Fine-tune

Upload a file

Please follow to the bedrock file upload guide for more details.

Create a fine-tuning job

from portkey_ai import Portkey

# Initialize the Portkey client

portkey = Portkey(
api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

fine_tune_job = portkey.fine_tuning.jobs.create(
    training_file="file_id", # encoded s3 file URI of the training data.
    model="model_id", # ex: modelId from bedrock for fine-tuning
    hyperparameters={
    "n_epochs": 1
    },
    role_arn="role_arn", # service role arn for bedrock job to assume when running.
    job_name="job_name", # name for the job, optional will created random if not provided.
    validation_file="file_id", # optional, must be encoded s3 file URI.
    suffix="finetuned_model_name",
    model_type="text" # optional, chat or text.
  )

print(fine_tune_job)

from portkey_ai import Portkey

# Initialize the Portkey client

portkey = Portkey(
api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

fine_tune_job = portkey.fine_tuning.jobs.create(
    training_file="file_id", # encoded s3 file URI of the training data.
    model="model_id", # ex: modelId from bedrock for fine-tuning
    hyperparameters={
    "n_epochs": 1
    },
    role_arn="role_arn", # service role arn for bedrock job to assume when running.
    job_name="job_name", # name for the job, optional will created random if not provided.
    validation_file="file_id", # optional, must be encoded s3 file URI.
    suffix="finetuned_model_name",
    model_type="text" # optional, chat or text.
  )

print(fine_tune_job)

import { Portkey } from "portkey-ai";
# Initialize the Portkey client
const portkey = Portkey(
    apiKey="PORTKEY_API_KEY",  // Replace with your Portkey API key
    virtualKey="VIRTUAL_KEY"   // Add your provider's virtual key
)

(async () => {
    const fine_tune_job = await portkey.fineTuning.jobs.create(
      training_file:"file_id", // encoded s3 file URI of the training data.
      model:"model_id", // ex: modelId from bedrock for fine-tuning
      hyperparameters: {
        "n_epochs": 1
      },
      role_arn: "role_arn", // service role arn for bedrock job to assume when running.
      job_name: "job_name", // name for the job, optional will created random if not provided.
      validation_file: "file_id", // optional, must be encoded s3 file URI.
      suffix: "finetuned_model_name",
      model_type: "text" // optional, chat or text.
    )

  console.log(fine_tune_job)
})();

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

openai = OpenAI(
    api_key='OPENAI_API_KEY',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        virtual_key="VIRTUAL_KEY",
        api_key="PORTKEY_API_KEY"
    )
)

fine_tune_job = openai.fine_tuning.jobs.create(
    training_file="file_id", # encoded s3 file URI of the training data.
    model="model_id", # bedrock modelId for fine-tuning
    hyperparameters={
      "n_epochs": 1
    },
    role_arn="role_arn", # service role arn for bedrock job to assume when running.
    job_name="job_name", # name for the job, optional will created random if not provided.
    validation_file="file_id", # optional, must be encoded s3 file URI.
    suffix="finetuned_model_name",
    model_type="text" # optional, chat or text.
  )

print(fine_tune_job)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const openai = new OpenAI({
  apiKey: 'OPENAI_API_KEY', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    virtualKey: "VIRTUAL_KEY",
    apiKey: "PORTKEY_API_KEY" // defaults to process.env["PORTKEY_API_KEY"]
  })
});

