mirror of
https://github.com/openai/openai-cookbook
synced 2024-11-04 06:00:33 +00:00
Merge pull request #50 from cmurtz-msft/azure-openai-ga
Azure OpenAI GA
This commit is contained in:
Ted Sanders
GitHub
commit
46b9e5cd62
227
examples/azure/completions.ipynb
Normal file
227
examples/azure/completions.ipynb
Normal file
@ -0,0 +1,227 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Azure completions example\n",
|
||||
"In this example we'll try to go over all operations needed to get completions working using the Azure endpoints. \\\n",
|
||||
"This example focuses on completions but also touches on some other operations that are also available using the API. This example is meant to be a quick way of showing simple operations and is not meant as a tutorial."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import openai\n",
|
||||
"from openai import cli"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"For the following sections to work properly we first have to setup some things. Let's start with the `api_base` and `api_version`. To find your `api_base` go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"openai.api_version = '2022-12-01'\n",
|
||||
"openai.api_base = '' # Please add your endpoint here"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We next have to setup the `api_type` and `api_key`. We can either get the key from the portal or we can get it through Microsoft Active Directory Authentication. Depending on this the `api_type` is either `azure` or `azure_ad`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup: Portal\n",
|
||||
"Let's first look at getting the key from the portal. Go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for one of the \"Keys\" values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"openai.api_type = 'azure'\n",
|
||||
"openai.api_key = '' # Please add your api key here"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Setup: Microsoft Active Directory Authentication\n",
|
||||
"Let's now see how we can get a key via Microsoft Active Directory Authentication. Uncomment the following code if you want to use Active Directory Authentication instead of keys from the portal."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# from azure.identity import DefaultAzureCredential\n",
|
||||
"\n",
|
||||
"# default_credential = DefaultAzureCredential()\n",
|
||||
"# token = default_credential.get_token(\"https://cognitiveservices.azure.com/.default\")\n",
|
||||
"\n",
|
||||
"# openai.api_type = 'azure_ad'\n",
|
||||
"# openai.api_key = token.token"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deployments\n",
|
||||
"In this section we are going to create a deployment using the `text-davinci-002` model that we can then use to create completions."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deployments: Create manually\n",
|
||||
"Create a new deployment by going to your Resource in your portal under \"Resource Management\" -> \"Model deployments\". Select `text-davinci-002` as the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Deployments: Create programatically\n",
|
||||
"We can also create a deployment using code:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = \"text-davinci-002\"\n",
|
||||
"\n",
|
||||
"# Now let's create the deployment\n",
|
||||
"print(f'Creating a new deployment with model: {model}')\n",
|
||||
"result = openai.Deployment.create(model=model, scale_settings={\"scale_type\":\"standard\"})\n",
|
||||
"deployment_id = result[\"id\"]\n",
|
||||
"print(f'Successfully created deployment with id: {deployment_id}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Deployments: Wait for deployment to succeed\n",
|
||||
"Now let's check the status of the newly created deployment and wait till it is succeeded."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(f'Checking for deployment status.')\n",
|
||||
"resp = openai.Deployment.retrieve(id=deployment_id)\n",
|
||||
"status = resp[\"status\"]\n",
|
||||
"print(f'Deployment {deployment_id} has status: {status}')\n",
|
||||
"while status not in [\"succeeded\", \"failed\"]:\n",
|
||||
" resp = openai.Deployment.retrieve(id=deployment_id)\n",
|
||||
" status = resp[\"status\"]\n",
|
||||
" print(f'Deployment {deployment_id} has status: {status}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Completions\n",
|
||||
"Now let's send a sample completion to the deployment."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = \"The food was delicious and the waiter\"\n",
|
||||
"completion = openai.Completion.create(deployment_id=deployment_id,\n",
|
||||
" prompt=prompt, stop=\".\", temperature=0)\n",
|
||||
" \n",
|
||||
"print(f\"{prompt}{completion['choices'][0]['text']}.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Deployments: Delete\n",
|
||||
"Finally let's delete the deployment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(f'Deleting deployment: {deployment_id}')\n",
|
||||
"openai.Deployment.delete(sid=deployment_id)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.8"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "3a5103089ab7e7c666b279eeded403fcec76de49a40685dbdfe9f9c78ad97c17"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@ -1,12 +1,13 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Azure embeddings example\n",
|
||||
"In this example we'll try to go over all operations for embeddings that can be done using the Azure endpoints. \\\n",
|
||||
"This example focuses on finetuning but touches on the majority of operations that are also available using the API. This example is meant to be a quick way of showing simple operations and is not meant as a tutorial."
