0.8.0

Features

• Support Trino data source. by @himanshu634 in #535
• Support metadata into Langfuse tracking. by @paopa in #566
• Optimize qdrant for multi-users setting. by @cyyeh in #558
• Support sub-pipeline evaluation. by @paopa in #582
• Optional attribute user_id for Langfuse metadata. by @paopa in #625
• Question-based accuracy metric. by @paopa in #585
• Allow multi-language support. by @cyyeh in #646

Fixes and Chores

• Disable passing embedding model dimension to embedders. by @cyyeh in #579
• Error handling for accuracy metric to avoid the select all query failure. by @paopa in #596
• Expand the timeout and move the waiting check mechanism when force deploying. by @paopa in #601
• UI layout is broken when selecting a sample dataset. by @fredalai in #609
• Correct the wrong version in docker image. by @paopa in #639
• Update dry run API parameter. by @cyyeh in #584
• Refine the metadata and output in Langfuse. by @cyyeh in #580
• Add script for MDL properties preparation. by @cyyeh in #589
• Support a environment variable to trigger force deploying. by @cyyeh in #592
• Handle add_quotes error. by @cyyeh in #595
• Disable the force deploy option in the launcher. by @cyyeh in #600
• Refine MDL preparation script. by @imAsterSun in #602
• Remove wren UI service form the dependencies list when AI service starting. by @cyyeh in #608
• Fix wrong ask candidate number. by @cyyeh in #610
• Correct the searching behavior in historical question pipeline. by @cyyeh in #611
• Update the behavior of calculating accuracy metric. by @cyyeh in #614
• Improve SQL generation. by @cyyeh in #618
• Improve eval data preparation. by @cyyeh in #621
• Retrieval improvement. by @cyyeh in #599
• Fix document meta. by @cyyeh in #637
• Fix view candidate indexing and retrieval. by @cyyeh in #635
• Fix filters logic for Qdrant. by @cyyeh in #638
• Rename a few methods for better representation in Langfuse. by @cyyeh in #643
• Improve SQL generation prompt. by @cyyeh in #645
• Refine multi-language prompt. by @cyyeh in #648

Security

Update dependency version for security issue in #626, #628, #612, #567, #591, #590, #594, #615

Maintenance

• Update README.md by @chilijung in #619, #593, #598
• Add PR title validatior by @paopa in #560
• Adjust dependable commit message and labels by @paopa in #604
• Update doc links by @fredalai in #634

Full Changelog: 0.7.5...0.8.0

0.8.0-rc.3

What's Changed

• chore(wren-ai-service): refine multi-language prompt by @cyyeh in #648
• release 0.8.0-rc.3 by @onlyjackfrost in #649

Full Changelog: 0.8.0-rc.2...0.8.0-rc.3

0.8.0-rc.2

What's Changed

• chore(wren-ai-service): update doc links by @fredalai in #634
• chore(wren-ai-service): fix document meta by @cyyeh in #637
• chore(wren-ai-service): fix view candidate indexing and retrieval by @cyyeh in #635
• chore(wren-ai-service): fix bugs by @cyyeh in #638
• fix(wren-ai-service): correct the wrong version in docker image by @paopa in #639
• chore(wren-ai-service): minor refactor by @cyyeh in #643
• chore(wren-ai-service): improve sql generation prompt by @cyyeh in #645
• feat(wren-ai-service): allow multi-language by @cyyeh in #646

Full Changelog: 0.8.0-rc.1...0.8.0-rc.2

0.8.0-rc.1

Full Changelog: 0.7.5...0.8.0-rc.1

What's Changed

• feat(wren-ai-service): add metadata into Langfuse trace by @paopa in #566
• chore(wren-ai-service): pr title validation by @paopa in #560
• feat(wren-ai-service): optimize qdrant for multi users setting by @cyyeh in #558
• fix(wren-ai-service): disable pass embedding model dim to embedders by @cyyeh in #579
• chore(deps): bump github.com/docker/docker from 26.0.2+incompatible to 26.1.4+incompatible in /wren-launcher in the go_modules group across 1 directory by @dependabot in #567
• feat(wren-ai-service): support sub-pipeline evaluation by @paopa in #582
• chore(wren-ai-service): update dry run api parameter by @cyyeh in #584
• chore(wren-ai-service): refine langfuse by @cyyeh in #580
• feat(wren-ai-service): question based accuracy metric by @paopa in #585
• chore(deps): bump github.com/docker/docker from 26.1.4+incompatible to 26.1.5+incompatible in /wren-launcher in the go_modules group across 1 directory by @dependabot in #591
• chore(wren-ai-service): bump aiohttp from 3.9.5 to 3.10.2 in /wren-ai-service in the pip group across 1 directory by @dependabot in #590
• chore(wren-ai-service): add script for mdl properties preparation by @cyyeh in #589
• update readme by @chilijung in #593
• chore(wren-ai-service): bump streamlit from 1.34.0 to 1.37.0 in /wren-ai-service in the pip group across 1 directory by @dependabot in #594
• chore(wren-ai-service): minor update by @cyyeh in #592
• Update README.md by @chilijung in #598
• fix(wren-ai-service): error handling for accuracy metric to avoid the select all query failed by @paopa in #596
• chore(wren-ai-service): handle add_quotes error by @cyyeh in #595
• fix(wren-ai-service): expand the timeout and move the waiting check mechanism when force deploying by @paopa in #601
• chore(wren-ai-service):update-launcher by @cyyeh in #600
• chore(wren-ai-service): Refine mdl preparation script by @imAsterSun in #602
• chore(wren-ai-service): custom dependabot commit message and labels by @paopa in #604
• chore(wren-ai-service): fix docker-compose-dev.yaml by @cyyeh in #608
• chore(wren-ai-service): fix wrong ask candidate number by @cyyeh in #610
• chore(wren-ai-service): fix historical question pipeline by @cyyeh in #611
• fix(wren-ui): UI layout is broken when selecting a sample dataset by @fredalai in #609
• chore(wren-ai-service): update deps by @cyyeh in #615
• chore(wren-ai-service): fix eval by @cyyeh in #614
• Trino integration. by @himanshu634 in #535
• Update README.md by @chilijung in #619
• chore(wren-ai-service): sql generation improvement by @cyyeh in #618
• chore(wren-ai-service): improve eval data preparation by @cyyeh in #621
• chore(deps): bump the npm_and_yarn group across 1 directory with 2 updates by @dependabot in #612
• chore(deps): bump the npm_and_yarn group across 1 directory with 2 updates by @dependabot in #626
• Chore(dep): add ws resolution by @onlyjackfrost in #628
• feat(wren-ai-service): optional attribute user_id for Langfuse metadata by @paopa in #625
• chore(wren-ai-service): retrieval improvement by @cyyeh in #599
• chore: release 0.8.0-rc.1 by @onlyjackfrost in #633

