NVIDIA / NVIDIA/NeMo-Retriever

[FEA]: Embedding and VDB upload from Jsonl file

Open
#206 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Python
Stars
3k
Forks
349
Avg merge
1d 23h
Merged PRs (30d)
116

Description

Is this a new feature, an improvement, or a change to existing functionality?

New Feature

How would you describe the priority of this feature request

Currently preventing usage

Please provide a clear description of problem this feature solves

I have a jsonl file with text snippets and corresponding ids that I want to embed and upload to Milvus through the Nv-Ingest python client and retrieve with LlamaIndex. It's important that the Ids are maintained through every step of this process.

Describe the feature, and optionally a solution or implementation and any alternatives

I would like a feature that would allow me to submit a jsonl file with an id field and a text field to the NV-Ingest client, which would embed and upload the text to the VDB while keeping the associated Id.

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the NV-Ingest Python client's existing file-ingestion, embedding, and vector-database upload entry points. Check how records are passed to Milvus and retrieved through LlamaIndex, then define the JSONL id and text flow. Done means a JSONL file can be submitted and each associated ID remains available through embedding, upload, and retrieval.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, databases, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.