| Name | magics-python JSON |
| Version |
0.0.2
JSON |
| download |
| home_page | None |
| Summary | Python client for Magics's Cloud Platform! |
| upload_time | 2024-10-13 04:21:09 |
| maintainer | None |
| docs_url | None |
| author | Magics AI |
| requires_python | >=3.8 |
| license | Apache-2.0 |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Magics Python API library
The [Magics Python API Library](https://pypi.org/project/magics/) is the official Python client for Magics's API platform, providing a convenient way for interacting with the REST APIs and enables easy integrations with Python 3.8+ applications with easy to use synchronous and asynchronous clients.
## Installation
To install Magics Python Library from PyPI, simply run:
```shell Shell
pip install -e .
```
### Setting up API Key
#### Setting environment variable
```shell
export MAGICS_API_KEY=xxxxx
```
#### Using the client
```python
from magics import Magics
client = Magics(api_key="xxxxx")
```
This repo contains both a Python Library and a CLI. We'll demonstrate how to use both below.
## Usage – Python Client
### Chat Completions
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
response = client.chat.completions.create(
model="mistralai/Mixtral-8x7B-Instruct-v0.1",
messages=[{"role": "user", "content": "tell me about new york"}],
)
print(response.choices[0].message.content)
```
#### Streaming
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
stream = client.chat.completions.create(
model="mistralai/Mixtral-8x7B-Instruct-v0.1",
messages=[{"role": "user", "content": "tell me about new york"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="", flush=True)
```
#### Async usage
```python
import os, asyncio
from magics import AsyncMagics
async_client = AsyncMagics(api_key=os.environ.get("MAGICS_API_KEY"))
messages = [
"What are the top things to do in San Francisco?",
"What country is Paris in?",
]
async def async_chat_completion(messages):
async_client = AsyncMagics(api_key=os.environ.get("MAGICS_API_KEY"))
tasks = [
async_client.chat.completions.create(
model="mistralai/Mixtral-8x7B-Instruct-v0.1",
messages=[{"role": "user", "content": message}],
)
for message in messages
]
responses = await asyncio.gather(*tasks)
for response in responses:
print(response.choices[0].message.content)
asyncio.run(async_chat_completion(messages))
```
### Completions
Completions are for code and language models shown [here](https://docs.magics.ai/docs/inference-models). Below, a code model example is shown.
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
response = client.completions.create(
model="codellama/CodeLlama-34b-Python-hf",
prompt="Write a Next.js component with TailwindCSS for a header component.",
max_tokens=200,
)
print(response.choices[0].text)
```
#### Streaming
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
stream = client.completions.create(
model="codellama/CodeLlama-34b-Python-hf",
prompt="Write a Next.js component with TailwindCSS for a header component.",
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="", flush=True)
```
#### Async usage
```python
import os, asyncio
from magics import AsyncMagics
async_client = AsyncMagics(api_key=os.environ.get("MAGICS_API_KEY"))
prompts = [
"Write a Next.js component with TailwindCSS for a header component.",
"Write a python function for the fibonacci sequence",
]
async def async_chat_completion(prompts):
async_client = AsyncMagics(api_key=os.environ.get("MAGICS_API_KEY"))
tasks = [
async_client.completions.create(
model="codellama/CodeLlama-34b-Python-hf",
prompt=prompt,
)
for prompt in prompts
]
responses = await asyncio.gather(*tasks)
for response in responses:
print(response.choices[0].text)
asyncio.run(async_chat_completion(prompts))
```
### Image generation
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
response = client.images.generate(
prompt="space robots",
model="stabilityai/stable-diffusion-xl-base-1.0",
steps=10,
n=4,
)
print(response.data[0].b64_json)
```
### Embeddings
```python
from typing import List
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
def get_embeddings(texts: List[str], model: str) -> List[List[float]]:
texts = [text.replace("\n", " ") for text in texts]
outputs = client.embeddings.create(model=model, input = texts)
return [outputs.data[i].embedding for i in range(len(texts))]
input_texts = ['Our solar system orbits the Milky Way galaxy at about 515,000 mph']
embeddings = get_embeddings(input_texts, model='magicscomputer/m2-bert-80M-8k-retrieval')
print(embeddings)
```
### Files
The files API is used for fine-tuning and allows developers to upload data to fine-tune on. It also has several methods to list all files, retrive files, and delete files. Please refer to our fine-tuning docs [here](https://docs.magics.ai/docs/fine-tuning-python).
