| Name | orign JSON |
| Version |
0.1.14
JSON |
| download |
| home_page | None |
| Summary | A Python client for Orign |
| upload_time | 2024-12-12 22:56:21 |
| maintainer | None |
| docs_url | None |
| author | Patrick Barker |
| requires_python | <4.0,>=3.10 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# orign-py
A Python client for [Orign](https://github.com/agentsea/orign)
## Installation
```bash
pip install orign
```
Install the Orign CLI
```sh
curl -fsSL -H "Cache-Control: no-cache" https://storage.googleapis.com/orign/releases/install.sh | bash
```
Login to Orign
```sh
$ orign login
```
## Usage
Get a list of available models
```sh
$ orign get models
```
### Chat
Define which model we would like to use
```python
from orign import ChatModel
model = ChatModel(model="allenai/Molmo-7B-D-0924", provider="vllm")
```
Open a socket connection to the model
```python
model.connect()
```
Chat with the model
```python
model.chat(msg="What's in this image?", image="https://tinyurl.com/2fz6ms35")
```
Stream tokens from the model
```python
for response in model.chat(msg="What is the capital of France?", stream_tokens=True):
print(response)
```
Send a thread of messages to the model
```python
model.chat(prompt=[
{"role": "user", "content": "What is the capital of France?"},
{"role": "assistant", "content": "Paris"},
{"role": "user", "content": "When was it built?"}
])
```
Send a batch of threads to the model
```python
model.chat(batch=[
[{"role": "user", "content": "What is the capital of France?"}, {"role": "assistant", "content": "Paris"}, {"role": "user", "content": "When was it built?"}],
[{"role": "user", "content": "What is the capital of Spain?"}, {"role": "assistant", "content": "Madrid"}, {"role": "user", "content": "When was it built?"}]
]):
```
Use the async API
```python
from orign import AsyncChatModel
model = AsyncChatModel(model="allenai/Molmo-7B-D-0924", provider="vllm")
await model.connect()
async for response in model.chat(
msg="What is the capital of france?", stream_tokens=True
):
print(response)
```
### Embeddings
Define which model we would like to use
```python
from orign import EmbeddingModel
model = EmbeddingModel(provider="sentence-tf", model="clip-ViT-B-32")
```
Embed a text
```python
model.embed(text="What is the capital of France?")
```
Embed an image
```python
model.embed(image="https://example.com/image.jpg")
```
Embed text and image
```python
model.embed(text="What is the capital of France?", image="https://example.com/image.jpg")
```
Use the async API
```python
from orign import AsyncEmbeddingModel
model = AsyncEmbeddingModel(provider="sentence-tf", model="clip-ViT-B-32")
await model.connect()
await model.embed(text="What is the capital of France?")
```
### OCR
Define which model we would like to use
```python
from orign import OCRModel
model = OCRModel(provider="easyocr")
```
Detect text in an image
```python
model.detect(image="https://example.com/image.jpg")
```
Use the async API
```python
from orign import AsyncOCRModel
model = AsyncOCRModel(provider="doctr")
await model.connect()
await model.detect(image="https://example.com/image.jpg")
```
## Examples
See the [examples](examples) directory for more usage examples.
