metadata

title: FinWise AI
emoji: 🏆
colorFrom: pink
colorTo: pink
sdk: streamlit
sdk_version: 1.35.0
app_file: app.py
pinned: false
license: mit

FinWise AI 🏆

FinWise AI is an AI-powered financial advisor built using the LLaMA 3 model from Meta and the Streamlit framework. This application provides users with financial insights and stock recommendations based on natural language queries.

Overview

FinWise AI leverages the powerful capabilities of the LLaMA 3 model, a state-of-the-art language model optimized for dialogue use cases. The application allows users to input queries about stock market investments and receive detailed, AI-generated insights.

Features

Natural Language Processing: Understands and responds to user queries about stock market investments.
Real-Time Insights: Provides up-to-date financial advice and stock recommendations.
Streamlit Integration: Offers an interactive web-based interface for user queries and displaying results.
Secure Handling of API Keys: Uses Hugging Face's secrets management for secure handling of API tokens.

How to Use

Input Your Query: Enter a natural language query in the text area provided. For example, "What are the best stocks to invest in today?"
Get Insights: Click on the "Get Financial Insights" button to receive detailed, AI-generated advice and stock recommendations.

Installation

To run this application locally, follow these steps:

Clone the Repository:

git clone https://huggingface.co/spaces/neuraldevx/FinWise-AI
cd FinWise-AI

Set Up Environment Variables: Add your Hugging Face token in the Hugging Face Spaces settings under the "Secrets" section with the name HF_TOKEN.
Install Dependencies:

Ensure you have the necessary dependencies listed in requirements.txt:
```
pip install -r requirements.txt
```
Run the Application:
```
streamlit run app.py
```

Configuration

The application is configured using the following settings:

Title: FinWise AI
Emoji: 🏆
Color From: Pink
Color To: Pink
SDK: Streamlit
SDK Version: 1.35.0
App File: app.py
Pinned: False
License: MIT

Check out the configuration reference at Hugging Face Spaces Config Reference.

License

This project is licensed under the MIT License.

Contributing

Contributions are welcome! Please fork the repository and submit a pull request.

Contact

For questions or comments about the model, please reach out through the model's repository on Hugging Face.

This project demonstrates the capabilities of the LLaMA 3 model from Meta and provides a foundation for building advanced financial advisory tools using AI.

Access and Usage Instructions

To use the LLaMA 3 model, you must first get access from Hugging Face:

Visit the Model Page: Go to the Meta-Llama-3-8B-Instruct page on Hugging Face.
Accept the License: Read and accept the model license. Once approved, you will be granted access to all the LLaMA 3 models.

Download Weights: Download the weights using the following command after approval:

huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir meta-llama/Meta-Llama-3-8B-Instruct

Use the Model: Load the model in your application as shown in the example:

import transformers
import torch

model_id = "meta-llama/Meta-Llama-3-8B-Instruct"

pipeline = transformers.pipeline(
  "text-generation",
  model=model_id,
  model_kwargs={"torch_dtype": torch.bfloat16},
  device="cuda",
)

Issues and Feedback

Please report any software bugs or other problems with the models through one of the following means:

Reporting issues with the model: Meta-Llama GitHub Issues
Reporting risky content generated by the model: Llama Output Feedback
Reporting bugs and security concerns: Facebook Whitehat

For further details, see the MODEL_CARD.md and LICENSE files in the repository.