app.py

from typing import List

import gradio as gr
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True, device='cpu')


def embed(document: str):
    return model.encode(document)


with gr.Blocks(title="Nomic Text Embeddings") as app:
    gr.Markdown("# Nomic Text Embeddings v1.5")
    gr.Markdown("Generate embeddings for your text using the nomic-embed-text-v1.5 model.")
    
    # Create an input text box
    text_input = gr.Textbox(label="Enter text to embed", placeholder="Type or paste your text here...")

    # Create an output component to display the embedding
    output = gr.JSON(label="Text Embedding")
    
    # Add a submit button with API name
    submit_btn = gr.Button("Generate Embedding", variant="primary")

    # Handle both button click and text submission
    submit_btn.click(embed, inputs=text_input, outputs=output, api_name="predict")
    text_input.submit(embed, inputs=text_input, outputs=output)
    
    # Add API usage guide
    gr.Markdown("## API Usage")
    gr.Markdown("""
    You can use this API programmatically. Hugging Face Spaces requires using their client libraries which handle queuing automatically.
    
    ### Quick Command-Line Usage
    ```bash
    # Install gradio client
    pip install gradio_client
    
    # Generate embedding with one command
    python -c "from gradio_client import Client; print(Client('ipepe/nomic-embeddings').predict('Your text here', api_name='/predict'))"
    ```
    
    ### Python Example (Recommended)
    ```python
    from gradio_client import Client
    
    client = Client("ipepe/nomic-embeddings")
    result = client.predict(
        "Your text to embed goes here",
        api_name="/predict"
    )
    print(result)  # Returns the embedding array
    ```
    
    ### JavaScript/Node.js Example
    ```javascript
    import { client } from "@gradio/client";
    
    const app = await client("ipepe/nomic-embeddings");
    const result = await app.predict("/predict", ["Your text to embed goes here"]);
    console.log(result.data);
    ```
    
    ### Direct HTTP (Advanced)
    Direct HTTP requests require implementing the Gradio queue protocol:
    1. POST to `/queue/join` to join queue
    2. Listen to `/queue/data` via SSE for results
    3. Handle session management
    
    For direct HTTP, we recommend using the official Gradio clients above which handle this automatically.
    
    The response will contain the embedding array as a list of floats.
    """)

if __name__ == '__main__':
    app.launch(server_name="0.0.0.0", show_error=True, server_port=7860)