Raw data
{
"_id": null,
"home_page": null,
"name": "orign",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Patrick Barker",
"author_email": "patrickbarkerco@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/61/37/069fcfec2d72ccf9453477f70d613842cb2d29bef92ebc0851ae5e36b57a/orign-0.1.14.tar.gz",
"platform": null,
"description": "# orign-py\n\nA Python client for [Orign](https://github.com/agentsea/orign)\n\n## Installation\n\n```bash\npip install orign\n```\n\nInstall the Orign CLI\n\n```sh\ncurl -fsSL -H \"Cache-Control: no-cache\" https://storage.googleapis.com/orign/releases/install.sh | bash\n```\n\nLogin to Orign\n\n```sh\n$ orign login\n```\n\n## Usage\n\nGet a list of available models\n\n```sh\n$ orign get models\n```\n\n### Chat\n\nDefine which model we would like to use\n\n```python\nfrom orign import ChatModel\n\nmodel = ChatModel(model=\"allenai/Molmo-7B-D-0924\", provider=\"vllm\")\n```\n\nOpen a socket connection to the model\n\n```python\nmodel.connect()\n```\n\nChat with the model\n\n```python\nmodel.chat(msg=\"What's in this image?\", image=\"https://tinyurl.com/2fz6ms35\")\n```\n\nStream tokens from the model\n\n```python\nfor response in model.chat(msg=\"What is the capital of France?\", stream_tokens=True):\n print(response)\n```\n\nSend a thread of messages to the model\n\n```python\nmodel.chat(prompt=[\n {\"role\": \"user\", \"content\": \"What is the capital of France?\"},\n {\"role\": \"assistant\", \"content\": \"Paris\"},\n {\"role\": \"user\", \"content\": \"When was it built?\"}\n])\n```\n\nSend a batch of threads to the model\n\n```python\nmodel.chat(batch=[\n [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}, {\"role\": \"assistant\", \"content\": \"Paris\"}, {\"role\": \"user\", \"content\": \"When was it built?\"}],\n [{\"role\": \"user\", \"content\": \"What is the capital of Spain?\"}, {\"role\": \"assistant\", \"content\": \"Madrid\"}, {\"role\": \"user\", \"content\": \"When was it built?\"}]\n]):\n```\n\nUse the async API\n\n```python\nfrom orign import AsyncChatModel\n\nmodel = AsyncChatModel(model=\"allenai/Molmo-7B-D-0924\", provider=\"vllm\")\nawait model.connect()\n\nasync for response in model.chat(\n msg=\"What is the capital of france?\", stream_tokens=True\n):\n print(response)\n```\n\n### Embeddings\nDefine which model we would like to use\n\n```python\nfrom orign import EmbeddingModel\n\nmodel = EmbeddingModel(provider=\"sentence-tf\", model=\"clip-ViT-B-32\")\n```\n\nEmbed a text\n\n```python\nmodel.embed(text=\"What is the capital of France?\")\n```\n\nEmbed an image\n\n```python\nmodel.embed(image=\"https://example.com/image.jpg\")\n```\n\nEmbed text and image\n\n```python\nmodel.embed(text=\"What is the capital of France?\", image=\"https://example.com/image.jpg\")\n```\n\nUse the async API\n\n```python\nfrom orign import AsyncEmbeddingModel\n\nmodel = AsyncEmbeddingModel(provider=\"sentence-tf\", model=\"clip-ViT-B-32\")\nawait model.connect()\n\nawait model.embed(text=\"What is the capital of France?\")\n```\n\n### OCR\n\nDefine which model we would like to use\n\n```python\nfrom orign import OCRModel\n\nmodel = OCRModel(provider=\"easyocr\")\n```\n\nDetect text in an image\n\n```python\nmodel.detect(image=\"https://example.com/image.jpg\")\n```\n\nUse the async API\n\n```python\nfrom orign import AsyncOCRModel\n\nmodel = AsyncOCRModel(provider=\"doctr\")\nawait model.connect()\n\nawait model.detect(image=\"https://example.com/image.jpg\")\n```\n\n## Examples\n\nSee the [examples](examples) directory for more usage examples.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Python client for Orign",
"version": "0.1.14",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "cfd822e5f1abb8c0bec92846c538aaad4612740be2d35c49d91dca106d0f7a20",
"md5": "4cf2a048eaea516687a5f97bb96aea77",
"sha256": "994e5080da9787601051bf626c71f8b6b8148f22a4b54415217abf3514b319c0"
},
"downloads": -1,
"filename": "orign-0.1.14-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4cf2a048eaea516687a5f97bb96aea77",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 14366,
"upload_time": "2024-12-12T22:56:19",
"upload_time_iso_8601": "2024-12-12T22:56:19.123705Z",
"url": "https://files.pythonhosted.org/packages/cf/d8/22e5f1abb8c0bec92846c538aaad4612740be2d35c49d91dca106d0f7a20/orign-0.1.14-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6137069fcfec2d72ccf9453477f70d613842cb2d29bef92ebc0851ae5e36b57a",
"md5": "f7a5ec2c3bec95bc75bee156c435b9b2",
"sha256": "f4d08781da9e25a8fd40d77bfd23af9eceda0548f8967fb7e745fdb4e03d48ce"
},
"downloads": -1,
"filename": "orign-0.1.14.tar.gz",
"has_sig": false,
"md5_digest": "f7a5ec2c3bec95bc75bee156c435b9b2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 8141,
"upload_time": "2024-12-12T22:56:21",
"upload_time_iso_8601": "2024-12-12T22:56:21.317986Z",
"url": "https://files.pythonhosted.org/packages/61/37/069fcfec2d72ccf9453477f70d613842cb2d29bef92ebc0851ae5e36b57a/orign-0.1.14.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-12 22:56:21",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "orign"
}
