Skip to content

Releases: epam/ai-dial-adapter-bedrock

0.7.0

05 Mar 15:17
Compare
Choose a tag to compare

Fixes

  • migrated to sdk==0.7.0: discarded_messages response field turned into a list of indices (#72)

Other

  • migrated to openai>=1.0 and langchain-openai libs (#71)

0.6.0

13 Feb 13:19
Compare
Choose a tag to compare

Features

  • Claude V2.1: supported array and enum types in the tools schema (#61)

Fixes

  • file metadata definition adjusted to follow DIAL Core 0.7.0 API (#60)
  • Claude V2.1: the completion is streamed in a single chunk when tools are used (#62)

Other

  • GitHub workflow update (#64)
  • bump aidial-sdk from 0.6.0 to 0.6.2 (#66)
  • bump aiohttp from 3.9.0 to 3.9.2 (#63)
  • bump jinja2 from 3.1.2 to 3.1.3 (#53)

0.5.0

15 Jan 18:18
Compare
Choose a tag to compare

Features:

  • added OTLP export (#52)
  • configure service name via env var (#55)

Fixes:

  • avoid generating empty content for Stability (#56)
  • capitalized name of stage with image (#51)
  • fixed stability adapter (#48)
  • propagating per request key (#57)

Other:

  • chore: Setup excludes for OSS Review Toolkit (#50)

0.4.1

21 Dec 11:39
Compare
Choose a tag to compare

Fixes:

  • fixed stability adapter (#48) (#49)

0.4.0

20 Dec 15:17
Compare
Choose a tag to compare

Features:

  • supported tools/functions in claude 2.1 (#43)

0.3.0

20 Dec 14:54
Compare
Choose a tag to compare

Features:

  • added llama 2 and cohere models (#30) (#35)
  • added pseudo chat config; added wrapper for Bedrock client (#36)
  • migrated to new auth method (#44)
  • saving stability artifacts to DIAL file storage (#34)
  • supported turn-based dialogue partitioning for llama model (#39)

Fixes:

  • added missing dot before file extension (#47)
  • don't use file storage by default; renamed env vars (#37)
  • fixed double extension bug (#46)

Other:

  • chore: add e2e tests trigger (#28)
  • chore: bump aiohttp from 3.8.6 to 3.9.0 (#32)

0.2.0

14 Nov 16:23
Compare
Choose a tag to compare

Features:

  • added integration tests for max_tokens and stop sequence parameters (#23)
  • allowed empty messages in each language model (#23)
  • supported history truncation via max_prompt_tokens and discarded_messages parameters (#23)
  • supported streaming for Titan and Claude (#23)

Fixes:

  • used number of bytes as token count estimator for AI21 and AWS Titan (#23)
  • fixed AI21 temperature setting (#23)
  • removed Assistant prefix occasionally generated by Titan (#23)

0.1.2

02 Nov 16:18
Compare
Choose a tag to compare

Features:

  • add slash commands dispatch (#11) (#12)

0.1.1

20 Oct 11:11
Compare
Choose a tag to compare

Other:

  • Merge pull request #7 from epam/integration-0.1.1
  • build(deps): bump urllib3 from 1.26.17 to 1.26.18 (#5)
  • build(deps-dev): bump langchain from 0.0.310 to 0.0.312 (#4)
  • chore: update workflow references (#6)

0.1.0

12 Oct 10:09
Compare
Choose a tag to compare

Features:

  • initial commit

Other:

  • [skip ci] Update version
  • chore: trigger ci