# SFNBlueprint Framework
SFNBlueprint is a modular framework for rapid building of intelligent agents to handle various data-related tasks,
such as category identification, code execution, feature suggestion generation, data analysis, and more.
These agents integrate with OpenAI to perform their tasks and can be extended with custom logic.
## Features
- **Base Agent**: A base class for all agents to extend.
- **Category Identification**: Automatically categorize datasets based on column names.
- **Data Cleaning Suggestions**: Generate suggestions for cleaning datasets.
- **Code Execution**: Dynamically execute code on data frames.
- **Feature Suggestion**: Get feature engineering suggestions based on your dataset.
- **Data Analysis**: Analyze datasets and return detailed statistics.
## Installation
You can install the SFNBlueprint framework via pip:
```bash
pip install SFNBlueprint
Usage
1. Environment Setup
To use the agents, you need an API key from OpenAI. Store the key in a .env file in your project root directory:
OPENAI_API_KEY=your_openai_api_key_here
Ensure the python-dotenv package is installed to load environment variables.
2. Using Agents
Example : Loading Data with SFNDataLoader
from sfn_blueprint import SFNDataLoader, Task
task = Task(description="Load CSV data", data=open("data.csv", "rb"))
data_loader = SFNDataLoader()
# Load data into a pandas DataFrame
dataframe = data_loader.execute_task(task)
print(dataframe.head()) # Display the first few rows
3. Extending Agents
You can create custom agents by extending the base class SFNAgent. Here's a minimal example of creating a new agent:
from sfn_blueprint import SFNAgent
class CustomAgent(SFNAgent):
def __init__(self):
super().__init__(name="Custom Agent", role="Performs custom task")
def execute_task(self, task):
# Custom logic here
return "Task executed"
Contact
For any queries or issues, please contact the maintainer at rajesh@stepfunction.ai.
1 maintainer
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 sfn-blueprint-0.2.0.tar.gz.
File metadata
- Download URL: sfn-blueprint-0.2.0.tar.gz
- Upload date:
- Size: 11.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b39eee09f5f885491ca2cfd98857310336c21dbdc0f39381d49bdbba77f7081c
|
|
| MD5 |
f92856606e2c7d90761deead674b8d37
|
|
| BLAKE2b-256 |
1a0e0b4e6f6d2a945838a2a7cd58a686d665a8381535f49c80560432b46af550
|
File details
Details for the file sfn_blueprint-0.2.0-py3-none-any.whl.
File metadata
- Download URL: sfn_blueprint-0.2.0-py3-none-any.whl
- Upload date:
- Size: 15.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0dd50a639f672209a3a3bbd611307ecd41d69a352d6a245684d7ddbbe296a362
|
|
| MD5 |
3524fb2e2e46465a184901339c7ce786
|
|
| BLAKE2b-256 |
ab6e1c85e9549b271933cd5a575e550d4cb1897bf942b32aca8732ba21673376
|
