Add ai chatbot

groq_chatbot/.env

@@ -0,0 +1 @@
+GROQ_API_KEY="your_groq_api_key_here"

groq_chatbot/Readme.md

@@ -0,0 +1,53 @@
+# AI Web Assistant (Groq + DuckDuckGo)
+
+A small Python AI chatbot that uses **Groq** for natural language processing and **DuckDuckGo** for web search.  
+The assistant can answer user questions and perform simple calculations.
+
+---
+## Features
+
+- Chatbot powered by Groq LLM
+- Search the web via DuckDuckGo
+- Perform basic math calculations
+- Easy to run locally with Python
+
+---
+
+## Setup Instructions
+
+### 1. Get a Groq API Key
+
+1. Go to [Groq Developer Portal](https://www.groq.com/) and sign up for a free account.  
+2. Generate a free **Groq API key** from your account dashboard.  
+3. Copy the API key and paste it inside the quotes in the .env file.
+
+---
+
+### 2. Set up a Python virtual environment (recommended)
+1. Open your terminal and navigate to the project folder.
+2. Run the following to create a virtual environment:
+    ```bash
+    python -m venv .venv (or py -m venv .venv)
+
+3. Activate the virtual environment by running:
+    ```bash
+    .venv\Scripts\activate (on Windows)
+    or
+    source .venv/bin/activate (on Linux and MacOS)
+
+### 3. Install dependancies
+1. Once your virtual environment is active, install the required packages:
+    ```bash
+    pip install -r requirements.txt
+
+### 4. Run the chatbot
+    ```bash
+    python main.py
+
+
+
+
+
+
+
+

groq_chatbot/main.py

@@ -0,0 +1,49 @@
+from dotenv import load_dotenv
+from langchain_groq import ChatGroq
+from langchain.agents import create_agent
+from tools import search_tool, handle_tool_errors
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain.tools import tool
+from langchain_core.messages import ToolMessage
+from langchain.agents.middleware import wrap_tool_call
+
+
+search = DuckDuckGoSearchRun()
+
+@tool
+def search_tool(query: str) -> str:
+    """Use DuckDuckGo to search for recent information."""
+    results = search.run(query)
+    return f"Results for:  {results}"
+
+@wrap_tool_call
+def handle_tool_errors(request, handler):
+    """Handle tool execution errors with custom messages."""
+    try:
+        return handler(request)
+    except Exception as e:
+        # Return a custom error message to the model
+        return ToolMessage(
+            content=f"Tool error: Please check your input and try again. ({str(e)})",
+            tool_call_id=request.tool_call["id"]
+        )
+
+load_dotenv()
+
+model = ChatGroq(
+    model="llama-3.1-8b-instant",
+    temperature=0,
+)
+
+agent = create_agent(
+    model, 
+    tools=[search_tool],
+    middleware=[handle_tool_errors],
+    system_prompt="You are an intelligent " \
+    "assistant that provides accurate information."
+)
+
+question = input("Enter your question: ")
+
+for chunk in agent.stream({"messages": [{"role": "user", "content": "why sky blue?"}]}, stream_mode="updates"):
+    print(chunk)

groq_chatbot/requirements.txt

@@ -0,0 +1,6 @@
+langchain 
+python-dotenv
+pydantic
+duckduckgo-search
+ddgs
+langchain-community