OpenAI Functions
pip install funcmodels
from funcmodels import openai_function
@openai_function
Highlights
This documentation assumes you're already familiar with OpenAI function calling, and Pydantic BaseModel.
from typing import Literal
@openai_function
def get_stock_price(ticker: str, currency: Literal["USD", "EUR"] = "USD"):
"""
Get the stock price of a company, by ticker symbol
Parameters
----------
ticker
The ticker symbol of the company
currency
The currency to use
"""
return f"182.41 {currency}, -0.48 (0.26%) today"
get_stock_price
OpenaiFunction({
"name": "get_stock_price",
"description": "Get the stock price of a company, by ticker symbol",
"parameters": {
"properties": {
"ticker": {
"type": "string",
"description": "The ticker symbol of the company"
},
"currency": {
"default": "USD",
"enum": [
"USD",
"EUR"
],
"type": "string",
"description": "The currency to use"
}
},
"required": [
"ticker"
],
"type": "object"
}
})
@openai_function dynamically creates a custom pydantic.BaseModel class with:
- Your function's parameters as attributes, for validation
- Class attribute,
schema, with an OpenAI Function object for your function- Parses docstring for description, and parameter descriptions, if present.
- Type structure based on pydantic's
.model_json_schema()
- Class method,
.from_json()to easily instantiate your model from raw JSON arguments received from OpenAI - A
.__call__()method to easily call your original function, using the model's validated attributes.
Get our OpenAI function definition dictionary
get_stock_price.schema
{'name': 'get_stock_price', 'description': 'Get the stock price of a company, by ticker symbol', 'parameters': {'properties': {'ticker': {'type': 'string', 'description': 'The ticker symbol of the company'}, 'currency': {'default': 'USD', 'enum': ['USD', 'EUR'], 'type': 'string', 'description': 'The currency to use'}}, 'required': ['ticker'], 'type': 'object'}}
Instantiate our pydantic model, validating arguments
model = get_stock_price(ticker="AAPL")
Or, go directly from raw json arguments from OpenAI
raw_arguments_from_openai = '{"ticker": "AAPL"}'
model = get_stock_price.from_json(raw_arguments_from_openai)
model.currency
'USD'
Call our function, with already-validated arguments
model()
'182.41 USD, -0.48 (0.26%) today'
If you prefer Pydantic syntax, we can achieve the same thing using Fields
from pydantic import Field
@openai_function
def get_stock_price(
ticker: str = Field(description="The ticker symbol of the company"),
currency: Literal["USD", "EUR"] = Field("USD", description="The currency to use."),
):
"Get the stock price of a company, by ticker symbol"
return f"182.41 {currency}, -0.48 (0.26%) today"
Here, the field descriptions are defined in the parameters themselves, rather than the docstring.
The result is the exact same function definition as before:
get_stock_price
OpenaiFunction({
"name": "get_stock_price",
"description": "Get the stock price of a company, by ticker symbol",
"parameters": {
"properties": {
"ticker": {
"type": "string",
"description": "The ticker symbol of the company"
},
"currency": {
"default": "USD",
"enum": [
"USD",
"EUR"
],
"type": "string",
"description": "The currency to use"
}
},
"required": [
"ticker"
],
"type": "object"
}
})
Metadata
Release files for funcmodels 0.0.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| funcmodels-0.0.7.tar.gz | 5.0 kB | Without provenance | Details for funcmodels-0.0.7.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| funcmodels-0.0.7-py2.py3-none-any.whl | Python 2, Python 3 | none | any | Details for funcmodels-0.0.7-py2.py3-none-any.whl |
Total release size: 11.3 kB
Release files / funcmodels-0.0.7.tar.gz
| Download URL | funcmodels-0.0.7.tar.gz |
|---|---|
| Size | 5.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6cc90131fd962a8207600cfead92e55206213fcb2d02401f25aeec83ff1af715
|
|
BLAKE2b-256 checksum How to use checksums |
d053d547368a9a49ffd64dec32cb5aa865dd8386963f6c9d4be53328d1b89124
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.11.6
|
Release files / funcmodels-0.0.7-py2.py3-none-any.whl
| Download URL | funcmodels-0.0.7-py2.py3-none-any.whl |
|---|---|
| Size | 6.3 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
f51c259efbaa0ffcf35057766fe9c9815430f6cacaf1605ac04b1096d5f3b94a
|
|
BLAKE2b-256 checksum How to use checksums |
70d11bd520bf3e531a9480c00cafb5734587aa7cdc5ed48ad6b5fe557a69d4c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.11.6
|
Security for funcmodels 0.0.7
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.