https://github.com/alexcg1/executor-chunk-level-equalizer

Put all text chunks on doc.chunks level, not lower traversal levels
https://github.com/alexcg1/executor-chunk-level-equalizer

Last synced: 16 days ago
JSON representation

Put all text chunks on doc.chunks level, not lower traversal levels

• Host: GitHub
• URL: https://github.com/alexcg1/executor-chunk-level-equalizer
• Owner: alexcg1
• Created: 2022-05-10T09:03:19.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-05-10T09:26:00.000Z (over 2 years ago)
• Last Synced: 2024-10-16T03:41:17.408Z (about 1 month ago)
• Language: Python
• Size: 2.93 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ChunkLevelEqualizer

Put all text chunks on doc.chunks level, not lower traversal levels. Used in [PDF search example](https://medium.com/jina-ai/building-an-ai-powered-pdf-search-engine-with-python-part-1-9102654e6ea1?source=collection_home---------0----------------------------)

Note: This REMOVES all top-level text chunks from doc.chunks and then moves all lower-level text chunks to doc.chunks

## Usage

#### via Docker image (recommended)

```python

from jina import Flow

	

f = Flow().add(uses='jinahub+docker://ChunkLevelEqualizer')

```

#### via source code

```python

from jina import Flow

	

f = Flow().add(uses='jinahub://ChunkLevelEqualizer')

```

- To override `__init__` args & kwargs, use `.add(..., uses_with: {'key': 'value'})`

- To override class metas, use `.add(..., uses_metas: {'key': 'value})`