上传文件

示例用法

import fs from "fs";
import OpenAI from 'openai';
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const client = new OpenAI({
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    apiKey: "PORTKEY_API_KEY",
    virtualKey: "PROVIDER_VIRTUAL_KEY"
  })
});

async function main() {
  const file = await client.files.create({
    file: fs.createReadStream("mydata.jsonl"),
    purpose: "batch",
  });

  console.log(file);
}

main();

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

client = OpenAI(
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        api_key="PORTKEY_API_KEY",
        virtual_key="PROVIDER_VIRTUAL_KEY"
    )
)

upload = client.files.create(
  file=open("mydata.jsonl", "rb"),
  purpose="batch"
)

import fs from "fs";
import Portkey from 'portkey-ai';

const client = new Portkey({
  apiKey: 'PORTKEY_API_KEY',
  virtualKey: 'PROVIDER_VIRTUAL_KEY'
});

async function main() {
  const file = await client.files.create({
    file: fs.createReadStream("mydata.jsonl"),
    purpose: "batch",
  });

  console.log(file);
}

main();

from portkey_ai import Portkey

client = Portkey(
  api_key = "PORTKEY_API_KEY",
  virtual_key = "PROVIDER_VIRTUAL_KEY"
)

upload = client.files.create(
  file=open("mydata.jsonl", "rb"),
  purpose="batch"
)

curl https://api.portkey.ai/v1/files \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
  -F purpose="fine-tune" \
  -F file="@mydata.jsonl"

Upload a file to be used across various endpoints, such as Assistant (<2M tokens), Fine-Tuning, and Batch (<100 MB). Total size of your bucket is 100 GB.

post

/files

Authorizations

x-portkey-api-keystringRequired

x-portkey-virtual-keystringRequired

Body

filestring · binaryRequired

The File object (not file name) to be uploaded.

purposestring · enumRequired

The intended purpose of the uploaded file.

Use "assistants" for Assistants and Message files, "vision" for Assistants image file inputs, "batch" for Batch API, and "fine-tune" for Fine-tuning.

Possible values:

Responses

200

application/json

The File object represents a document that has been uploaded to OpenAI.

idstringRequired

The file identifier, which can be referenced in the API endpoints.

bytesintegerRequired

The size of the file, in bytes.

created_atintegerRequired

The Unix timestamp (in seconds) for when the file was created.

filenamestringRequired

The name of the file.

objectstring · enumRequired

The object type, which is always file.

Possible values:

purposestring · enumRequired

The intended purpose of the file. Supported values are assistants, assistants_output, batch, batch_output, fine-tune, fine-tune-results and vision.

Possible values:

statusstring · enumRequiredDeprecated

Deprecated. The current status of the file, which can be either uploaded, processed, or error.

Possible values:

status_detailsstringOptionalDeprecated

Deprecated. For details on why a fine-tuning training file failed validation, see the error field on fine_tuning.job.

post

/files

curl https://api.portkey.ai/v1/files \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
  -F purpose="fine-tune" \
  -F file="@mydata.jsonl"

200

{
  "id": "text",
  "bytes": 1,
  "created_at": 1,
  "filename": "text",
  "object": "file",
  "purpose": "assistants"
}

Previous文件 Next列出文件

Last updated 1 year ago

hashtag示例用法

hashtagUpload a file to be used across various endpoints, such as Assistant (<2M tokens), Fine-Tuning, and Batch (<100 MB). Total size of your bucket is 100 GB.

示例用法

Upload a file to be used across various endpoints, such as Assistant (<2M tokens), Fine-Tuning, and Batch (<100 MB). Total size of your bucket is 100 GB.