FlowiseAI/Flowise

Help with loading JSON file and extracting metadata

Open

#3374 opened on Oct 18, 2024

View on GitHub
 (3 comments) (0 reactions) (0 assignees)TypeScript (52,823 stars) (24,335 forks)batch import
enhancementhelp wanted

Description

Hi there!

I'd like to load a JSON file into the document store using the Json File DocumentLoader, but I'm having some trouble getting the metadata to show up correctly.

The JSON File Looks Like This:

{

"id": "doc1", "text": "This is a sample document with some content.", "metadata": { "author": "John Doe", "createdDate": "2023-02-20T14:30:00.000Z", "category": "article" } }

The Issue:

When I load this JSON file into the document loader, I don't see the metadata in the expected format:

image

Flowise Version:

Just to give you some context, my Flowise version is v2.1.2.

Can You Help Me? Is my expectation wrong?

Is there something specific that I need to do or configure to get the metadata showing up correctly in the document loader?

Thanks in advance for your help!

flowise is v2.1.2

Contributor guide

Tech stack
typescriptnodejs
Domain
backenddata
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
JavaScriptFlowise basicsJSONDocumentLoader concept
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75
Research direction
Examine the JsonFileDocumentLoader component in the Flowise codebase, likely in the components directory. Understand the expected metadata format and compare with the user's example. Look for any configuration options for metadata extraction. Check the issue comments for maintainer responses.