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
client.files.upload(file="somedata.jsonl") # uploads a file
client.files.list() # lists all uploaded files
client.files.retrieve(id="file-d0d318cb-b7d9-493a-bd70-1cfe089d3815") # retrieves a specific file
client.files.retrieve_content(id="file-d0d318cb-b7d9-493a-bd70-1cfe089d3815") # retrieves content of a specific file
client.files.delete(id="file-d0d318cb-b7d9-493a-bd70-1cfe089d3815") # deletes a file
```
### Fine-tunes
The finetune API is used for fine-tuning and allows developers to create finetuning jobs. It also has several methods to list all jobs, retrive statuses and get checkpoints. Please refer to our fine-tuning docs [here](https://docs.magics.ai/docs/fine-tuning-python).
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
client.fine_tuning.create(
training_file = 'file-d0d318cb-b7d9-493a-bd70-1cfe089d3815',
model = 'mistralai/Mixtral-8x7B-Instruct-v0.1',
n_epochs = 3,
n_checkpoints = 1,
batch_size = "max",
learning_rate = 1e-5,
suffix = 'my-demo-finetune',
wandb_api_key = '1a2b3c4d5e.......',
)
client.fine_tuning.list() # lists all fine-tuned jobs
client.fine_tuning.retrieve(id="ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b") # retrieves information on finetune event
client.fine_tuning.cancel(id="ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b") # Cancels a fine-tuning job
client.fine_tuning.list_events(id="ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b") # Lists events of a fine-tune job
client.fine_tuning.download(id="ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b") # downloads compressed fine-tuned model or checkpoint to local disk
```
### Models
This lists all the models that Magics supports.
```python
import os
from magics import Magics
client = Magics(api_key=os.environ.get("MAGICS_API_KEY"))
models = client.models.list()
for model in models:
print(model)
```
## Usage – CLI
### Chat Completions
```bash
magics chat.completions \
--message "system" "You are a helpful assistant named Magics" \
--message "user" "What is your name?" \
--model mistralai/Mixtral-8x7B-Instruct-v0.1
```
The Chat Completions CLI enables streaming tokens to stdout by default. To disable streaming, use `--no-stream`.
### Completions
```bash
magics completions \
"Large language models are " \
--model mistralai/Mixtral-8x7B-v0.1 \
--max-tokens 512 \
--stop "."
```
The Completions CLI enables streaming tokens to stdout by default. To disable streaming, use `--no-stream`.
### Image Generations
```bash
magics images generate \
"space robots" \
--model stabilityai/stable-diffusion-xl-base-1.0 \
--n 4
```
The image is opened in the default image viewer by default. To disable this, use `--no-show`.
