NVIDIA/nv-ingest

Issues

• [FEA]: Move chart and table data extractors out of pdfium as stand-alone stages

  #145 opened 2 months ago by drobison00
  0

• [FEA]: Support arbitrary python functions to determine document split points

  #194 opened 2 months ago by randerzander
  0

• [FEA]: Allow the user to specify the milvus collection name in the VdbUpload task

  #193 opened 2 months ago by randerzander
  0

• [BUG]: Paddle Version checking can get into an infinite loop when failing or PADDLE_HTTP_ENDPOINT is not specified

  #192 opened 2 months ago by drobison00
  0

• [FEA]: Remove yolox postprocessing duplicate code

  #106 opened 3 months ago by edknv
  1

• [FEA]: Add support for table and chart extraction from images, docx files, and pptx files.

  #191 opened 2 months ago by drobison00
  0

• [BUG]: There are corner cases where multi-part responses are chunked too large

  #187 opened 2 months ago by drobison00
  0

• [FEA]: Improve Client Library API

  #186 opened 2 months ago by drobison00
  0

• [BUG]: failed to solve: process "/bin/bash -c source activate base && conda install setuptools==70.0.0" did not complete successfully: exit code: 1

  #182 opened 2 months ago by ruchaa-apte
  1

• [DOC]: Make clear EA status in the README

  #181 opened 2 months ago by jarmak-nv
  0

• [FEA]: Add native async calls in addition to Futures based async functionality

  #180 opened 2 months ago by edknv
  0

• [DOC]: Add minimal version of docker compose in prerequisites

  #178 opened 2 months ago by mdemouth
  0

• [BUG]: nv-ingest-nv-ingest-ms-runtime-1 container failed to connect yolox endpoints

  #165 opened 2 months ago by angudadevops
  11

• [FEA]: Improve milvus connection logging

  #173 opened 2 months ago by edknv
  0

• [DOC]: Add instructions on how a 4x GPU should be distributed between services

  #171 opened 2 months ago by sosahi
  0

• [FEA]: Add bulk ingest to vdb task

  #164 opened 2 months ago by jperez999
  0

• [FEA]: Add bm25 to supported indexes in vdb task (milvus)

  #167 opened 2 months ago by jperez999
  0

• [FEA]:

  #159 opened 2 months ago by randerzander
  1

• [BUG]: Redis Task Sink fails to unpack cuDF dataframe with .to_dict() for some versions of Cuda 12 and PyArrow 17+

  #155 opened 3 months ago by drobison00
  0

• [FEA]: Move to the CUDA Base container + Morpheus conda install

  #95 opened 3 months ago by jarmak-nv
  1

• [FEA]: Enhanced tracing for individual pipeline stages - raw output

  #100 opened 3 months ago by jdye64
  1

• [BUG]: StoreTask fails

  #149 opened 3 months ago by randerzander
  0

• [BUG]: Add a DEFAULT log level that maps to INFO

  #146 opened 3 months ago by sosahi
  0

• [BUG]: Docker pull permission denied

  #138 opened 3 months ago by Nghiauet
  0

• [DOC]: better document how to track metrics in Prometheus

  #136 opened 3 months ago by sosahi
  0

• [DOC]: document visualization of traces in more details

  #135 opened 3 months ago by sosahi
  0

• [DOC]: better document the jobs and their expected output

  #134 opened 3 months ago by sosahi
  0

• [DOC]: improve the error handling

  #133 opened 3 months ago by sosahi
  0

• [DOC]: update langchain and llamaindex examples to submit a job including store and vdb_upload tasks

  #122 opened 3 months ago by sosahi
  0

• [DOC]: update the endpoints in langchain and llamaindex notebooks

  #124 opened 3 months ago by sosahi
  0

• [DOC]: Document the client's error codes

  #131 opened 3 months ago by sosahi
  0

• [DOC]: document all the tasks allowed via the API

  #132 opened 3 months ago by sosahi
  0

• [DOC]: embed an API inspection tool for API specs

  #130 opened 3 months ago by sosahi
  0

• Upgrade Python version to 3.10.15

  #104 opened 3 months ago by sosahi
  0

• [BUG]: Jupyter Notebook Unable to Communicate with Docker Compose Services

  #123 opened 3 months ago by abeltre1
  0

• [DOC]: improve the error and exception handling in the example notebook

  #121 opened 3 months ago by sosahi
  0

• [DOC]: Add instruction for setting up the docker container for client example inside the notebook

  #120 opened 3 months ago by sosahi
  0

• [DOC]: move the minikube setup subsection to a "Tip"

  #118 opened 3 months ago by sosahi
  0

• [DOC]: list a kubernetes cluster and helm versions as prerequisites in the help deployment guide

  #117 opened 3 months ago by sosahi
  0

• [DOC]: add note on milvus deployment's possibility to use GPU for acceleration

  #116 opened 3 months ago by sosahi
  0

• [DOC]: add an architecture diagram for the pipeline including the NIMs

  #115 opened 3 months ago by sosahi
  0

• [DOC]: move the usage of tkinter for image inspection ot the python notebook

  #114 opened 3 months ago by sosahi
  0

• [DOC]: tkinter installs via apt

  #113 opened 3 months ago by sosahi
  0

• [DOC]: Add a "Next Steps" section for more production-grade setup

  #112 opened 3 months ago by sosahi
  0

• [DOC]: add description for "Task" and "Job"

  #111 opened 3 months ago by sosahi
  0

• [DOC]: include info on required env variables for unstructured.io and adobe

  #110 opened 3 months ago by sosahi
  0

• [FEA]: Add HTTPS client support to the nv-ingest-cli RestClient

  #103 opened 3 months ago by jdye64
  0

• [FEA]: Enforce Minimum Input Dimensions for YOLOX Predictions in PaddleOCR Pipeline

  #98 opened 3 months ago by edknv
  0

• [DOC]: add note to make sure nvidia is the default container runtime

  #101 opened 3 months ago by sosahi
  0

• [FEA]: CODEOWNERS

  #102 opened 3 months ago by jarmak-nv
  0