A utility package that leverages the capabilities of llms to allow working with values with undertermined format
Project description
unsure
unsure is a library for creating operations on uncertain or ambiguous values, utilizing an inference endpoint to determine transformations and comparisons. It's meant to leverage ai while yielding predictable and invariant results.
Installation
To install the package, run:
pip install unsurepy
Configuration
All that needs to be configured is the inference endpoint.
Through API Key
It supports Groq apis and OpenAi apis for now, so a groqApiKey can be provided like this
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
and for openAi
from unsurepy import create_unsure
unsure = create_unsure(groq_ai_api_key='your key here')
Through and inference function
from unsurepy import create_unsure
def inference_endpoint(q: str) -> str:
# any function that returns a string here, you can call OpenAI, Gemini, Claude, or your own model, just return a string
pass
create_unsure(inference_endpoint=inference_endpoint)
Usage
Once it's configured you can start using the operators just like this
Is operator:
Checks equality. Example:
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
print(unsure("Lion").is_("Mammal")) # True
Pick operator:
Picks an information from a string. Example:
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
print(unsure("Contact Number: +1-800-555-5555").pick("phone number")) # "+1-800-555-5555"
print(unsure("Phone: +1-800-555-5555").pick("phone number")) # "+1-800-555-5555"
print(unsure("Call us at +1-800-555-5555").pick("phone number")) # "+1-800-555-5555"
Categorize operator:
Categorizes the string into the given categories. Example:
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
print(unsure("Sky").categorize(["blue", "green"])) # "blue"
print(unsure("Grass").categorize(["blue", "green"])) # "green"
flatMapTo operator:
Transforms the string into what's demanded. Example:
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
print(unsure("Response: {\"key\": \"should get this\"}").flat_map_to("key's value")) # "should get this"
print(
unsure("HTML Content: <html><body><div class=\"scrapable\">Target Content<div></body></html>")
.flat_map_to("content of the div with the class scrapable")
) # "target content"
print(unsure("Favorite Color: #FF5733").flat_map_to("color in hex")) # "#ff5733"
print(unsure("Order Total: 12345 USD").flat_map_to("price")) # "12345"
mapTo operator:
Transforms the string into what's demanded but returns an unsure, so it's chainable. Example:
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
print(unsure("Amount: 200.23 $").map_to("number").map_to("integer").flat()) # "200"
flat operator:
Returns either the changed transformation's result or the initial value if no mapTo was used. Example:
from unsurepy import create_unsure
unsure = create_unsure(groq_api_key='your key here')
print(unsure("Amount: 200.23 $").map_to("number").map_to("integer").flat()) # "200"
print(unsure("Some value").flat()) # "Some value"
Options
inferenceEndpoint: The function that will be called in the operators.
groqApiKey: The Api key that will be used to call groq APIs using llama3-70b-8192 model.
openAiApiKey: The Api key that will be used to call Open Ai APIs using gpt-3.5-turbo.
model: You can specify the model you want to use, for open source models llama3-70b-8192 works best which is the default.
preventLowerCase: Prevents lowercasing the inference response.
Note: If both inferenceEndpoint and groqApiKey are provided inferenceEndpoint will be used.
License
This project is under the ISC license. Requests and contributions are most welcomed.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file unsurepy-1.0.2.tar.gz.
File metadata
- Download URL: unsurepy-1.0.2.tar.gz
- Upload date:
- Size: 4.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
db15fd07b87ef00038874fc502d8bef831b7aed3b51de59ec69bab5f79187874
|
|
| MD5 |
33f6ecff87280180bd1f2951b5fb68dc
|
|
| BLAKE2b-256 |
09686554b157215c7a3a8de6050585e09288b04f706d8f1862ba5ac91677e75c
|
File details
Details for the file unsurepy-1.0.2-py3-none-any.whl.
File metadata
- Download URL: unsurepy-1.0.2-py3-none-any.whl
- Upload date:
- Size: 6.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
205c43238c4feaf0f005a5218ab1c34fa8265fcba7dcdd23378a4cfc16396f19
|
|
| MD5 |
70f23c8c44ef399aa509a6793dc3c5b5
|
|
| BLAKE2b-256 |
ee32f4ce41f5e48b1f7a019e0f6927414b8daee84f838ac3352b9cb9aea86b08
|
