat clients / embedding generators by @stephentoub in #5650
• Update documentation SynchronizationContext in FakeTimeProvider by @amadeuszl in #5665
• Backport JsonSchemaExporter bugfix. by @eiriktsarpalis in #5671
• Add OpenAIRealtimeExtensions with ToConversationFunctionTool by @SteveSandersonMS in #5666
• Tweak CachingHelpers.GetCacheKey to clean up better on failure by @stephentoub in #5654
• Ensure non-streaming usage data from function calling is in history by @stephentoub in #5676
• Fix a few FunctionInvocationChatClient streaming issues by @stephentoub in #5680
• Change UseLogging to accept an ILoggerFactory instead of ILogger by @stephentoub in #5682
• Expose a schema transformer on AIJsonSchemaCreateOptions. by @eiriktsarpalis in #5677
• Update M.E.AI CHANGELOG.md for latest bits by @stephentoub in #5684
• [main] Update dependencies from dotnet/aspnetcore by @dotnet-maestro in #5678
• Add API allowing to disable retries for a given list of HTTP methods by @iliar-turdushev in #5634
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #5693
• Update M.E.AI code coverage mins from 0 by @stephentoub in #5698
• [main] Update dependencies from dotnet/aspnetcore by @dotnet-maestro in #5702
• Improve FakeTimeProvider documentation, remove redundant tests by @amadeuszl in #5683
• [main] Update dependencies from dotnet/aspnetcore by @dotnet-maestro in #5703
• For AI integration tests, use config including user secrets by @SteveSandersonMS in #5706
• Fix handling of text-only user messages in AzureAIInferenceChatClient by @stephentoub in #5714
• Make UseLogging a nop when NullLoggerFactory is used by @stephentoub in #5717
• Fix streaming function calling by @SteveSandersonMS in #5718
• Removes Experimental attribute from ResilienceHandler class by @iliar-turdushev in #5670
• Usage aggregation via Dictionary<string, long> by @SteveSandersonMS in #5709
• Update otel chat client / embedding generator for 1.29 draft of the spec by @stephentoub in #5712
• Additional tests to the logging generator by @rainsxng in #5704
• Update OpenAI dependency to 2.1.0 by @stephentoub in #5725
• Fix build by @RussKie in #5728
• Add a few missing options to OpenAIChatclient.ToOpenAIOptions by @stephentoub in #5727
• Ollama support for stre...

.NET Extensions 9.0.0

9.0.0 are all pushed now to NuGet.org!

What's Changed

• Adding CI support for dev branch by @joperezr in #4704
• Update SDK by @captainsafia in #4743
• Update SDK version by @sebastienros in #4760
• Enable AOT compatibility for all libraries by @eerhardt in #4625
• rev SDK to current nightly (build-ops) by @mgravell in #4786
• Correct build transitive targets location by @RussKie in #4773
• Update SDK to 23608.3 by @amcasey in #4800
• Add workflow for automatic SDK updates by @wtgodbe in #4886
• Ensure we emit preview.1 versions as prerelease label. by @joperezr in #4909
• Branding updates for 9.0 preview 2 by @joperezr in #4910
• Update Microsoft.AspNetCore.Diagnostics.Middleware.csproj by @RussKie in #4938
• Use 9.0 preview 3 shipping versions by @joperezr in #5094
• Migrate HybridCache from aspnetcore to extensions by @mgravell in #5391
• Fix CVE-2024-21319 by @RussKie in #5418
• HybridCache: ensure that Size is always specified in L1 by @mgravell in #5420
• Merge internal changes from Preview 9 release by @joperezr in #5479
• Improve registration of IDistributedCache in READMEs by @stephentoub in #5480
• Flip default on FunctionInvokingChatClient.ConcurrentInvocation by @stephentoub in #5485
• Remove x64 hardcoding from global.json runtimes by @eiriktsarpalis in #5488
• Fix AIFunctionFactory support for AOT. by @eiriktsarpalis in #5494
• Mark the FunctionCall/ResultContent.Exception properties as [JsonIgnore] by @stephentoub in #5492
• First cut of code ownership by @RussKie in #5486
• Doc updates to HybridCacheOptions by @gewarren in #5493
• Set WriteIndented=true for M.E.AI logging / telemetry / etc. by @stephentoub in #5497
• Sanitize structured output schema type name to satisfy restrictions by @kzu in #5504
• Remove unnecessary suppression in AIFunctionFactory by @eerhardt in #5505
• Allowing tags to start with _ by @carolineRe13 in #5478
• Use the same JsonSerializerOptions default in all locations. by @eiriktsarpalis in #5507
• Use the logging generator in LoggingChatClient / LoggingEmbeddingGenerator by @stephentoub in #5508
• Avoid use of FormattableString when logging by @stephentoub in #5503
• Add comment about use of hashing in CachingHelpers by @stephentoub in #5509
• Build fix - remove unnecessary 'using' by @SteveSandersonMS in #5512
• Rework the AIFunctionFactory APIs and remove redundant overloads following removal of trimmer annotations. by @eiriktsarpalis in #5510
• Improve CachingChatClient's coalescing of streaming updates by @stephentoub in #5514
• Add thread-safety comments about M.E.AI middleware components by @stephentoub in #5515
• Update README with rate limiting example by @stephentoub in #5519
• Add AdditionalPropertiesDictionary.TryGetValue by @stephentoub in #5528
• Expose an AIJsonUtilities class in M.E.AI and lower M.E.AI.Abstractions to STJv8 by @eiriktsarpalis in #5513
• Address PR feedback from #5513 by @eiriktsarpalis in #5533
• Update UseOpenTelemetry for latest genai spec updates by @stephentoub in #5532
• Use 8.0 era dependencies for non net9.0 TFMs by @joperezr in #5470
• Update the meter names of NetworkMetrics to match other meters in ResourceMonitoring by @makazeu in #5541
• Fix typo in ChatCompletions comment by @stephentoub in #5545
• Remove unnecessary ctors from FunctionResultContent by @stephentoub in #5536
• Make GenerateAsync extension just return the embedding by @stephentoub in #5543
• Remove AIContent.ModelId, add StreamingChatCompletionUpdate.ModelId by @stephentoub in #5535
• Fix embedding integration test after telemetry updates by @stephentoub in #5555
• Lower M.E.AI.Ollama STJ dependency back to 8 by @stephentoub in #5554
• Add missing [JsonIgnore] on ChatCompletion.Message by @stephentoub in #5552
• Add OllamaChatClient ctor with string endpoint by @stephentoub in #5553
• Fix a few issues in IChatClient implementations by @stephentoub in #5549
• Script to generate weekly digest by @RussKie in #5550
• Improve EmbeddingGeneratorExtensions by @stephentoub in #5551
• Update .gitattributes by @RussKie in #5565
• Fix cloning of ChatOptions.TopK by @stephentoub in #5564
• Add string constructor to OllamaEmbeddingGenerator by @stephentoub in #5562
• Remove some defunct lazy init from chat clients by @stephentoub in #5561
• Add EmbeddingGeneratorOptions.Dimensions by @stephentoub in #5563
• Structured output improvements (continuation of PR 5522) by @SteveSandersonMS in #5560
• Work around fixed bug in System.Memory.Data by @stephentoub in #5569
• Update M.E.AI.AzureAIInference for its beta2 release by @stephentoub in #5558
• [release/9.0] Merging changes from main into release branch for November release by @joperezr in #5602

New Contributors

• @captainsafia made their first contribution in #4743
• @kzu made their first contribution in #5504
• @carolineRe13 made their first contribution in #5478

Full Changelog: v8.10.0...v9.0.0