(async () => {
    const fine_tune_job = await openai.fineTuning.jobs.create({
      training_file: "file_id", // encoded s3 file URI of the training data.
      model: "model_id", // ex: `modelId` from bedrock for fine-tuning
      hyperparameters: {
        "n_epochs": 1
      },
      role_arn: "role_arn", // service role arn for bedrock job to assume when running.
      job_name: "job_name", // name for the job, optional will created random if not provided.
      validation_file: "file_id", // optional, must be encoded s3 file URI.
      suffix: "finetuned_model_name",
      model_type: "text" // optional, chat or text.
    });

  console.log(fine_tune_job)
})();

curl \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: <api_key>' \
--header 'x-portkey-virtual-key: <virtual_key>' \
--header 'x-portkey-aws-s3-bucket: <s3_bucket>' \
--data '{
  "model": "<model_id>",
  "model_type": "text", #chat or text
  "suffix": "<finetune_model_name>",
  "training_file": "<s3_path.jsonl>",
  "role_arn": "<role_arn>",
  "job_name": "<job_name>",
  "hyperparameters": {
    "n_epochs": 1
  }
}' \
'https://api.portkey.ai/v1/fine_tuning/jobs'

Notes:

Bedrock fine-tuning dataset format is a little bit different from OpenAI’s fine-tuning dataset format.
model_type field is required for the dataset transformation, currently gateway does the following dataset transformation:
- chat -> text-to-text
- chat -> chat.
model param should be the ModelID that is required for fine-tuning not for the inference. ModelID is different for inference and fine-tuning.

List of supported finetune models and their IDs are available at Bedrock documentation

List Fine-tuning Jobs

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

# List all fine-tuning jobs
jobs = portkey.fine_tuning.jobs.list(
    limit=10  # Optional: Number of jobs to retrieve (default: 20)
)

print(jobs)

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

# List all fine-tuning jobs
jobs = portkey.fine_tuning.jobs.list(
    limit=10  # Optional: Number of jobs to retrieve (default: 20)
)

print(jobs)

import { Portkey } from "portkey-ai";

// Initialize the Portkey client
const portkey = Portkey({
    apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
    virtualKey: "VIRTUAL_KEY"   // Add your provider's virtual key
});

(async () => {
    // List all fine-tuning jobs
    const jobs = await portkey.fineTuning.jobs.list({
        limit: 10  // Optional: Number of jobs to retrieve (default: 20)
    });

    console.log(jobs);
})();

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

openai = OpenAI(
    api_key='OPENAI_API_KEY',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        virtual_key="VIRTUAL_KEY",
        api_key="PORTKEY_API_KEY"
    )
)

# List all fine-tuning jobs
jobs = openai.fine_tuning.jobs.list(
    limit=10  # Optional: Number of jobs to retrieve (default: 20)
)

print(jobs)

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

const openai = new OpenAI({
    apiKey: 'OPENAI_API_KEY',
    baseURL: PORTKEY_GATEWAY_URL,
    defaultHeaders: createHeaders({
        virtualKey: "VIRTUAL_KEY",
        apiKey: "PORTKEY_API_KEY"
    })
});

(async () => {
    // List all fine-tuning jobs
    const jobs = await openai.fineTuning.jobs.list({
        limit: 10  // Optional: Number of jobs to retrieve (default: 20)
    });

    console.log(jobs);
})();

curl \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: <api_key>' \
--header 'x-portkey-virtual-key: <virtual_key>' \
'https://api.portkey.ai/v1/fine_tuning/jobs?limit=10'

Retrieve Fine-tuning Job

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

# Retrieve a specific fine-tuning job
job = portkey.fine_tuning.jobs.retrieve(
    job_id="job_id"  # The ID of the fine-tuning job to retrieve
)

print(job)

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

# Retrieve a specific fine-tuning job
job = portkey.fine_tuning.jobs.retrieve(
    job_id="job_id"  # The ID of the fine-tuning job to retrieve
)

print(job)

import { Portkey } from "portkey-ai";

// Initialize the Portkey client
const portkey = Portkey({
    apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
    virtualKey: "VIRTUAL_KEY"   // Add your provider's virtual key
});

(async () => {
    // Retrieve a specific fine-tuning job
    const job = await portkey.fineTuning.jobs.retrieve({
        job_id: "job_id"  // The ID of the fine-tuning job to retrieve
    });

    console.log(job);
})();