|
||||
"This example focuses on embeddings but also touches some other operations that are also available using the API. This example is meant to be a quick way of showing simple operations and is not meant as a tutorial."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -20,12 +21,39 @@
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"In the following section the endpoint and key need to be set up of the next sections to work. \\\n",
|
||||
"Please go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value and one of the Keys. They will act as api_base and api_key in the code below."
|
||||
"For the following sections to work properly we first have to setup some things. Let's start with the `api_base` and `api_version`. To find your `api_base` go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"openai.api_version = '2022-12-01'\n",
|
||||
"openai.api_base = '' # Please add your endpoint here"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We next have to setup the `api_type` and `api_key`. We can either get the key from the portal or we can get it through Microsoft Active Directory Authentication. Depending on this the `api_type` is either `azure` or `azure_ad`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup: Portal\n",
|
||||
"Let's first look at getting the key from the portal. Go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for one of the \"Keys\" values."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -34,11 +62,32 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"openai.api_key = '' # Please add your api key here\n",
|
||||
"openai.api_base = '' # Please add your endpoint here\n",
|
||||
"\n",
|
||||
"openai.api_type = 'azure'\n",
|
||||
"openai.api_version = '2022-03-01-preview' # this may change in the future"
|
||||
"openai.api_key = '' # Please add your api key here"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Setup: Microsoft Active Directory Authentication\n",
|
||||
"Let's now see how we can get a key via Microsoft Active Directory Authentication. Uncomment the following code if you want to use Active Directory Authentication instead of keys from the portal."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# from azure.identity import DefaultAzureCredential\n",
|
||||
"\n",
|
||||
"# default_credential = DefaultAzureCredential()\n",
|
||||
"# token = default_credential.get_token(\"https://cognitiveservices.azure.com/.default\")\n",
|
||||
"\n",
|
||||
"# openai.api_type = 'azure_ad'\n",
|
||||
"# openai.api_key = token.token"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -46,22 +95,22 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deployments\n",
|
||||
"In this section we are going to create a deployment using the finetune model that we just adapted and then used the deployment to create a simple completion operation."
|
||||
"In this section we are going to create a deployment that we can use to create embeddings."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deployments: Create Manually\n",
|
||||
"Let's create a deployment using the text-similarity-curie-001 engine. You can create a new deployment by going to your Resource in your portal under \"Resource Management\" -> \"Deployments\"."
|
||||
"### Deployments: Create manually\n",
|
||||
"Let's create a deployment using the `text-similarity-curie-001` model. Create a new deployment by going to your Resource in your portal under \"Resource Management\" -> \"Model deployments\"."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Deployments: Create Programatically\n",
|
||||
"### (Optional) Deployments: Create programatically\n",
|
||||
"We can also create a deployment using code:"
|
||||
]
|
||||
},
|
||||
@ -113,18 +162,24 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print('While deployment running, selecting a completed one.')\n",
|
||||
"print('While deployment running, selecting a completed one that supports embeddings.')\n",
|
||||
"deployment_id = None\n",
|
||||
"result = openai.Deployment.list()\n",
|
||||
"for deployment in result.data:\n",
|
||||
" if deployment[\"status\"] == \"succeeded\":\n",
|
||||
" deployment_id = deployment[\"id\"]\n",
|
||||
" break\n",
|
||||
" if deployment[\"status\"] != \"succeeded\":\n",
|
||||
" continue\n",
|
||||
" \n",
|
||||
" model = openai.Model.retrieve(deployment[\"model\"])\n",
|
||||
" if model[\"capabilities\"][\"embeddings\"] != True:\n",
|
||||
" continue\n",
|
||||
" \n",
|
||||
" deployment_id = deployment[\"id\"]\n",
|
||||
" break\n",
|
||||
"\n",
|
||||
"if not deployment_id:\n",
|
||||
" print('No deployment with status: succeeded found.')\n",
|
||||
"else:\n",
|
||||
" print(f'Found a successful deployment with id: {deployment_id}.')"
