v1.1.2

This release upgraded version (v0.2.75) of llama-cpp-python bindings for llama.cpp, which will prevent us from hitting CVE-2024-34359.
Other changes:

• Testing changes, workflow cleanup, increasing test coverage, and introduce e2e tests interfacing with Ilab
• Bootc images disk-image support
• object detection recipe + MS refactor
• Milvus vector database support for RAG
• General recipes and Bootc Training fixes

What's Changed

• README cleanup by @danmcp in #460
• Allow to use a different instructlab git repository via env vars by @javipolo in #458
• Add target for creating disk-images by @javipolo in #455
• Maintain permissions when copying files into build directories by @rhatdan in #462
• Reschedule testing framework workflow to run once a day by @lmilbaum in #463
• bootc e2e workflow - build temp image shim with ssh keys around bootc by @Gregory-Pereira in #428
• Build and Install Bootc Image by @lmilbaum in #464
• Reboot instance after bootc install by @lmilbaum in #467
• adding Tmate session, and testing playbook by @Gregory-Pereira in #468
• HF_TOKEN is not propagated to the podman command by @romfreiman in #473
• instructlab e2e testing by @lmilbaum in #471
• ansible cfg refactor for e2e training workflow by @Gregory-Pereira in #476
• Add pull task to e2e workflow by @Gregory-Pereira in #475
• Running e2e tests by @lmilbaum in #477
• chore(deps): update all dependencies by @platform-engineering-bot in #479
• chore(deps): update auto merged updates by @platform-engineering-bot in #478
• fixing run path for model_converter by @Gregory-Pereira in #481
• split build and pull on bootc_training workflow by @Gregory-Pereira in #484
• Use newer kernel version when there are multiple available by @javipolo in #488
• Allow both json and toml as config files for bootc-image-builder by @javipolo in #470
• Error on umasks other then 022 by @rhatdan in #474
• Turn on instructlab for intel by @rhatdan in #489
• Install habanalabs packages in containerfile by @enriquebelarte in #490
• Update Auto merged updates by @redhat-renovate-bot in #492
• object detection recipe and MS tests by @Gregory-Pereira in #278
• add interrupt to llamacpp by @MichaelClifford in #494
• Lower ConversationBufferWindowMemory by @MichaelClifford in #495
• Add Milvus database compatibility with the RAG recipe by @Shreyanand in #334
• update readme's to clarify app ports used by @MichaelClifford in #496
• Renovate config by @lmilbaum in #499
• fix: prevent multipes requests in chatbot recipe by @jeffmaury in #498
• chore(deps): update auto merged updates by @platform-engineering-bot in #501
• downgrade langchain to < 0.2.0 in nlp recipes by @Gregory-Pereira in #502

New Contributors

• @romfreiman made their first contribution in #473
• @redhat-renovate-bot made their first contribution in #492

Full Changelog: v1.1.1...v1.1.2

v1.1.1

What's Changed

• Cleanout OCI build Directory first when doing a make by @rhatdan in #447
• fix template by @n1hility in #448
• remove chron schedulign for the e2e workflow as its not ready by @Gregory-Pereira in #449
• Remove typo from removal of deepspeed-trainer by @rhatdan in #451
• README.md cleanup by @danmcp in #454
• Update training README.md by @rhatdan in #452
• Fix Makefile.common path by @javipolo in #453
• chore: handle some AVX flags properly on certain Intel CPUs by @benoitf in #457
• chore: handle some AVX flags properly on certain Intel CPUs by @benoitf in #459

New Contributors

• @danmcp made their first contribution in #454
• @benoitf made their first contribution in #457

Full Changelog: v1.1.0...v1.1.1

v1.1.0

Release v1.1.0 is once again targeted at bringing containers/ai-lab-recipes into alignment with containers/podman-desktop-extension-ai-lab.

Core differences:

• Introduction of grainte-7b-lab as the standard model for (mostly) all of our natural language processing applications
• General improvements to Summarizer and Audio-to-Text recipes
  • Greater variety of supported input file types
• Introduction of an experimental /training directory for building hardware accelerated bootc images to support training workloads
• Increased workflow build coverage
• Integration with @platform-engineering-bot to provide automated dependency bumps

What's Changed

• fix: Convert to Makefile-style and correct wrong usage by @PaulYuuu in #289
• Consistently name llamacpp-python by @rhatdan in #292
• Add support for bootc on audio-to-text recipe by @rhatdan in #287
• chore(deps): update auto merged updates by @platform-engineering-bot in #295
• recipes: update descriptions by @vrothberg in #298
• chore(deps): update all dependencies by @platform-engineering-bot in #296
• Fix document chunking in summarizer by @MichaelClifford in #293
• adding merlinite and granite models by @Gregory-Pereira in #300
• fixing testing framework with image ref being moved by @Gregory-Pereira in #301
• add model workflows by @sallyom in #304
• fix convert_models context by @sallyom in #306
• fix convert_models build with build path permissions (temporary) by @Gregory-Pereira in #307
• temporarily remove model-converter image build by @sallyom in #309
• make model-images only run with cron or manual temporarily by @sallyom in #312
• add mistral-7b-code model and change env by @sallyom in #313
• Show progress bar when downloading models by @rhatdan in #305
• add mistral-7b-code model and change env by @sallyom in #314
• rfe(bootc-image-builder): Support "--chown" option by @PaulYuuu in #299
• fix typo in model image names on push by @sallyom in #317
• after 10 failed attempts, finally updating the model-image workflow the right way by @sallyom in #318
• add PDF reading to summarizer by @MichaelClifford in #302
• Accelerated container image for AMD by @kwozyman in #316
• Fixup download-models by @rhatdan in #303
• Update model download example in models README.md by @MichaelClifford in #319
• remove extra registry in image push by @sallyom in #320
• quay defaults x86_64 arch to amd64 by @Gregory-Pereira in #321
• forgot endif by @Gregory-Pereira in #323
• Image names must be lower case by @rhatdan in #324
• joining the org by @Gregory-Pereira in #325
• Accelerated container image for NVidia by @kwozyman in #328
• Cleanup NVIDIA training. by @rhatdan in #331
• Update whisper model recipe to convert audio files by @hemajv in #326
• Better separation between CentOS and RHEL by @kwozyman in #332
• upping model download timeout and connection values by @Gregory-Pereira in #329
• Add model download utility by @MichaelClifford in #275
• set summarizer write to tempfile by @MichaelClifford in #330
• Update suggested model in chat and summary docs by @MichaelClifford in #333
• Intel Habanalabs bootc image by @kwozyman in #335
• make granite default for models/ and llamacpp/ by @MichaelClifford in #339
• Add pdf option to rag recipe by @MichaelClifford in #342
• Add clean for models, wastes lots of space by @rhatdan in #344
• Add -bootc identifier to training images by @rhatdan in #340
• Add building of instructlab container images by @rhatdan in #341
• Fix typo in instruclab Makefile by @rhatdan in #346
• add instructlab nvidia base image by @sallyom in #345
• Break apart push by @rhatdan in #347
• Get exact token count in summarizer by @MichaelClifford in #348
• try non protected build with path changes by @Gregory-Pereira in #308
• fix push image step double registry by @Gregory-Pereira in #355
• [Model Upgrade] upgrade mistral-7b-instruct-v0.1 to mistral-7b-instruct-v0.2 by @Gregory-Pereira in #352
• improper variable definition by @cooktheryan in #359
• Update the ailab images link in README by @hellohellenmao in #363
• Update all dependencies by @platform-engineering-bot in #362
• Fixes for configuring training by @rhatdan in #358
• only build from dispatch and cron, not paths by @Gregory-Pereira in #383
• add rouge score to summarizer by @MichaelClifford in #376
• Expand documentation for training images by @kwozyman in #369
• Rename training repos to add bootc- indicator by @rhatdan in #368
• minor update for bootc-image-builder target by @PaulYuuu in #367
• Downloading models makefile moved by @lmilbaum in #385
• download models from models dir by @Gregory-Pereira in #389
• refactor instructlab training images to use make targets by @Gregory-Pereira in #387
• swap granite for mistral cleanup + model and recipe housekeeping by @Gregory-Pereira in #350
• update ailab-images with intel-bootc and amd-bootc by @Gregory-Pereira in #392
• version pinning ubuntu runner by @Gregory-Pereira in #388
• Update Auto merged updates by @platform-engineering-bot in #361
• add slack notifications to instructlab wofklows by @Gregory-Pereira in #390
• With latest rocm-smi no need for EPEL in Containerfile by @rhatdan in #386
• model container builder by @kwozyman in #398
• Add missing habanalabs modules by @enriquebelarte in #396
• Add nvidia-instructlab-bootc and supporting materials by @n1hility in #360
• adding instructlab workflow and renaming bootc workflow by @Gregory-Pereira in #400
• Fix name of intel-bootc by @rhatdan in #401
• reworking workflow names for visibility from actions tab by @Gregory-Pereira in #394
• updating instructlab workflow name by @Gregory-Pereira in #403
• Add hl-smi binary from firmware-tools by @enriquebelarte in #402
• Minor text edits to top dir files by @MichaelClifford in #404
• Improve summary chunking by @MichaelClifford in #397
• fix bootc workflow with intel image rename by @Gregory-Pereira in #407
• Remove old fine tuning example by @MichaelClifford in https:...

Release v1.0.0

Release v1.0.0 is meant to bring containers/ai-lab-recipes in alignment with the work undergone by the Podman Desktop team in their repo (containers/podman-desktop-extension-ai-lab). The following recipes give first-class support with respect to running as catalog recipes within Podman Desktop:

• chatbot
• codegen
• sumarrizer
• whisper + audio_to_text
• object_detection

The following recipes are under development with respect to their workflow within the Podman Desktop AI-lab extension but are considered stable running locally and in the context of this repo:

• RAG
• multimodal

Full change log

• add for rh-demo by @sallyom in #1
• add streaming by @MichaelClifford in #2
• update finetune dir by @MichaelClifford in #5
• update containerfile with download by @sallyom in #6
• add summarize app by @MichaelClifford in #7
• Refactor src and chat service by @MichaelClifford in #8
• fix bug in summarizer imports by @MichaelClifford in #10
• Fix 9: part 2 by @MichaelClifford in #11
• add arch diagram by @MichaelClifford in #12
• add upload_file_ui.py to summarizer ai apps by @MichaelClifford in #13
• Create ai-studio.yaml by @sallyom in #14
• fix: update chatbot ai-studio.yaml and containerfile by @lstocchi in #17
• add playground build by @MichaelClifford in #18
• Updates to READMEs & Containerfiles by @sallyom in #15
• fix: merge chatbot config files into one by @lstocchi in #20
• add scratch model image containerfile by @sallyom in #22
• Add RAG demo to the app by @Shreyanand in #4
• update summarizer dir for podman AI studio by @MichaelClifford in #23
• fix: fix contextdir for summarizer containers by @lstocchi in #25
• fix: rename folders in rag sample by @lstocchi in #26
• update summarizer containerfiles by @MichaelClifford in #24
• fix: fix summarizer app by @lstocchi in #27
• Add chatbot quadlet by @sallyom in #29
• remove flag option by @MichaelClifford in #28
• add quadlet.image for chatbot by @sallyom in #32
• RAG, Langchain and Chromadb example by @MichaelClifford in #31
• add chatbot langchain recipe by @MichaelClifford in #33
• update UI to streamlit by @MichaelClifford in #34
• add playground interaction demo notebook by @MichaelClifford in #19
• Update readmes by @sallyom in #35
• add chatbot-langchain quadlet files by @sallyom in #36
• add document selection by @MichaelClifford in #37
• add langchain summarizer application by @MichaelClifford in #40
• adds check for text files to rag app by @MichaelClifford in #39
• fix: adapt playground for use with tooling by @jeffmaury in #42
• initial gh actions for pushing to quay.io/redhate-et/locallm-* by @sallyom in #43
• Update images & remove unused files by @sallyom in #44
• Code generation app demo by @suppathak in #38
• add summarizer quadlet files by @sallyom in #48
• update gh actions by @sallyom in #49
• Add quadlet code generation by @sallyom in #50
• feat: add ports to ai-studio by @lstocchi in #51
• add model service check by @MichaelClifford in #41
• fix: fix rag-langchain app by @lstocchi in #47
• fix: add model service check to Summarizer by @lstocchi in #53
• fix: add model service check to code-generation app by @lstocchi in #54
• quick fix: actions cp/paste error by @sallyom in #56
• Update image references from quay.io/sallyom to quay.io/redhat-et and update readme by @sallyom in #55
• chore: add version to ai-studio.yaml by @lstocchi in #59
• Add whisper.cpp model by @hemajv in #58
• Add model conversion tool by @MichaelClifford in #57
• Add object detection recipe by @MichaelClifford in #71
• Add whisper model server by @hemajv in #73
• Add experimental llamacpp/vulkan server by @slp in #75
• delete duplicate docs by @MichaelClifford in #77
• add llamacpp cuda server by @MichaelClifford in #78
• Remove old recipes by @MichaelClifford in #76
• update model-service-endpoints-quadlets by @sallyom in #79
• Add whisper streamlit app by @hemajv in #80
• Add multimodal support by @MichaelClifford in #45
• Add option for config file in playground by @MichaelClifford in #72
• chore: add image field to define image name when building by @lstocchi in #81
• image updates by @sallyom in #82
• update chatapp readme by @MichaelClifford in #85
• update summarizer readme by @MichaelClifford in #86
• update codegen readme by @MichaelClifford in #87
• Update README by @MichaelClifford in #92
• update rag readme and app by @MichaelClifford in #91
• add whisper quadlet, move whisper model-service, update docs by @sallyom in #83
• Fix a typo in the README. by @vrothberg in #97
• fix: rename ai studio to ai lab by @lstocchi in #99
• update audio-to-text for ai studio by @MichaelClifford in #100
• Rename top level directories by @rhatdan in #103
• add vector_dbs dir by @MichaelClifford in #102
• Replace playground with model_servers by @MichaelClifford in #101
• playground tests by @lmilbaum in #96
• Generalize test requirements by @lmilbaum in #107
• summarizer-langchain->summarizer & small fix by @sallyom in #106
• Onboard Renovate to repo. by @cevich in #105
• fix some podman build commands & update playground -> model_servers by @sallyom in #110
• cleanup by @lmilbaum in #109
• chatbot GHA workflow by @lmilbaum in #108
• Reorganize by @MichaelClifford in #111
• update python base images by @sallyom in #98
• remove old /src files by @MichaelClifford in #113
• Move model_converter/ by @MichaelClifford in #115
• model_servers workflow renamed by @lmilbaum in #112
• chatbot tests by @lmilbaum in #116
• README update to match repo restructure by @sallyom in #118
  ...