nateraw/bge-large-en-batched – Run with an API on Replicate

nateraw / bge-large-en-batched

Cold

Public
10 runs
L40S

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=nateraw/bge-large-en-batched

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-batched 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-batched:2d008f128c3dad6834ec4323a96766211754f40602e669ad7fdfd6468644c70a",
  {
    input: {
      path: "https://replicate.delivery/pbxt/JdHX0Er26JMM85ryJIH71JG5WVTeehTTipBqsmV2f5XdaS4V/samsum.txt",
      batch_size: 128,
      normalize_embeddings: true
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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-batched using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/bge-large-en-batched:2d008f128c3dad6834ec4323a96766211754f40602e669ad7fdfd6468644c70a",
    input={
        "path": "https://replicate.delivery/pbxt/JdHX0Er26JMM85ryJIH71JG5WVTeehTTipBqsmV2f5XdaS4V/samsum.txt",
        "batch_size": 128,
        "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-batched 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-batched:2d008f128c3dad6834ec4323a96766211754f40602e669ad7fdfd6468644c70a",
    "input": {
      "path": "https://replicate.delivery/pbxt/JdHX0Er26JMM85ryJIH71JG5WVTeehTTipBqsmV2f5XdaS4V/samsum.txt",
      "batch_size": 128,
      "normalize_embeddings": true
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

embeddings.npy

{
  "completed_at": "2023-10-03T02:15:41.603267Z",
  "created_at": "2023-10-03T02:11:30.385163Z",
  "data_removed": false,
  "error": null,
  "id": "43yfqm3bmuiqifdh2cubnkc6fy",
  "input": {
    "path": "https://replicate.delivery/pbxt/JdHX0Er26JMM85ryJIH71JG5WVTeehTTipBqsmV2f5XdaS4V/samsum.txt",
    "batch_size": 128,
    "normalize_embeddings": true
  },
  "logs": "Downloading data files:   0%|          | 0/1 [00:00<?, ?it/s]\nDownloading data files: 100%|██████████| 1/1 [00:00<00:00, 7796.10it/s]\nExtracting data files:   0%|          | 0/1 [00:00<?, ?it/s]\nExtracting data files: 100%|██████████| 1/1 [00:00<00:00, 956.95it/s]\nGenerating train split: 0 examples [00:00, ? examples/s]\nGenerating train split: 14732 examples [00:00, 447452.36 examples/s]\nMap:   0%|          | 0/14732 [00:00<?, ? examples/s]\nMap:   7%|▋         | 1000/14732 [00:12<02:54, 78.52 examples/s]\nMap:  14%|█▎        | 2000/14732 [00:23<02:30, 84.88 examples/s]\nMap:  20%|██        | 3000/14732 [00:34<02:13, 88.12 examples/s]\nMap:  27%|██▋       | 4000/14732 [00:46<02:01, 88.16 examples/s]\nMap:  34%|███▍      | 5000/14732 [00:57<01:50, 88.05 examples/s]\nMap:  34%|███▍      | 5000/14732 [01:07<01:50, 88.05 examples/s]\nMap:  41%|████      | 6000/14732 [01:08<01:37, 89.76 examples/s]\nMap:  48%|████▊     | 7000/14732 [01:19<01:27, 88.67 examples/s]\nMap:  54%|█████▍    | 8000/14732 [01:30<01:15, 89.13 examples/s]\nMap:  54%|█████▍    | 8000/14732 [01:41<01:15, 89.13 examples/s]\nMap:  61%|██████    | 9000/14732 [01:42<01:04, 88.81 examples/s]\nMap:  68%|██████▊   | 10000/14732 [01:53<00:53, 88.45 examples/s]\nMap:  75%|███████▍  | 11000/14732 [02:04<00:42, 88.79 examples/s]\nMap:  81%|████████▏ | 12000/14732 [02:15<00:30, 88.88 examples/s]\nMap:  88%|████████▊ | 13000/14732 [02:26<00:19, 89.31 examples/s]\nMap:  88%|████████▊ | 13000/14732 [02:37<00:19, 89.31 examples/s]\nMap:  95%|█████████▌| 14000/14732 [02:38<00:08, 89.62 examples/s]\nMap: 100%|██████████| 14732/14732 [02:46<00:00, 88.49 examples/s]\nMap: 100%|██████████| 14732/14732 [02:46<00:00, 88.39 examples/s]",
  "metrics": {
    "predict_time": 172.671675,
    "total_time": 251.218104
  },
  "output": "https://pbxt.replicate.delivery/feWKGHryXxng70oUvxGekSYJCj11wd1ZJFCCQrL79qfu0KpGB/embeddings.npy",
  "started_at": "2023-10-03T02:12:48.931592Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/43yfqm3bmuiqifdh2cubnkc6fy",
    "cancel": "https://api.replicate.com/v1/predictions/43yfqm3bmuiqifdh2cubnkc6fy/cancel"
  },
  "version": "2d008f128c3dad6834ec4323a96766211754f40602e669ad7fdfd6468644c70a"
}

Generated in

2 minutes 53 seconds

Tweak itReport

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.