Releases: yomorun/yomo
Releases · yomorun/yomo
v1.18.14
v1.18.13
What's Changed
- feat(ai-bridge): support Github Models by @fanweixiao in #885
- chore: developers can docker run ai bridge by @woorui in #855
Full Changelog: v1.18.12...v1.18.13
v1.8.12
What's Changed
- feat: Baselime as default OpenTracing provider to analysis TimeToFirstToken (TTFT) and TimeBetweenTokens (TBT) by @woorui in #872
BASELIME_API_KEY=xxxx yomo serve -c config.yaml
for observability.
Full Changelog: v1.18.11...v1.18.12
v1.18.11
What's Changed
- feat(llm-bridge): add gemini provider by @woorui in #863
- refactor: use goroutinue instead of mutex to sync messages by @woorui in #842
- feat(llm-sfn): log function calling jsonschema when sfn start by @woorui in #847
- feat(log): 🌈 tinted console logs by @woorui in #851
- feat: function definition supports enum by @woorui in #848
- fix: return an error if data cannot be unmarshal as FunctionCall by @woorui in #849
- fix: error raised when function scheme
required
is null by @venjiang in #860
Full Changelog: v1.18.10...v1.18.11
v1.18.10
What's Changed
- feat(llm-bridge): add ollama provider with mistral model support by @wujunzhuo in #834
- fix(cli): serverless ctx mock pkg move bug by @woorui in #827
- fix(cli): yomo run sfn exit if init error by @woorui in #828
- chore(deps): bump github.com/sashabaranov/go-openai from 1.24.0 to 1.24.1 by @dependabot in #826
- fix: response should include token usage from previous function calls by @woorui in #830
- fix: ai bridge run sfn timeout after 60s by @woorui in #829
- fix: example by @venjiang in #838
- perf: optimize yomo build speed by @venjiang in #840
- feat(ai-bridge): handle llm-sfn return nothing or multiple results returned by @woorui in #833
- feat: improve warning log if llm-sfn not return anything by @woorui in #841
Full Changelog: v1.18.9...v1.18.10
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