nateraw/bge-large-en-v1.5:9cf9f015 | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

nateraw /bge-large-en-v1.5:9cf9f015

Playground API

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=nateraw/bge-large-en-v1.5

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run nateraw/bge-large-en-v1.5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nateraw/bge-large-en-v1.5:9cf9f015a9cb9c61d1a2610659cdac4a4ca222f2d3707a68517b18c198a9add1",
  {
    input: {
      texts: "[\"In the water, fish are swimming.\", \"Fish swim in the water.\", \"A book lies open on the table.\"]",
      batch_size: 32,
      convert_to_numpy: true,
      normalize_embeddings: true
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run nateraw/bge-large-en-v1.5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/bge-large-en-v1.5:9cf9f015a9cb9c61d1a2610659cdac4a4ca222f2d3707a68517b18c198a9add1",
    input={
        "texts": "[\"In the water, fish are swimming.\", \"Fish swim in the water.\", \"A book lies open on the table.\"]",
        "batch_size": 32,
        "convert_to_numpy": True,
        "normalize_embeddings": True
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run nateraw/bge-large-en-v1.5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "nateraw/bge-large-en-v1.5:9cf9f015a9cb9c61d1a2610659cdac4a4ca222f2d3707a68517b18c198a9add1",
    "input": {
      "texts": "[\\"In the water, fish are swimming.\\", \\"Fish swim in the water.\\", \\"A book lies open on the table.\\"]",
      "batch_size": 32,
      "convert_to_numpy": true,
      "normalize_embeddings": true
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

https://replicate.delivery/pbxt/bkf7f94q2qp2OE9cP7XbFy3Tee3x01i1SKveJ1syjonv5VYNC/embeddings.npy

{
  "completed_at": "2023-10-05T08:54:37.825893Z",
  "created_at": "2023-10-05T08:53:16.508248Z",
  "data_removed": false,
  "error": null,
  "id": "wnn37y3boxihxnv2kyrk4atkiu",
  "input": {
    "path": null,
    "texts": "[\"In the water, fish are swimming.\", \"Fish swim in the water.\", \"A book lies open on the table.\"]",
    "batch_size": 32,
    "convert_to_numpy": true,
    "normalize_embeddings": true
  },
  "logs": "Torch cuda available True\ntorch cuda.get_device_name(0) NVIDIA A40\nort.get_available_providers() ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider']\nParameter 'function'=<function Predictor.predict.<locals>.process at 0x7fc2940b2820> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. Make sure your transforms and parameters are serializable with pickle or dill for the dataset fingerprinting and caching to work. If you reuse this transform, the caching mechanism will consider it to be different from the previous calls and recompute everything. This warning is only showed once. Subsequent hashing failures won't be showed.\nMap:   0%|          | 0/3 [00:00<?, ? examples/s]\nBatches:   0%|          | 0/1 [00:00<?, ?it/s]\u001b[A\nBatches: 100%|██████████| 1/1 [00:00<00:00, 86.99it/s]\nMap: 100%|██████████| 3/3 [00:00<00:00, 201.72 examples/s]\nSaved embeddings to /tmp/embeddings.npy. To load, run `np.load('/tmp/embeddings.npy')`",
  "metrics": {
    "predict_time": 1.023847,
    "total_time": 81.317645
  },
  "output": "https://replicate.delivery/pbxt/bkf7f94q2qp2OE9cP7XbFy3Tee3x01i1SKveJ1syjonv5VYNC/embeddings.npy",
  "started_at": "2023-10-05T08:54:36.802046Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/wnn37y3boxihxnv2kyrk4atkiu",
    "cancel": "https://api.replicate.com/v1/predictions/wnn37y3boxihxnv2kyrk4atkiu/cancel"
  },
  "version": "9cf9f015a9cb9c61d1a2610659cdac4a4ca222f2d3707a68517b18c198a9add1"
}

Generated in

1.0 second

Tweak it Report