Full Changelog: 0.7.5...0.8.0-rc.1

0.7.5

Features

• Implement evaluation metrics. by @paopa in #544
• Users can run Wren AI from shell script. by @onlyjackfrost in #559

Fixes and Chores

• Update indexing async components and test cases by @cyyeh in #549
• Fix getting incorrect native sql issue by @onlyjackfrost in #550
• Fix select models duplicated keys issue by @andreashimin in #551
• Handle errors in the evaluation process by @paopa in #561
• Some small refactor to ai service by @cyyeh in #554
• Modify the wording when the step's preview data is empty by @andreashimin in #547
• Adjust telemetry and logger by @onlyjackfrost in #556
• Remove legacy code by @fredalai in #555

Maintenance

• Add CONTRIBUTING guide in ai service by @cyyeh in #552

Full Changelog: 0.7.4...0.7.5

0.7.5-rc.2

What's Changed

• chore(wren-ai-service): fix entrypoint by @cyyeh in #568
• update bootstrap image

Full Changelog: 0.7.5-rc.1...0.7.5-rc.2

0.7.5-rc.1

What's Changed

• feat(wren-ui): Modify step's preview data empty state wording by @andreashimin in #547
• feat(ai-service): feedback loop by @cyyeh in #261
• chore(wren-ai-service): update indexing async components and update tests to async version by @cyyeh in #549
• Fix(wren-ui): Fix getting incorrect native sql issue by @onlyjackfrost in #550
• fix(wren-ui): Fix select models duplicated keys issue by @andreashimin in #551
• feat(wren-ai-service): Implement evaluation metrics by @paopa in #544
• chore(wren-ai-service): add CONTRIBUTING guide by @cyyeh in #552
• chore(wren-ai-service): small refactoring by @cyyeh in #554
• fix(wren-ai-service): error handling for evaluation process by @paopa in #561
• Chore(wren-launcher): support passing api key with arg and helper function by @onlyjackfrost in #559
• Chore: adjust telemetry and logger by @onlyjackfrost in #556
• chore(wren-ui): remove unused code by @fredalai in #555

Full Changelog: 0.7.4...0.7.5-rc.1

0.7.4

Features

• Add gpt-4o-mini by @cyyeh in #541
• Implement the process for the evaluation framework by @paopa in #525

Fixes and Chores

• Bump requests from 2.31.0 to 2.32.2 in /wren-ai-service in the pip group across 1 directory by @dependabot in #530
• Some function refactor for evaluation by @cyyeh in #536
• Update kustomizations based on new version of wren-ai-service by @cyyeh in #514

Full Changelog: 0.7.3...0.7.4

0.7.3

Fixes and Chores

• Evaluation dataset curation app by @cyyeh in #398
• Pull ollama models if not exist automatically by @cyyeh in #512
• Optimize the PyTest and Image release CI by @paopa in #508
• Fix ibis-service related envs in the env.dev.example by @paopa in #517
• Bump setuptools from 69.5.1 to 70.0.0 in /wren-ai-service in the pip group across 1 directory by @dependabot in #519

Full Changelog: 0.7.2...0.7.3

0.7.2

Fixes and Chores

• Multiple table selection enabled after search. #396 by @himanshu634 in #491
• Fix unit tests and add some test cases for ibis adapter by @onlyjackfrost in #503
• Remove logs and instruction by @onlyjackfrost in #521 & #523

Maintaince

• Update ai-service README for easier contributing from communities by @cyyeh in #515
• Add wren engine as a submodule by @grieve54706 in #507

New Contributors

• @himanshu634 made their first contribution in #491
• @grieve54706 made their first contribution in #507

Full Changelog: 0.7.1...0.7.2