### Files
```bash
# Help
magics files --help
# Check file
magics files check example.jsonl
# Upload file
magics files upload example.jsonl
# List files
magics files list
# Retrieve file metadata
magics files retrieve file-6f50f9d1-5b95-416c-9040-0799b2b4b894
# Retrieve file content
magics files retrieve-content file-6f50f9d1-5b95-416c-9040-0799b2b4b894
# Delete remote file
magics files delete file-6f50f9d1-5b95-416c-9040-0799b2b4b894
```
### Fine-tuning
```bash
# Help
magics fine-tuning --help
# Create fine-tune job
magics fine-tuning create \
--model magicscomputer/llama-2-7b-chat \
--training-file file-711d8724-b3e3-4ae2-b516-94841958117d
# List fine-tune jobs
magics fine-tuning list
# Retrieve fine-tune job details
magics fine-tuning retrieve ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b
# List fine-tune job events
magics fine-tuning list-events ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b
# Cancel running job
magics fine-tuning cancel ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b
# Download fine-tuned model weights
magics fine-tuning download ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b
```
### Models
```bash
# Help
magics models --help
# List models
magics models list
```
Raw data
{
"_id": null,
"home_page": null,
"name": "magics-python",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": null,
"author": "Magics AI",
"author_email": "support@magics.ai",
"download_url": "https://files.pythonhosted.org/packages/70/bb/356e804b292d63d86265f39222f4c91abdcdd2ba8c4e8e9313bd2da1e935/magics-python-0.0.2.tar.gz",
"platform": null,
"description": "\n# Magics Python API library\n\nThe [Magics Python API Library](https://pypi.org/project/magics/) is the official Python client for Magics's API platform, providing a convenient way for interacting with the REST APIs and enables easy integrations with Python 3.8+ applications with easy to use synchronous and asynchronous clients.\n\n\n\n## Installation\n\nTo install Magics Python Library from PyPI, simply run:\n\n```shell Shell\n pip install -e . \n```\n\n### Setting up API Key\n\n#### Setting environment variable\n\n```shell\nexport MAGICS_API_KEY=xxxxx\n```\n\n#### Using the client\n\n```python\nfrom magics import Magics\n\nclient = Magics(api_key=\"xxxxx\")\n```\n\nThis repo contains both a Python Library and a CLI. We'll demonstrate how to use both below.\n\n## Usage \u2013 Python Client\n\n### Chat Completions\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\nresponse = client.chat.completions.create(\n model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n messages=[{\"role\": \"user\", \"content\": \"tell me about new york\"}],\n)\nprint(response.choices[0].message.content)\n```\n\n#### Streaming\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\nstream = client.chat.completions.create(\n model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n messages=[{\"role\": \"user\", \"content\": \"tell me about new york\"}],\n stream=True,\n)\n\nfor chunk in stream:\n print(chunk.choices[0].delta.content or \"\", end=\"\", flush=True)\n```\n\n#### Async usage\n\n```python\nimport os, asyncio\nfrom magics import AsyncMagics\n\nasync_client = AsyncMagics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\nmessages = [\n \"What are the top things to do in San Francisco?\",\n \"What country is Paris in?\",\n]\n\nasync def async_chat_completion(messages):\n async_client = AsyncMagics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n tasks = [\n async_client.chat.completions.create(\n model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n messages=[{\"role\": \"user\", \"content\": message}],\n )\n for message in messages\n ]\n responses = await asyncio.gather(*tasks)\n\n for response in responses:\n print(response.choices[0].message.content)\n\nasyncio.run(async_chat_completion(messages))\n```\n\n### Completions\n\nCompletions are for code and language models shown [here](https://docs.magics.ai/docs/inference-models). Below, a code model example is shown.