|
||||
" print(f'Found a succeeded deployment that supports embeddings with id: {deployment_id}.')"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -168,7 +223,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.9.9 ('openai')",
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@ -182,12 +237,11 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.9"
|
||||
"version": "3.10.8"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97"
|
||||
"hash": "3a5103089ab7e7c666b279eeded403fcec76de49a40685dbdfe9f9c78ad97c17"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
@ -6,7 +6,7 @@
|
||||
"source": [
|
||||
"# Azure Fine tuning example\n",
|
||||
"In this example we'll try to go over all operations that can be done using the Azure endpoints and their differences with the openAi endpoints (if any).<br>\n",
|
||||
"This example focuses on finetuning but touches on the majority of operations that are also available using the API. This example is meant to be a quick way of showing simple operations and is not meant as a finetune model adaptation tutorial.\n"
|
||||
"This example focuses on finetuning but also touches on the majority of operations that are available using the API. This example is meant to be a quick way of showing simple operations and is not meant as a finetune model adaptation tutorial.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -24,7 +24,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"In the following section the endpoint and key need to be set up of the next sections to work.<br> Please go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value and one of the Keys. They will act as api_base and api_key in the code below."
|
||||
"For the following sections to work properly we first have to setup some things. Let's start with the `api_base` and `api_version`. To find your `api_base` go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -33,19 +33,23 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"openai.api_key = '' # Please add your api key here\n",
|
||||
"openai.api_base = '' # Please add your endpoint here\n",
|
||||
"\n",
|
||||
"openai.api_type = 'azure'\n",
|
||||
"openai.api_version = '2022-03-01-preview' # this may change in the future"
|
||||
"openai.api_version = '2022-12-01'\n",
|
||||
"openai.api_base = '' # Please add your endpoint here"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Microsoft Active Directory Authentication\n",
|
||||
"Instead of key based authentication, you can use Active Directory to authenticate using credential tokens. Uncomment the next code section to use credential based authentication:"
|
||||
"We next have to setup the `api_type` and `api_key`. We can either get the key from the portal or we can get it through Microsoft Active Directory Authentication. Depending on this the `api_type` is either `azure` or `azure_ad`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup: Portal\n",
|
||||
"Let's first look at getting the key from the portal. Go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for one of the \"Keys\" values."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -54,19 +58,32 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\"\"\"\n",
|
||||
"from azure.identity import DefaultAzureCredential\n",
|
||||
"openai.api_type = 'azure'\n",
|
||||
"openai.api_key = '' # Please add your api key here"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### (Optional) Setup: Microsoft Active Directory Authentication\n",
|
||||
"Let's now see how we can get a key via Microsoft Active Directory Authentication. Uncomment the following code if you want to use Active Directory Authentication instead of keys from the portal."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# from azure.identity import DefaultAzureCredential\n",
|
||||
"\n",
|
||||
"default_credential = DefaultAzureCredential()\n",
|
||||
"token = default_credential.get_token(\"https://cognitiveservices.azure.com/.default\")\n",
|
||||
"# default_credential = DefaultAzureCredential()\n",
|
||||
"# token = default_credential.get_token(\"https://cognitiveservices.azure.com/.default\")\n",
|
||||
"\n",
|
||||
"openai.api_type = 'azure_ad'\n",
|
||||
"openai.api_key = token.token\n",
|
||||
"openai.api_version = '2022-03-01-preview' # this may change in the future\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"openai.api_base = '' # Please add your endpoint here\n",
|
||||
"\"\"\""
|
||||
"# openai.api_type = 'azure_ad'\n",
|
||||
"# openai.api_key = token.token"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -89,9 +106,9 @@
|
||||
"training_file_name = 'training.jsonl'\n",
|
||||
"validation_file_name = 'validation.jsonl'\n",
|
||||
"\n",
|
||||
"sample_data = [{\"prompt\": \"When I go to the store, I want an\", \"completion\": \"apple\"},\n",
|
||||
" {\"prompt\": \"When I go to work, I want a\", \"completion\": \"coffe\"},\n",
|
||||
" {\"prompt\": \"When I go home, I want a\", \"completion\": \"soda\"}]\n",
|
||||
"sample_data = [{\"prompt\": \"When I go to the store, I want an\", \"completion\": \"apple.\"},\n",
|
||||
" {\"prompt\": \"When I go to work, I want a\", \"completion\": \"coffee.\"},\n",
|
||||
" {\"prompt\": \"When I go home, I want a\", \"completion\": \"soda.\"}]\n",
|
||||
"\n",
|
||||
"print(f'Generating the training file: {training_file_name}')\n",
|
||||
"with open(training_file_name, 'w') as training_file:\n",
|
||||
@ -141,7 +158,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(f'Deleting already uploaded files.')\n",
|
||||
"print(f'Deleting already uploaded files...')\n",
|
||||
"for id in results:\n",
|
||||
" openai.File.delete(sid = id)\n"
|
||||
]
|
||||
@ -197,7 +214,7 @@
|
||||
"source": [
|
||||
"print(f'Downloading training file: {training_id}')\n",
|
||||
"result = openai.File.download(training_id)\n",
|
||||
"print(result)"
|
||||
"print(result.decode('utf-8'))"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -225,9 +242,12 @@
|
||||
"create_args = {\n",
|
||||
" \"training_file\": training_id,\n",
|
||||
" \"validation_file\": validation_id,\n",
|
||||
" \"model\": \"curie\",\n",
|
||||
" \"model\": \"babbage\",\n",
|
||||
" \"compute_classification_metrics\": True,\n",
|
||||
" \"classification_n_classes\": 3\n",
|
||||
" \"classification_n_classes\": 3,\n",
|
||||
" \"n_epochs\": 20,\n",
|
||||
" \"batch_size\": 3,\n",
|
||||
" \"learning_rate_multiplier\": 0.3\n",
|
||||
"}\n",
|
||||
"resp = openai.FineTune.create(**create_args)\n",
|
||||
"job_id = resp[\"id\"]\n",
|
||||
@ -258,7 +278,7 @@
|
||||
" print(f\"Stream interrupted. Job is still {status}.\")\n",
|
||||
" return\n",
|
||||
"\n",
|
||||
"print('Streaming events for the fine-tuning job: {job_id}')\n",
|
||||
"print(f'Streaming events for the fine-tuning job: {job_id}')\n",
|
||||
"signal.signal(signal.SIGINT, signal_handler)\n",
|
||||
"\n",
|
||||
"events = openai.FineTune.stream_events(job_id)\n",
|
||||
@ -296,7 +316,7 @@
|
||||
"\n",
|
||||
"print('Checking other finetune jobs in the subscription.')\n",
|
||||
"result = openai.FineTune.list()\n",
|
||||
"print(f'Found {len(result)} finetune jobs.')"
|
||||
"print(f'Found {len(result.data)} finetune jobs.')"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -413,10 +433,10 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print('Sending a test completion job')\n",
|
||||
"start_phrase = 'When I go to the store, I want a'\n",
|
||||
"response = openai.Completion.create(deployment_id=deployment_id, prompt=start_phrase, max_tokens=4)\n",
|
||||
"start_phrase = 'When I go home, I want a'\n",
|
||||
"response = openai.Completion.create(deployment_id=deployment_id, prompt=start_phrase, temperature=0, stop=\".\")\n",
|
||||
"text = response['choices'][0]['text'].replace('\\n', '').replace(' .', '.').strip()\n",
|
||||
"print(f'\"{start_phrase} {text}\"')\n"
|
||||
"print(f'\"{start_phrase} {text}.\"')"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -447,7 +467,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.9.9 64-bit ('3.9.9')",
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@ -461,12 +481,11 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.9"
|
||||
"version": "3.10.8"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "cb9817b186a29e4e9713184d901f26c1ee05ad25243d878baff7f31bb1fef480"
|
||||
"hash": "3a5103089ab7e7c666b279eeded403fcec76de49a40685dbdfe9f9c78ad97c17"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
Loading…
Reference in New Issue
Block a user