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

openai = OpenAI(
    api_key='OPENAI_API_KEY',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        virtual_key="VIRTUAL_KEY",
        api_key="PORTKEY_API_KEY"
    )
)

# Retrieve a specific fine-tuning job
job = openai.fine_tuning.jobs.retrieve(
    fine_tuning_job_id="job_id"  # The ID of the fine-tuning job to retrieve
)

print(job)

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

const openai = new OpenAI({
    apiKey: 'OPENAI_API_KEY',
    baseURL: PORTKEY_GATEWAY_URL,
    defaultHeaders: createHeaders({
        virtualKey: "VIRTUAL_KEY",
        apiKey: "PORTKEY_API_KEY"
    })
});

(async () => {
    // Retrieve a specific fine-tuning job
    const job = await openai.fineTuning.jobs.retrieve(
        "job_id"  // The ID of the fine-tuning job to retrieve
    );

    console.log(job);
})();

curl \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: <api_key>' \
--header 'x-portkey-virtual-key: <virtual_key>' \
'https://api.portkey.ai/v1/fine_tuning/jobs/<job_id>'

Cancel Fine-tuning Job

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

# Cancel a fine-tuning job
cancelled_job = portkey.fine_tuning.jobs.cancel(
    job_id="job_id"  # The ID of the fine-tuning job to cancel
)

print(cancelled_job)

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY" # Add your provider's virtual key
)

# Cancel a fine-tuning job
cancelled_job = portkey.fine_tuning.jobs.cancel(
    job_id="job_id"  # The ID of the fine-tuning job to cancel
)

print(cancelled_job)

import { Portkey } from "portkey-ai";

// Initialize the Portkey client
const portkey = Portkey({
    apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
    virtualKey: "VIRTUAL_KEY"   // Add your provider's virtual key
});

(async () => {
    // Cancel a fine-tuning job
    const cancelledJob = await portkey.fineTuning.jobs.cancel({
        job_id: "job_id"  // The ID of the fine-tuning job to cancel
    });

    console.log(cancelledJob);
})();

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

openai = OpenAI(
    api_key='OPENAI_API_KEY',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        virtual_key="VIRTUAL_KEY",
        api_key="PORTKEY_API_KEY"
    )
)

# Cancel a fine-tuning job
cancelled_job = openai.fine_tuning.jobs.cancel(
    fine_tuning_job_id="job_id"  # The ID of the fine-tuning job to cancel
)

print(cancelled_job)

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

const openai = new OpenAI({
    apiKey: 'OPENAI_API_KEY',
    baseURL: PORTKEY_GATEWAY_URL,
    defaultHeaders: createHeaders({
        virtualKey: "VIRTUAL_KEY",
        apiKey: "PORTKEY_API_KEY"
    })
});

(async () => {
    // Cancel a fine-tuning job
    const cancelledJob = await openai.fineTuning.jobs.cancel(
        "job_id"  // The ID of the fine-tuning job to cancel
    );

    console.log(cancelledJob);
})();

curl \
--request POST \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: <api_key>' \
--header 'x-portkey-virtual-key: <virtual_key>' \
'https://api.portkey.ai/v1/fine_tuning/jobs/<job_id>/cancel'

References

Fine-tune Support types for models: Link
Fine-tuning Documentation: Link

Ecosystem

LLMs

Vector Databases

Agents

Libraries

Upload a file

Create a fine-tuning job

List Fine-tuning Jobs

Retrieve Fine-tuning Job

Cancel Fine-tuning Job

References

Ecosystem

LLMs

Vector Databases

Agents

Libraries

​Upload a file

​Create a fine-tuning job

​List Fine-tuning Jobs

​Retrieve Fine-tuning Job

​Cancel Fine-tuning Job

​References

Upload a file

Create a fine-tuning job

List Fine-tuning Jobs

Retrieve Fine-tuning Job

Cancel Fine-tuning Job

References