\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\nresponse = client.completions.create(\n model=\"codellama/CodeLlama-34b-Python-hf\",\n prompt=\"Write a Next.js component with TailwindCSS for a header component.\",\n max_tokens=200,\n)\nprint(response.choices[0].text)\n```\n\n#### Streaming\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\nstream = client.completions.create(\n model=\"codellama/CodeLlama-34b-Python-hf\",\n prompt=\"Write a Next.js component with TailwindCSS for a header component.\",\n stream=True,\n)\n\nfor chunk in stream:\n print(chunk.choices[0].delta.content or \"\", end=\"\", flush=True)\n```\n\n#### Async usage\n\n```python\nimport os, asyncio\nfrom magics import AsyncMagics\n\nasync_client = AsyncMagics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\nprompts = [\n \"Write a Next.js component with TailwindCSS for a header component.\",\n \"Write a python function for the fibonacci sequence\",\n]\n\nasync def async_chat_completion(prompts):\n async_client = AsyncMagics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n tasks = [\n async_client.completions.create(\n model=\"codellama/CodeLlama-34b-Python-hf\",\n prompt=prompt,\n )\n for prompt in prompts\n ]\n responses = await asyncio.gather(*tasks)\n\n for response in responses:\n print(response.choices[0].text)\n\nasyncio.run(async_chat_completion(prompts))\n```\n\n### Image generation\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\nresponse = client.images.generate(\n prompt=\"space robots\",\n model=\"stabilityai/stable-diffusion-xl-base-1.0\",\n steps=10,\n n=4,\n)\nprint(response.data[0].b64_json)\n```\n\n### Embeddings\n\n```python\nfrom typing import List\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\ndef get_embeddings(texts: List[str], model: str) -> List[List[float]]:\n texts = [text.replace(\"\\n\", \" \") for text in texts]\n outputs = client.embeddings.create(model=model, input = texts)\n return [outputs.data[i].embedding for i in range(len(texts))]\n\ninput_texts = ['Our solar system orbits the Milky Way galaxy at about 515,000 mph']\nembeddings = get_embeddings(input_texts, model='magicscomputer/m2-bert-80M-8k-retrieval')\n\nprint(embeddings)\n```\n\n### Files\n\nThe files API is used for fine-tuning and allows developers to upload data to fine-tune on. It also has several methods to list all files, retrive files, and delete files. Please refer to our fine-tuning docs [here](https://docs.magics.ai/docs/fine-tuning-python).\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\nclient.files.upload(file=\"somedata.jsonl\") # uploads a file\nclient.files.list() # lists all uploaded files\nclient.files.retrieve(id=\"file-d0d318cb-b7d9-493a-bd70-1cfe089d3815\") # retrieves a specific file\nclient.files.retrieve_content(id=\"file-d0d318cb-b7d9-493a-bd70-1cfe089d3815\") # retrieves content of a specific file\nclient.files.delete(id=\"file-d0d318cb-b7d9-493a-bd70-1cfe089d3815\") # deletes a file\n```\n\n### Fine-tunes\n\nThe finetune API is used for fine-tuning and allows developers to create finetuning jobs. It also has several methods to list all jobs, retrive statuses and get checkpoints. Please refer to our fine-tuning docs [here](https://docs.magics.ai/docs/fine-tuning-python).\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\nclient.fine_tuning.create(\n training_file = 'file-d0d318cb-b7d9-493a-bd70-1cfe089d3815',\n model = 'mistralai/Mixtral-8x7B-Instruct-v0.1',\n n_epochs = 3,\n n_checkpoints = 1,\n batch_size = \"max\",\n learning_rate = 1e-5,\n suffix = 'my-demo-finetune',\n wandb_api_key = '1a2b3c4d5e.......',\n)\nclient.fine_tuning.list() # lists all fine-tuned jobs\nclient.fine_tuning.retrieve(id=\"ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\") # retrieves information on finetune event\nclient.fine_tuning.cancel(id=\"ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\") # Cancels a fine-tuning job\nclient.fine_tuning.list_events(id=\"ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\") # Lists events of a fine-tune job\nclient.fine_tuning.download(id=\"ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\") # downloads compressed fine-tuned model or checkpoint to local disk\n```\n\n### Models\n\nThis lists all the models that Magics supports.