Release v3.2.3

What's Changed

This release adds full support for OpenAI Assistants.

• Adjusting FeatureMatrix with supported features
• adding Body to the httpException callback
• refinining file_search
• Added CodeInterpreter, added doc and converted ToolChoiceType to frozen dictionary
• fix
• formatting
• optimize assistants streaming
• adding colors and adding demo for streaming a file extraction assistant
• adding TornadoTest Attribute to streaming assistant
• Streaming of assistatants prototype
• add mistral to feature matrix
• adding multiple entries of function calling to test out deserialization
• Update project versions to v3.2.2
• changing serialization so that it does not cause stack overflow
• Adding submit tool endpoint
• Thread rename & other refactorings
• Converting to enums and mappint ToolOutput
• clean up message roles
• formatting
• add a few ctors, format
• formatting&enumartion of string types
• enumarizing TruncationStrategy type
• Fixing MessageAnnotation serialization issues and adding demo case for extracing info from a file
• correcting serialization of enum and adding rest of the RunSteps tests
• refining mapping of RunStep
• moving all json propreties to Newtonsoft
• adding demo test cases for Run endpoint
• adapting to new Torando tests
• merge conflict
• Refactor message handling and annotations for threads.
• adding mapping for Message
• adding support for Threads CRUD

Updated Projects

LlmTornado.Tests.csproj -> 0.0.1
LlmTornado.Demo.csproj -> 0.0.1
LlmTornado.csproj -> 3.2.3

Release v3.2.2

What's Changed

This release fixes minor inconsistencies in the Files API.

• add proxy prop to message part
• fix upload endpoint consistency
• Update project versions to v3.2.1

Updated Projects

LlmTornado.csproj -> 3.2.2

Release v3.2.1

What's Changed

This release adds support for Gemini 2.0 models.

• Update FeatureMatrix.md
• gemini-2.0-flash-001, gemini-2.0-pro-exp-02-05, gemini-2.0-flash-lite-preview-02-05
• update csproj
• Update project versions to v3.2.0

Updated Projects

LlmTornado.csproj -> 3.2.1

Release v3.2.0

What's Changed

This release adds support for using Google's Caching with Gemini API.

• add google strict function call test
• google: fix strict function calls in conjunction with streaming
• Update FeatureMatrix.md
• Update FeatureMatrix.md
• Update FeatureMatrix.md
• Update FeatureMatrix.md
• fix edge case in google stream processing
• fix google streaming functions decoding
• google: support caching in chat, improve usage
• google: cachedContents.delete
• google: cachedContents.patch
• google: cachedContents.get
• google: cachedContents.list
• rework tests infrastructure
• google: cachedContents.create
• Update FeatureMatrix.md
• swap chat event handlers to valuetasks
• Update project versions to v3.1.35

Updated Projects

LlmTornado.Tests.csproj -> 0.1.0
LlmTornado.Demo.csproj -> 0.1.0
LlmTornado.csproj -> 3.2.0

Release v3.1.35

What's Changed

• google: support fileData message parts
• Update FeatureMatrix.md
• Update README.md
• Update FeatureMatrix.md
• Update FeatureMatrix.md
• add feature matrix
• google: files.delete
• google: list all files, oai: support query in list all files
• google: files.upload, files.get
• Update project versions to v3.1.34

Updated Projects

LlmTornado.Tests.csproj -> 0.0.1
LlmTornado.Demo.csproj -> 0.0.1
LlmTornado.csproj -> 3.1.35

Release v3.1.34

What's Changed

• fix
• oai: o3-mini-2025-01-31, o3-mini
• include chatmodel usage in demo
• adding rest of the test cases for Assistant
• clearing unused usings
• naming fix & using ChatModel other than string
• code formatting
• removing usings
• fixing modify endpoint (openai api rejects any fields it does not recognize)
• resolvin rebase conflicts
• adding test cases for assistants
• Refactor response formats and make assistant properties mutable
• Refactor and improve documentation in ResponseFormat and ToolResources
• adding assistant tool converter and adding ResponseFormat with converter
• adjusting request fields and xml doc
• decoupling AssistantTool from Tool
• adding some assistant endpoint related changes
• code format
• adding support for http strict
• extract url builder, code formatting
• Update project versions to v3.1.33
• adding QueryParams to the http request

Updated Projects

LlmTornado.Demo.csproj -> 0.0.1
LlmTornado.csproj -> 3.1.34

Release v3.1.33

What's Changed

• anthropic: support caching
• improve vector stores, fix potentially not disposing httpresult
• gemini-2.0-flash-thinking-exp, gemini-2.0-flash-exp
• adding test case for custom chunking strategy
• Update README.md
• Update README.md
• fix
• Update project versions to v3.1.32
• minor changes
• adding self-cleaning test-cases
• fixing issues from PR review
• fixing issues from PR review
• fixing xml doc and pointing created_at to created property in base result class
• adding rest of the endpoints for VectorStoreFile
• fixing json convertor
• adding VectorStoreFile object and converter for chunking strategy
• adding vectore store to the baes API + changing json tag
• adding base for VectoreStore endpoint
• using Path.Join to file navigations rather Window's \

Updated Projects

LlmTornado.Demo.csproj -> 0.0.1
LlmTornado.csproj -> 3.1.33

Release v3.1.32

What's Changed

• add ollama streaming demo
• add ollama demo
• Update dotnet.yml
• Update dotnet.yml
• Update dotnet.yml
• fix
• exclude forks from status checking
• fix ci
• Pruned .gitignore
• Update .gitignore
• Update project versions to v3.1.31

Updated Projects

LlmTornado.Demo.csproj -> 0.0.1
LlmTornado.csproj -> 3.1.32

Release v3.1.31

What's Changed

• add release script
• fix
• fix
• setup ci
• llama-3.3-70b-versatile, llama-3.1-8b-instant, llama-guard-3-8b

Updated Projects

LlmTornado.csproj -> 3.1.31
LlmTornado.Demo.csproj -> 0.0.1

3.1.30

Features

• SSE implementation for OpenAI and Anthropic is reworked, fixing some rare issues with mid-response tool calls.