Add LangChain v1 chatbot with Groq API integration

Implemented a public Gradio chat interface using LangChain v1 with Groq's GPT-OSS-20B model. The app includes message history support, public sharing, and requires no HuggingFace login for users.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.gitignore

@@ -0,0 +1,50 @@
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+ENV/
+env/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Gradio
+gradio_cached_examples/
+flagged/
+.gradio/
+
+# Claude Code
+.claude/

README.md

@@ -1,12 +1,44 @@
----
-title: Test
-emoji: 🏃
-colorFrom: blue
-colorTo: red
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# LangChain Groq Chat Demo
+
+A simple chat interface using LangChain v1 with Groq's GPT-OSS-20B model and Gradio.
+
+## Setup
+
+1. Get a Groq API key from [console.groq.com](https://console.groq.com)
+2. Set your API key as an environment variable or create a `.env` file:
+   ```
+   GROQ_API_KEY=your_groq_api_key_here
+   ```
+
+## Running Locally
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+The app will launch with:
+- A public shareable URL (valid for 72 hours)
+- Local access at `http://localhost:7860`
+- Network access at `http://0.0.0.0:7860`
+
+## Deploying to Hugging Face Spaces
+
+1. Create a new **Public** Space on Hugging Face (select "Public" visibility)
+2. Select "Gradio" as the SDK
+3. Upload these files to your Space: `app.py`, `requirements.txt`
+4. Add your `GROQ_API_KEY` in the Space settings under "Variables and secrets"
+5. The Space will automatically deploy and be publicly accessible without requiring login
+
+## Files
+
+- `app.py` - Main Gradio application with LangChain v1 integration
+- `requirements.txt` - Python dependencies (LangChain v1 compatible)
+- `README.md` - This file
+
+## Features
+
+- Uses OpenAI's GPT-OSS-20B model via Groq API (fast inference)
+- LangChain v1 with message history support
+- Public sharing enabled by default
+- No Hugging Face login required to use the app

app.py

@@ -0,0 +1,85 @@
+import os
+import gradio as gr
+from langchain_groq import ChatGroq
+from langchain_core.messages import HumanMessage, AIMessage
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_core.runnables.history import RunnableWithMessageHistory
+from langchain_community.chat_message_histories import ChatMessageHistory
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Store for chat histories
+chat_histories = {}
+
+def get_session_history(session_id: str):
+    if session_id not in chat_histories:
+        chat_histories[session_id] = ChatMessageHistory()
+    return chat_histories[session_id]
+
+def create_chain():
+    groq_api_key = os.getenv("GROQ_API_KEY")
+    if not groq_api_key:
+        raise ValueError("GROQ_API_KEY environment variable is not set")
+    
+    llm = ChatGroq(
+        model="openai/gpt-oss-20b",
+        temperature=0.7,
+        max_retries=2,
+    )
+    
+    prompt = ChatPromptTemplate.from_messages([
+        ("system", "You are a helpful AI assistant. Be concise and helpful."),
+        MessagesPlaceholder(variable_name="history"),
+        ("human", "{input}"),
+    ])
+    
+    chain = prompt | llm
+    
+    return RunnableWithMessageHistory(
+        chain,
+        get_session_history,
+        input_messages_key="input",
+        history_messages_key="history",
+    )
+
+conversation_chain = create_chain()
+
+def chat(message, history):
+    try:
+        response = conversation_chain.invoke(
+            {"input": message},
+            config={"configurable": {"session_id": "default"}}
+        )
+        history.append([message, response.content])
+        return "", history
+    except Exception as e:
+        error_msg = f"Error: {str(e)}"
+        history.append([message, error_msg])
+        return "", history
+
+with gr.Blocks(title="LangChain Groq Chat Demo") as demo:
+    gr.Markdown("# LangChain + Groq Chat Demo")
+    gr.Markdown("Chat with OpenAI's GPT-OSS-20B model using LangChain v1")
+    
+    chatbot = gr.Chatbot(height=400)
+    msg = gr.Textbox(
+        placeholder="Type your message here...",
+        label="Message",
+        scale=4
+    )
+    
+    with gr.Row():
+        submit = gr.Button("Send", variant="primary")
+        clear = gr.Button("Clear")
+    
+    msg.submit(chat, [msg, chatbot], [msg, chatbot])
+    submit.click(chat, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: ([], ""), outputs=[chatbot, msg])
+
+if __name__ == "__main__":
+    demo.launch(
+        share=True,  # Creates a public URL that anyone can access
+        server_name="0.0.0.0",  # Makes it accessible on network
+        server_port=7860  # Standard port for Gradio apps
+    )

requirements.txt

@@ -0,0 +1,5 @@
+langchain==1.0.8
+langchain-community==0.4.1
+langchain-groq==1.0.1
+gradio>=4.44.1
+python-dotenv==1.0.0