/

Hugging Face

&

Meilisearch

Integrate Hugging Face and Meilisearch

Connect Hugging Face and Meilisearch nodes in your workflow. Integrate with any tool or database and ship powerful backend logic and APIs instantly - No code required!

Node stack

Supported Hugging Face and Meilisearch Nodes

Add any other tools or your preferred database nodes. If an integration is not available generate your own using AI

Caption Image

Generate caption for the image using Hugging Face's [Salesforce/blip-image-captioning-large](https://huggingface.co/Salesforce/blip-image-captioning-large) model for image captioning pretrained on COCO dataset - base architecture (with ViT large backbone).

Image Classification

Get classification labels for your image using Hugging Face's [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) model which is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.

Text Summarization

Summarize long text using Hugging Face's [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) model which is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.

Text-To-Image

Generate image from text, using Hugging Face's [openskyml/dalle-3-xl](https://huggingface.co/openskyml/dalle-3-xl) test model very similar to Dall•E 3.

Text-To-Music

Generate music from text using Hugging Face's [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) model capable of generating high-quality music samples conditioned on text descriptions or audio prompts.

Add Document

Add a single document to MeiliSearch. Accepts a JSON object representing the document and adds it to the index

Add Documents

Add a list of documents to MeiliSearch index.

Delete Document

Delete a document from a Meilisearch index.

Full Text Search

Performs a full text search on a Meilisearch index

Get Document

Retrieve a document from a Meilisearch index using the given Document ID.

Hybrid Search

Performs a hybrid search combining full-text and attribute-based filtering, returning a JSON object or an array of them. For more details on using vector search in MeiliSearch, visit the [official documentation](https://www.meilisearch.com/docs/learn/experimental/vector_search#using-vector-search).

Update Document

Update a single document in MeiliSearch. Accepts a JSON object representing the document and updates it.

Update Documents

Update multiple documents in MeiliSearch by sending an array of JSON objects.

Update Synonyms

Update the synonyms for any index in your MeiliSearch instance

Quick start

How to integrate Hugging Face and Meilisearch

Step 1 — Add the nodes to your workflow

Create a new workflow in BuildShip, click “Add node”, and select the Hugging Face and Meilisearch actions you want to use.

Step 2 — Configure each node

Go to each node to authenticate (or add your API key) and fill in the required parameters.

Step 3 — Connect the nodes

Each node in BuildShip can connect to others by using their output variables. When you reference a variable from one node in another, BuildShip automatically links them in the workflow.

Step 4 — Test your workflow

Define your starting data in the Inputs node and choose what to do with the result in the Flow Output node. Finally, run a test to see your workflow in action.

blog posts & tutorials

Recommended Reads

Below are recommneded blogs that will help in your journey