|
--- |
|
inference: false |
|
language: en |
|
license: apache-2.0 |
|
library_name: txtai |
|
tags: |
|
- sentence-similarity |
|
datasets: |
|
- maxiw/hf-posts |
|
--- |
|
|
|
# Hugging Face Posts txtai embeddings index |
|
|
|
This is a [txtai](https://github.com/neuml/txtai) embeddings index for the [Hugging Face Posts dataset](https://huggingface.co/datasets/maxiw/hf-posts). |
|
|
|
txtai must be [installed](https://neuml.github.io/txtai/install/) to use this model. |
|
|
|
## Example |
|
|
|
This index can be loaded from the Hugging Face Hub with txtai as shown below. |
|
|
|
```python |
|
from txtai import Embeddings |
|
|
|
# Load the index from the HF Hub |
|
embeddings = Embeddings() |
|
embeddings.load(provider="huggingface-hub", container="neuml/txtai-hfposts") |
|
|
|
# Search for posts discussing transformers |
|
embeddings.search("transformers") |
|
``` |
|
|
|
## Use Cases |
|
|
|
Hugging Face Posts is an exploratory dataset to analyze what is being discussed on the [Hugging Face Posts](https://huggingface.co/posts) platform. |
|
|
|
An embeddings index generated by txtai is a fully encapsulated index format. It doesn't require a database server or dependencies outside of the Python install. |
|
|
|
## More information |
|
|
|
Read more about this model and how it was built in [this article](https://neuml.hashnode.dev/analyzing-hugging-face-posts-with-graphs-and-agents). |
|
|
