Skip to content

Releases: epam/ai-dial-adapter-vertexai

0.17.2

20 Feb 12:49
Compare
Choose a tag to compare

Fixes

  • add stable alias for Gemini 2.0 Flash model (gemini-2.0-flash-001) (#190) (#194)

0.17.1

14 Feb 13:58
Compare
Choose a tag to compare

Features

  • add Gemini 2.0 Pro and Gemini 2.0 Flash Lite models (#185) (#188)

Fixes

  • improve error messages and document limits validation for Gemini models (#187) (#188)

Other

  • bump cryptography from 43.0.1 to 44.0.1 (#186) (#188)

0.17.0

06 Feb 14:23
Compare
Choose a tag to compare

Features

  • support of Claude 3 models (#179)
  • support multiple regions with a single vertexai deployment (#179)
  • support response_format and seed for Gemini models (#181, #183)
  • add gemini-2.0-flash-thinking-exp-01-21 model (#184)

Fixes

  • remove gemini-exp-1206 and gemini-2.0-flash-thinking-exp-1219 models following their deprecation in Vertex AI (#184)

Other

  • add pytest-html plugin (#182)
  • bump epam/ai-dial-ci from 1.11.0 to 1.11.1 (#180)

0.16.0

24 Jan 10:55
Compare
Choose a tag to compare

Features

  • Add new Gemini 2.0 models (#172)

Fixes

  • add model field to chat completion responses (#174)

Other

  • Ignore pydantic v2 warnings (#178)
  • bump epam/ai-dial-ci from 1.10.2 to 1.11.0 (#173)
  • fix model id in readme (#175)

0.15.0

15 Jan 17:46
Compare
Choose a tag to compare

Fixes

  • gemini: improve error message on empty user messages (#164)
  • gemini: fix bug in FinishReasonOtherError constructor (#161)

Other

  • pin poetry to 1.8.5 (#167)
  • refactor adapter to facilitate follow-up Gemini 2.0 integration (#170)
  • bump pydantic from 1.10.13 to 2.10.4 (#165)
  • bump epam/ai-dial-ci from 1.10.0 to 1.10.2 (#163)
  • bump virtualenv from 20.24.5 to 20.26.6 (#171)

0.14.1

20 Dec 10:58
Compare
Choose a tag to compare

Fixes

  • Gemini: fixed bug in a finish reason handler (#161) (#162)

0.14.0

18 Dec 17:30
Compare
Choose a tag to compare

Features

  • support streaming with multiple candidates (#158)

Other

  • add integration tests for multi-input embeddings (#159)
  • pin Docker image to alpine-3.20 (#160)
  • bump aidial-sdk from 0.15.0 to 0.16.0 (#156)

0.13.0

20 Nov 13:55
Compare
Choose a tag to compare

Features

  • Add Google Search Grounding static tool (#147)
  • Calculate Google Search Grounding price in tokens, allow configuration fo Search usage (#153)

Fixes

  • Gemini: reporting safety error properly (#149)
  • fixed bug in truncate prompt (#143)
  • utilize reference url and markdown in attachments for Grounding (#151)

Other

  • bump aidial-sdk from 0.14.0 to 0.15.0 (#154)
  • bump aiohttp from 3.10.2 to 3.10.11 (#152)
  • bump epam/ai-dial-ci from 1.9.3 to 1.9.4 (#145)
  • bump epam/ai-dial-ci from 1.9.4 to 1.10.0 (#155)
  • cleanup untagged images (#146)
  • improved integration tests (#124)
  • migrated from Ubuntu (ubuntu:23.10) to the Alpine image (python:3.11-alpine) (#113)

0.12.1

24 Oct 09:04
Compare
Choose a tag to compare

Fixes

  • fixed bug in truncate prompt (#143) (#144)

0.12.0

23 Oct 15:54
Compare
Choose a tag to compare

Features

  • Gemini: supported prompt truncation and request.max_prompt_tokens parameter (#141, #139)
  • Gemini: supported system_instruction and tools in token counting (#137)
  • supported content parts in all models (#133)
  • added Docker healthcheck (#120)

Other

  • bump epam/ai-dial-ci from 1.9.1 to 1.9.2 (#138)
  • bump epam/ai-dial-ci from 1.9.2 to 1.9.3 (#142)
  • bump starlette from 0.36.3 to 0.40.0; fastapi from 0.109.2 to 0.115.2 (#140)
  • fixed README table formatting (#135)