| Name | nix-gpt-client JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | None |
| Summary | A Python library for easy interaction with the GPT API, featuring typed requests and responses. |
| upload_time | 2024-05-17 12:43:58 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.11 |
| license | None |
| keywords |
openai
gpt
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# nix-gpt-client
nix-gpt-client is a simple Python library for working with the GPT API. It uses Pydantic to add input and output
schemas, allowing you to manage data structures with ease.
## Table of Contents
- [Installation](#installation)
- [Usage](#usage)
- [License](#license)
## Installation
To install `nix-gpt-client`, you can use `pip`. Python 3.11 or higher is required.
```bash
pip install nix-gpt-client
```
## Usage
1. If you want to use typing, create Pydantic schemas for input and output data structures:
```python
from datetime import datetime
from pydantic import BaseModel, Field
class GPTInput(BaseModel):
time: datetime = Field(description="The current time")
timezone: str = Field(description="The timezone of the current time")
target_timezone: str = Field(description="The target timezone")
class GPTOutput(BaseModel):
target_time: datetime = Field(description="The target time")
```
2. Then create GPTClient object, set schemas, and add system message:
```python
from nix.gptclient import GPTClient, GPTModel, GPTMessageRole, GPTSchemaType
gpt_client = GPTClient(
model=GPTModel.GPT_3_5_TURBO,
top_p=0.5,
presence_penalty=0,
frequency_penalty=0,
temperature=0)
gpt_client.set_schema(GPTInput, GPTSchemaType.input)
gpt_client.set_schema(GPTOutput, GPTSchemaType.output)
gpt_client.add_message(GPTMessageRole.system, """
Take from \'Input JSON schema\' the fields 'time', 'timezone', and 'target_timezone'.
Then generate an Output JSON schema with the field 'target_time', which represents the given 'time' converted
from 'timezone' to 'target_timezone'.
""")
```
3. Add data like user message and call `run` method to get the response:
```python
input_data = {
"time": datetime.now().__str__(),
"timezone": "UTC",
"target_timezone": "America/New_York"
}
gpt_client.add_message(GPTMessageRole.user, input_data)
response = json.loads(gpt_client.run())
```
4. The response will be:
```json
{
"target_time": "2024-05-06T13:04:38.621713-04:00"
}
```
Full example:
```python
import json
from datetime import datetime
from dotenv import load_dotenv
from pydantic import BaseModel, Field
from src import GPTClient, GPTModel, GPTMessageRole, GPTSchemaType
load_dotenv()
class GPTInput(BaseModel):
time: datetime = Field(description="The current time")
timezone: str = Field(description="The timezone of the current time")
target_timezone: str = Field(description="The target timezone")
class GPTOutput(BaseModel):
target_time: datetime = Field(description="The target time")
gpt_client = GPTClient(
model=GPTModel.GPT_3_5_TURBO,
top_p=0.5,
presence_penalty=0,
frequency_penalty=0,
temperature=0)
gpt_client.set_schema(GPTInput, GPTSchemaType.input)
gpt_client.set_schema(GPTOutput, GPTSchemaType.output)
gpt_client.add_message(GPTMessageRole.system, """
Take from \'Input JSON schema\' the fields 'time', 'timezone', and 'target_timezone'.
Then generate an Output JSON schema with the field 'target_time', which represents the given 'time' converted
from 'timezone' to 'target_timezone'.
""")
input_data = {
"time": datetime.now().__str__(),
"timezone": "UTC",
"target_timezone": "America/New_York"
}
gpt_client.add_message(GPTMessageRole.user, input_data)
response = json.loads(gpt_client.run())
print(response)
```
## License
This project is licensed under the MIT License. See the LICENSE file for more details.
