opea-project/GenAIExamples
Generative AI Examples is a collection of GenAI examples such as ChatQnA, Copilot, which illustrate the pipeline capabilities of the Open Platform for Enterprise AI (OPEA) project.
ShellApache-2.0
Issues
- 4
[Bug]Max output tokens from an LLM should be configurable.
#1131 opened by mkbhanda - 0
- 0
[Feature] Hosted OPEA Example (Huggingface space)
#1111 opened by joshuayao - 0
[Feature] text-to-image Gen
#1109 opened by joshuayao - 0
[Feature] graph RAG enhanced ChatQnA (Neo4j)
#1108 opened by joshuayao - 5
[Bug] file update load feature is not enabled in docsum
#1010 opened by lianhao - 3
[Bug] DocSum Svelte UI failed to send request
#1065 opened by Ruoyu-y - 2
[Bug] Default ChatQnA service gives incorrect output for seed question when testing with curl
#1005 opened by devpramod - 6
[Bug]
#1127 opened by vishakh15nair - 1
[Bug] OPEA docker container and habana runtime issue
#1164 opened by anatu-git - 2
[Feature] Move Docker install instructions to a common place versus under ChatQnA
#1042 opened by mkbhanda - 0
[Feature] Examples on AMD ROCm for OPEA v1.1
#1153 opened by joshuayao - 4
- 2
- 0
[Bug]FaqGen return HTTP status 500
#1132 opened by artem-astafev - 2
[Bug] docsum return HTTP status 500
#1129 opened by lianhao - 0
[Bug] Cleanup -- remove image https://hub.docker.com/r/opea/llm-vllm-hpu/tags
#1140 opened by mkbhanda - 0
[Bug] vLLM-service runtime issue for ChatQnA
#1119 opened by louie-tsai - 1
Setup OpenSSF Scorecard (Current Score: 5.6)
#1107 opened by zixuan-x - 1
[Bug]wrong TGI endpoint for ChatQnA testing
#1104 opened by louie-tsai - 1
[Feature] Digital Human
#1110 opened by joshuayao - 0
[Feature] Llamaindex integration
#1112 opened by joshuayao - 7
[Bug] ChatQnA browser interface gives an error - "failed to load chat content"
#989 opened by arun-gupta - 0
[Feature] Haystack Integration
#1114 opened by joshuayao - 0
[Feature] Langchain integration
#1113 opened by joshuayao - 0
[Bug] Model not following prompt template
#1051 opened by devpramod - 3
[Bug] Broken build instructions
#1001 opened by eero-t - 0
[Bug] Fail to build the LLM Docker Image
#1074 opened by Jackie-shi - 0
[Bug] file update load feature is not enabled in faqgen
#1066 opened by lianhao - 0
[Feature] AvatarChatbot: Allow user to choose avatar images and model type between runs, instead of just the audio question
#1055 opened by ctao456 - 6
[Bug] ChatQnA model is hallucinating
#1026 opened by arun-gupta - 4
[Bug] DocSum cannot support requests
#1028 opened by lianghouxu - 2
[Bug] CodeTrans generates inconsistent and random outputs when processing dummy code inputs
#1012 opened by lianhao - 2
[Bug] codegen shows non-meaningful output in the UI
#1011 opened by lianhao - 0
EMR performance tuning
#1046 opened by kevinintel - 0
GNR performance tuning
#1047 opened by kevinintel - 0
Gaudi3 performance tuning
#1048 opened by kevinintel - 1
[Bug]ChatQnA browser interface requires http link, creates a friction point for developers
#988 opened by arun-gupta - 0
[Bug] Broken bug template
#1002 opened by eero-t - 0
[Bug] Non-intuitive user feedback in ChatQnA while the answer is being prepared
#1003 opened by arun-gupta - 2
- 0
- 0
- 0
- 0
- 2
[Bug] Docs: Instructions in README to migrate to conversational-UI missing some steps.
#991 opened by mkbhanda - 2
[Bug] MultimodalQnA/docker_compose/intel/cpu/xeon/README.md docker compose typo
#986 opened by NotAdityaPawar - 0
restructure 20 examples
#1037 opened by kevinintel - 1
- 0
[Bug] ChatQnA is taking ~75 seconds to provide response for the first answer
#1004 opened by arun-gupta