\n\n```python\nimport os\nfrom magics import Magics\n\nclient = Magics(api_key=os.environ.get(\"MAGICS_API_KEY\"))\n\nmodels = client.models.list()\n\nfor model in models:\n print(model)\n```\n\n## Usage \u2013 CLI\n\n### Chat Completions\n\n```bash\nmagics chat.completions \\\n --message \"system\" \"You are a helpful assistant named Magics\" \\\n --message \"user\" \"What is your name?\" \\\n --model mistralai/Mixtral-8x7B-Instruct-v0.1\n```\n\nThe Chat Completions CLI enables streaming tokens to stdout by default. To disable streaming, use `--no-stream`.\n\n### Completions\n\n```bash\nmagics completions \\\n \"Large language models are \" \\\n --model mistralai/Mixtral-8x7B-v0.1 \\\n --max-tokens 512 \\\n --stop \".\"\n```\n\nThe Completions CLI enables streaming tokens to stdout by default. To disable streaming, use `--no-stream`.\n\n### Image Generations\n\n```bash\nmagics images generate \\\n \"space robots\" \\\n --model stabilityai/stable-diffusion-xl-base-1.0 \\\n --n 4\n```\n\nThe image is opened in the default image viewer by default. To disable this, use `--no-show`.\n\n### Files\n\n```bash\n# Help\nmagics files --help\n\n# Check file\nmagics files check example.jsonl\n\n# Upload file\nmagics files upload example.jsonl\n\n# List files\nmagics files list\n\n# Retrieve file metadata\nmagics files retrieve file-6f50f9d1-5b95-416c-9040-0799b2b4b894\n\n# Retrieve file content\nmagics files retrieve-content file-6f50f9d1-5b95-416c-9040-0799b2b4b894\n\n# Delete remote file\nmagics files delete file-6f50f9d1-5b95-416c-9040-0799b2b4b894\n```\n\n### Fine-tuning\n\n```bash\n# Help\nmagics fine-tuning --help\n\n# Create fine-tune job\nmagics fine-tuning create \\\n --model magicscomputer/llama-2-7b-chat \\\n --training-file file-711d8724-b3e3-4ae2-b516-94841958117d\n\n# List fine-tune jobs\nmagics fine-tuning list\n\n# Retrieve fine-tune job details\nmagics fine-tuning retrieve ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\n\n# List fine-tune job events\nmagics fine-tuning list-events ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\n\n# Cancel running job\nmagics fine-tuning cancel ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\n\n# Download fine-tuned model weights\nmagics fine-tuning download ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b\n```\n\n### Models\n\n```bash\n# Help\nmagics models --help\n\n# List models\nmagics models list\n```\n\n\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Python client for Magics's Cloud Platform!",
"version": "0.0.2",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1ec4ab1fd48789cb685b15b1ea0906113f2638aebbd3bd8a7a88738f6d254b23",
"md5": "2ea72ead25d29cbb98be343d5195387d",
"sha256": "a25893fd0ad59c87992a6bb48f27ca0af3df8d9d3bb6dfee0bfcabdf5e5ac77b"
},
"downloads": -1,
"filename": "magics_python-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2ea72ead25d29cbb98be343d5195387d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 69312,
"upload_time": "2024-10-13T04:21:08",
"upload_time_iso_8601": "2024-10-13T04:21:08.058759Z",
"url": "https://files.pythonhosted.org/packages/1e/c4/ab1fd48789cb685b15b1ea0906113f2638aebbd3bd8a7a88738f6d254b23/magics_python-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "70bb356e804b292d63d86265f39222f4c91abdcdd2ba8c4e8e9313bd2da1e935",
"md5": "c414efbc70e783123b1ad176c0dac183",
"sha256": "40a916244ca7c206c3bbe8620f21635b4759c4edbd4a4ad513f6e35e08d48a70"
},
"downloads": -1,
"filename": "magics-python-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "c414efbc70e783123b1ad176c0dac183",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 50212,
"upload_time": "2024-10-13T04:21:09",
"upload_time_iso_8601": "2024-10-13T04:21:09.550339Z",
"url": "https://files.pythonhosted.org/packages/70/bb/356e804b292d63d86265f39222f4c91abdcdd2ba8c4e8e9313bd2da1e935/magics-python-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-13 04:21:09",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "magics-python"
}
