agent / README.md
sachin-philip's picture
updated readme
52fbe2a
---
title: Agentic Assistant k2
emoji:
colorFrom: blue
colorTo: gray
sdk: gradio
sdk_version: 5.38.0
app_file: app.py
pinned: false
short_description: Agentic base on top of kimi-k2-small to power internal MCP
---
# Agentic Assistant
A Gradio-based chat interface powered by LangChain and HuggingFace models.
## Setup
### 1. Install Dependencies
```bash
pip install -r requirements.txt
```
### 2. Environment Variables
Create a `.env` file in the project root with the following variables:
```bash
# Required: HuggingFace API Token
# Get your free token from: https://huggingface.co/settings/tokens
HUGGINGFACEHUB_API_TOKEN=your_huggingface_token_here
# Optional: SerpAPI Key (for web search functionality)
# Get your key from: https://serpapi.com/
SERPAPI_API_KEY=your_serpapi_key_here
```
### 3. Run the Application
```bash
python app.py
```
## Features
- 🤖 Powered by Moonshot AI's Kimi K2 1.5B model
- 🔍 Optional web search capability (requires SerpAPI key)
- 💬 Interactive chat interface with Gradio
- 🛠️ Built with LangChain for agent capabilities
## Troubleshooting
- **Missing API Token**: Make sure you've set the `HUGGINGFACEHUB_API_TOKEN` environment variable
- **Import Errors**: The code now uses `langchain_community` imports to avoid deprecation warnings
- **Web Search**: If you don't have a SerpAPI key, the agent will run without web search functionality
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference