v1.18.9

What's Changed

• refactor: serverless context by @venjiang in #822
• feat: client error handler accept reconnect error by @woorui in #823

Full Changelog: v1.18.8...v1.18.9

v1.18.8

What's Changed

• feat: completions api flush after first calling by @woorui in #807
• fix: improve GetChatCompletions by @woorui in #809
• feat: client cannot write tag that within reserved range by @woorui in #815
• fix: test-prompt command error by @venjiang in #816
• feat: add transID for ai function by @woorui in #817

Full Changelog: v1.18.7...v1.18.8

v1.18.7

What's Changed

• test: add unit test for ai package by @fanweixiao in #769
• refactor: cli test-prompt subcommand by @venjiang in #772
• fix: client close conn by @woorui in #773
• add tests for api_server and provider by @fanweixiao in #770
• fix: the yomo test-prompt command error when running multiple sfn instances by @venjiang in #774
• test: fix unittest by @woorui in #780
• fix: ctrl+c cannot exit client if the client is reconnecting by @woorui in #787
• refactor: llm api by @venjiang in #781
• fix: fix panic if cannot find a conn form the connector by @woorui in #797
• refactor: use openai pkg & support chat in stream by @woorui in #791
• feat: connector can be customized in NewZipper() by @woorui in #801
• fix: service system prompt init as an empty string by @woorui in #804
• refactor: handshake with ai function definition by @woorui in #798
• refactor: cli by @venjiang in #802

Full Changelog: v1.18.6...v1.18.7

v1.18.6

What's Changed

• feat(llm): add Cloudflare OpenAI Gateway support by @fanweixiao in #764
• feat(llm): remove the no function call error by @venjiang in #767
• fix(llm): ai service race by @fanweixiao in #768
• fix(cli): support windows by @venjiang in #766
• feat(cli): impl wasm set wanted target by @woorui in #718
• chore(deps): bump github.com/quic-go/quic-go from 0.41.0 to 0.42.0 by @dependabot in #756

Full Changelog: v1.18.5...v1.18.6

v1.18.5

What's Changed

• feat(function-calling): support multi-turn chat completion request for OpenAI by @fanweixiao in #758
• feat(cli): add yomo test-prompt command to dry-run your function calling test easily by @venjiang in #760
• wip: reuse openai chat completion request and models by @fanweixiao in #755
• feat/sfn: add ctx.Metadata("key") by @woorui in #754

Full Changelog: v1.18.4...v1.18.5

v1.18.4

What's Changed

• feat: add Cloudflare AI Gateway for Azure OpenAI provider by @fanweixiao in #748
• chore: bump to go1.21 by @woorui in #747

Full Changelog: v1.18.3...v1.18.4

v1.18.3

What's Changed

• refactor: split provider and register by @woorui in #743

Full Changelog: v1.18.2...v1.18.3

v1.18.2

What's Changed

• feat: add Google Gemini API provider for LLM Function Calling (#2) by @fanweixiao in #742
• refactor: separate the logic of distributed tracing by @woorui in #736

Full Changelog: v1.18.1...v1.18.2

v1.18.1

What's Changed

• feat: add OpenAI provider for LLM Function Calling by @venjiang in #735
• refactor: improve azure openai provider configuration follows azure-sdk by @fanweixiao in #734

Full Changelog: v1.18.0...v1.18.1

v1.18.0

What's Changed

• feat: add LLM function calling support, currently support Azure OpenAI by @venjiang @fanweixiao in #724
• feat: allocating connection id on server side by @woorui in #725

Full Changelog: v1.17.5...v1.18.0