Metadata-Version: 2.1
Name: verahession
Version: 0.1.12
Summary: Python client library for Vera AI chatbot by Hession Dynamics
Home-page: https://github.com/hession-dynamics/verahession
Author: Jack Hession
Author-email: support@hessiondynamics.com
License: MIT
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: License :: OSI Approved :: MIT License
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: requests (>=2.20.0)

# Verahession

**Verahession** is a lightweight Python interface for interacting with **V.E.R.A.** (Vocally Enhanced Research Assistant), an AI-powered conversational agent. This module provides simple tools to connect to the VERA API, send messages, rewrite input, and run local intent classification using your own training data.

---

---

## 🔧 Features

- 🧠 Send and receive messages using an API-based LLM
- ✍️ Rewrite user input intelligently
- 🏋️‍♂️ Train a local intent classification model
- 🔍 Detect user intent with confidence scoring

---

## 📦 Installation

```bash
python3 -m pip install verahession
```

---

## 🔑 API Key

To use the Vera API (LLM), you need an API key.  
Visit [hessiondynamics.com](https://hessiondynamics.com) to request your key.

---

## 🚀 Example Usage

```python
from verahession.api import vera_interface
from verahession.assistant import *

# Initialize Vera interface
vera = vera_interface(API_KEY="your_api_key_here", AGENT_NAME="Brian", USER_NAME="Jack")

# Send a message
message = input("You: ")
result = vera.send(message)
print("Vera says:", result.get("response", result))

# Rewrite a message (or text, whatever)
message = input("Text: ")
result = vera.rewrite(message)
print("Vera rewrites:", result.get("response", result))

# Train the intent classifier
bot_trainer = trainer("./intents.json", "./model.pth")
bot_trainer.train()

# Classify a new input
classifier = Classifier("./model.pth")
message = input("You: ")
intent, confidence = classifier.classify(message)
print(intent)
print(confidence)
```

---

## 📁 File Structure

- `verahession/api.py` – Vera API interface (LLM)
- `verahession/assistant.py` – Local trainer & classifier tools
- `intents.json` – Training data for intent classification
- `model.pth` – Output model file after training

---

## 📄 License

MIT License

---