Raw data
{
"_id": null,
"home_page": null,
"name": "nix-gpt-client",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": "nks_nix <nikusunix@gmail.com>",
"keywords": "openai, gpt",
"author": null,
"author_email": "nks_nix <nikusunix@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/db/67/eed85fb6203a6c6bf0a1c68daecc4c1ea319d0a377c4047562231718812c/nix_gpt_client-0.1.2.tar.gz",
"platform": null,
"description": "# nix-gpt-client\n\nnix-gpt-client is a simple Python library for working with the GPT API. It uses Pydantic to add input and output\nschemas, allowing you to manage data structures with ease.\n\n## Table of Contents\n\n- [Installation](#installation)\n- [Usage](#usage)\n- [License](#license)\n\n## Installation\n\nTo install `nix-gpt-client`, you can use `pip`. Python 3.11 or higher is required.\n\n```bash\npip install nix-gpt-client\n```\n\n## Usage\n\n1. If you want to use typing, create Pydantic schemas for input and output data structures:\n\n```python\nfrom datetime import datetime\nfrom pydantic import BaseModel, Field\n\n\nclass GPTInput(BaseModel):\n time: datetime = Field(description=\"The current time\")\n timezone: str = Field(description=\"The timezone of the current time\")\n target_timezone: str = Field(description=\"The target timezone\")\n\n\nclass GPTOutput(BaseModel):\n target_time: datetime = Field(description=\"The target time\")\n```\n\n2. Then create GPTClient object, set schemas, and add system message:\n\n```python\nfrom nix.gptclient import GPTClient, GPTModel, GPTMessageRole, GPTSchemaType\n\ngpt_client = GPTClient(\n model=GPTModel.GPT_3_5_TURBO,\n top_p=0.5,\n presence_penalty=0,\n frequency_penalty=0,\n temperature=0)\n\ngpt_client.set_schema(GPTInput, GPTSchemaType.input)\ngpt_client.set_schema(GPTOutput, GPTSchemaType.output)\n\ngpt_client.add_message(GPTMessageRole.system, \"\"\"\nTake from \\'Input JSON schema\\' the fields 'time', 'timezone', and 'target_timezone'.\nThen generate an Output JSON schema with the field 'target_time', which represents the given 'time' converted \nfrom 'timezone' to 'target_timezone'.\n\"\"\")\n```\n\n3. Add data like user message and call `run` method to get the response:\n\n```python\ninput_data = {\n \"time\": datetime.now().__str__(),\n \"timezone\": \"UTC\",\n \"target_timezone\": \"America/New_York\"\n}\n\ngpt_client.add_message(GPTMessageRole.user, input_data)\n\nresponse = json.loads(gpt_client.run())\n```\n\n4. The response will be:\n\n```json\n{\n \"target_time\": \"2024-05-06T13:04:38.621713-04:00\"\n}\n```\n\nFull example:\n\n```python\nimport json\nfrom datetime import datetime\nfrom dotenv import load_dotenv\nfrom pydantic import BaseModel, Field\nfrom src import GPTClient, GPTModel, GPTMessageRole, GPTSchemaType\n\nload_dotenv()\n\n\nclass GPTInput(BaseModel):\n time: datetime = Field(description=\"The current time\")\n timezone: str = Field(description=\"The timezone of the current time\")\n target_timezone: str = Field(description=\"The target timezone\")\n\n\nclass GPTOutput(BaseModel):\n target_time: datetime = Field(description=\"The target time\")\n\n\ngpt_client = GPTClient(\n model=GPTModel.GPT_3_5_TURBO,\n top_p=0.5,\n presence_penalty=0,\n frequency_penalty=0,\n temperature=0)\n\ngpt_client.set_schema(GPTInput, GPTSchemaType.input)\ngpt_client.set_schema(GPTOutput, GPTSchemaType.output)\n\ngpt_client.add_message(GPTMessageRole.system, \"\"\"\nTake from \\'Input JSON schema\\' the fields 'time', 'timezone', and 'target_timezone'.\nThen generate an Output JSON schema with the field 'target_time', which represents the given 'time' converted \nfrom 'timezone' to 'target_timezone'.\n\"\"\")\n\ninput_data = {\n \"time\": datetime.now().__str__(),\n \"timezone\": \"UTC\",\n \"target_timezone\": \"America/New_York\"\n}\n\ngpt_client.add_message(GPTMessageRole.user, input_data)\n\nresponse = json.loads(gpt_client.run())\n\nprint(response)\n```\n\n## License\n\nThis project is licensed under the MIT License. See the LICENSE file for more details.\n",
"bugtrack_url": null,
"license": null,
"summary": "A Python library for easy interaction with the GPT API, featuring typed requests and responses.",
"version": "0.1.2",
"project_urls": {
"Changelog": "https://github.com/nixnks/nix-gpt-client/CHANGELOG.md",
"Documentation": "https://readthedocs.org",
"Homepage": "https://github.com/nixnks/nix-gpt-client",
"Repository": "https://github.com/nixnks/nix-gpt-client.git"
},
"split_keywords": [
"openai",
" gpt"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a6c31e7e6fe6fdd95e30576ab69f0cd01ef1d21a247dfd554db939e24875baac",
"md5": "6451e1a52fdbca781649a540c68c5e25",
"sha256": "e3f228fac7e069a8da398ca54e8a3586dae50f5fd3db4b34b883ff8dcc9c6f77"
},
"downloads": -1,
"filename": "nix_gpt_client-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6451e1a52fdbca781649a540c68c5e25",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 5295,
"upload_time": "2024-05-17T12:43:55",
"upload_time_iso_8601": "2024-05-17T12:43:55.761843Z",
"url": "https://files.pythonhosted.org/packages/a6/c3/1e7e6fe6fdd95e30576ab69f0cd01ef1d21a247dfd554db939e24875baac/nix_gpt_client-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "db67eed85fb6203a6c6bf0a1c68daecc4c1ea319d0a377c4047562231718812c",
"md5": "94dfb2d05b73c6a797ca494d433ca7dd",
"sha256": "fb478b1209ff63d080ba013c05f81f3e589d79ea9e34ea2448d6919f7cb30405"
},
"downloads": -1,
"filename": "nix_gpt_client-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "94dfb2d05b73c6a797ca494d433ca7dd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 4530,
"upload_time": "2024-05-17T12:43:58",
"upload_time_iso_8601": "2024-05-17T12:43:58.220646Z",
"url": "https://files.pythonhosted.org/packages/db/67/eed85fb6203a6c6bf0a1c68daecc4c1ea319d0a377c4047562231718812c/nix_gpt_client-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-17 12:43:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nixnks",
"github_project": "nix-gpt-client",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "nix-gpt-client"
}
