pushing files

README.md

@@ -1,14 +1,47 @@
 ---
-title: Ollama Test
-emoji: 🏃
-colorFrom: green
-colorTo: purple
+title: Llama 2 Chat
+emoji: 🤖
+colorFrom: blue
+colorTo: indigo
 sdk: gradio
-sdk_version: 5.23.3
+sdk_version: "4.19.2"
 app_file: app.py
 pinned: false
-license: apache-2.0
-short_description: A small application with llama2 model using Ollama
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Llama 2 Chat
+
+A simple chat interface for the Llama 2 model using Ollama.
+
+## Features
+
+- Chat interface using Gradio
+- Powered by Llama 2 model via Hugging Face
+- Simple and intuitive UI
+- Example prompts included
+
+## Usage
+
+1. Enter your prompt in the text box
+2. Click "Submit" or press Enter
+3. Wait for the model's response
+4. Try the example prompts for quick testing
+
+## Technical Details
+
+- Built with Gradio
+- Uses Hugging Face Inference API
+- Deployed on Hugging Face Spaces
+
+## Local Development
+
+To run this locally:
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+## Note
+
+This application uses the Hugging Face Inference API to access the Llama 2 model. No local server setup is required. 

app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import requests
+import os
+
+
+# For Hugging Face Spaces deployment:
+# Set these environment variables in your Space settings:
+# OLLAMA_HOST: Your Ollama server URL
+# OLLAMA_MODEL: Model name (e.g., "llama2")
+
+# Get environment variables for deployment
+OLLAMA_HOST = os.getenv("OLLAMA_HOST", "http://localhost:11434")
+OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", "llama2")
+API_URL = f"{OLLAMA_HOST}/api/generate"
+
+def generate_response(prompt):
+    try:
+        # Make request to local Ollama server
+        response = requests.post(
+            API_URL, 
+            json={
+                "model": OLLAMA_MODEL,
+                "prompt": prompt,
+                "stream": False
+            }
+        )
+        
+        # Check for specific error cases
+        if response.status_code == 404:
+            return "Error: Ollama server not found. Make sure Ollama is running and OLLAMA_HOST is set correctly."
+        elif response.status_code == 500:
+            return "Error: Server error. Check if the model is loaded in Ollama and OLLAMA_MODEL is set correctly."
+        
+        response.raise_for_status()
+        return response.json()['response']
+    except requests.exceptions.RequestException as e:
+        return f"Error: {str(e)}"
+    except Exception as e:
+        return f"Unexpected error: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
+    outputs=gr.Textbox(lines=10),
+    title="Llama 2 Chat",
+    description="Chat with Llama 2 model using local Ollama server. Enter your prompt below and get a response.",
+    examples=[
+        ["What is artificial intelligence?"],
+        ["Tell me a short story about a robot."],
+        ["Explain quantum computing in simple terms."]
+    ]
+)
+
+# Launch the app
+if __name__ == "__main__":
+    # For local development
+    demo.launch()
+    # For Hugging Face Spaces:
+    # demo.launch(server_name="0.0.0.0", server_port=7860) 

ollama_t.py

@@ -0,0 +1,46 @@
+import requests
+import json
+
+def generate_response(prompt):
+    # Ollama API endpoint
+    url = "http://localhost:11434/api/generate"
+    
+    # Request payload
+    data = {
+        "model": "llama2",
+        "prompt": prompt,
+        "stream": False
+    }
+    
+    try:
+        # Send POST request to Ollama server
+        response = requests.post(url, json=data)
+        response.raise_for_status()  # Raise an exception for bad status codes
+        
+        # Parse the response
+        result = response.json()
+        return result.get('response', 'No response generated')
+    
+    except requests.exceptions.RequestException as e:
+        return f"Error connecting to Ollama server: {str(e)}"
+
+def main():
+    print("Welcome to the Ollama Llama 2 Test Application!")
+    print("Type 'quit' to exit")
+    
+    while True:
+        # Get user input
+        user_input = input("\nEnter your prompt: ")
+        
+        # Check if user wants to quit
+        if user_input.lower() == 'quit':
+            print("Goodbye!")
+            break
+        
+        # