Skip to content

Generative AI Examples v0.7 Release Notes
Compare
Choose a tag to compare
@kevinintel kevinintel released this 28 Jun 16:46
· 505 commits to main since this release
v0.7
77ba913
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.

OPEA Highlight

  • Add 3 MegaService examples: Translation, SearchQnA and AudioQnA
  • Add 4 MicroService and LLM supports llamaIndex, vllm, RayServe
  • Enable Dataprep: extract info from table, image...etc
  • Add HelmChart and GenAI Microservice Connector(GMC) test

GenAIExamples

  • ChatQnA

    • ChatQnA supports Qwen2(422b4b)
    • Add no_proxy in docker compose yaml for micro services(99eb6a, 240587)
    • Fix DataPrep image build in ChatQnA(2fb070)
    • Add Nvidia GPU support for ChatQnA(e80e56)
    • Update ChatQnA docker_compose.yaml to fix downloads failing(e948a7, f2a943)
    • Chat QNA React UI with conversation history(b994bc)
    • Adapt Chinese characters(2f4723)

  • Other examples

    • Refactor Translation Example(409c723)
    • Add AudioQnA with GenAIComps(b4d8e1)
    • Add SearchQnA with GenAIComps(6b76a9)
    • Add env for searchqna(d9b62a)
    • Supports ASR on HPU(2a4860)
    • Fix DocSum Gaudi building instructions(29de55)
    • Add image build job in docker compose e2e gaudi test in CI(4fecd4)

  • CI

    • Add docker build job in manifest e2e workflow(c5f309)
    • Create reuse workflow for get-test-matrix in CI(961abb)
    • Enable new CI runner and improve manifest e2e test scripts(26d6ea)
    • Enable building latest megaservice image on push event in CI(a0b94b)
    • Fix the image build refer(01eed8)
    • Add build docker image option for test scripts(e32a51)
    • Add e2e test of chatqna(afcb3a), codetrans(295b818), codegen(960cf38), docsum(2e62ecc))

GenAIComps

  • Cores

    • Add aio orchestrator to boost concurrent serving(db3b4f)
    • Add microservice level perf statistics(597b3c, ba1d11)
    • Add Gateway for Translation(1b654d)

  • LLM

    • Support Qwen2 in LLM Microservice(3f5cde)
    • Fix the vLLM docker compose issues(3d134d)
    • Enable vLLM Gaudi support for LLM service based on officially habana vllm release(0dedc2)
    • Openvino support in vllm(7dbad0)
    • Support Ollama microservice(a00e36)
    • Support vLLM XFT LLM microservice(2a6a29, 309c2d, fe5f39)
    • Add e2e test for llm summarization tgi(e8ebd9)

  • DataPrep

    • Support Dataprep(f7443f), embedding(f37ce2) microservice with Llama Index
    • Fix dataprep microservice path issue(e20acc)
    • Add milvus microservice(e85033)
    • Add Ray version for multi file process(40c1aa)
    • Fix dataprep timeout issue(61ead4)
    • Add e2e test for dataprep redis langchain(6b7bec)
    • Supported image summarization with LVM in dataprep microservice(86412c)
    • Enable conditional splitting for html files(e1dad1)
    • Added support for pyspark in dataprep microservice(a5eb14)
    • DataPrep extract info from table in the docs(953e78)
    • Added support for extracting info from image in the docs(e23745)

  • Other Components

    • Add PGvector support in Vectorstores(1b7001) and Retriever(75eff6), Dataprep(9de3c7)
    • Add Mosec embedding(f76685) and reranking(a58ca4)
    • Add knowledge graph components(4c0afd)
    • Add LVMs LLaVA component(bd385b)
    • Add asr/tts components for xeon and hpu(cef6ea)
    • Add WebSearch Retriever Microservice(900178)
    • Add initial pii detection microservice(e38041)
    • Pinecone support for dataprep and retrieval microservice(8b6486)
    • Support prometheus metrics for opea microservices(758914), (900178)
    • Add no_proxy env for micro services(df0c11)
    • Enable RAGAS(8a670e)
    • Fix RAG performance issues(70c23d)
    • Support rerank and retrieval of RAG OPT(b51675)
    • Reranking using an optimized bi-encoder(574847)
    • Use parameter for retriever(358dbd), reranker(dfdd08)

  • CI

    • CI optimization to support multiple test for single kind of service(38f646)
    • Update CI to support dataprep_redis path level change(5c0773)
    • Enable python coverage(cd91cf)
    • Add codecov(da2689)
    • Enable microservice docker images auto build and push(16c5fd)

GenAIEvals

  • Enable autorag to automatically generate the evaluation dataset and evaluate the RAG system(b24bff)
  • Support document summarization evaluation with microservice(3ec544)
  • Add RAGASMetric(7406bf)
  • Update install bkc(26ddcc)

GenAIInfra

  • GMC

    • Enable gmc e2e for manifests changes and some minor fix (758432)
    • GMC: make "namespace" field of each resource in the CR optional (7073ac)
    • ChatQnA demo yaml files integration between GMC and Oneclick (020899)
    • Add gmc e2e (595185)
    • Add docker build and push target for GMC (04d7f2)
    • GMC: overwrite config map template before GMC resources are deployed (ce9190)
    • GMC: replace the service and deployment name if GMC has defined (eec845)
    • Add gmc guide (6bb8a3)
    • GMC: adopt separate e2e for gaudi and xeon (c5075b)
    • Update readme and user guide for GMC (2d17c9)
    • GMC: add Codetrans example (aed70d)
    • Enable GMC e2e on Gaudi (d204a7)

  • HelmChart

    • Helm chart: Add default minimal pod security (8fcf0a)
    • Support e2e test for chatqna helm chart (2f317d)
    • Add helm charts for deploy ChatQnA (20dce6)
    • Reorg of helm charts (d332c2)

  • Others

    • Add DocSum llm service manifests (9ab8de)
    • Enable golang e2e test in CI (bc9aba)
    • Add e2e test for docsum example (89aa5a)
    • Add docsum example on both xeon and gaudi node (c88817)
Assets 2
Loading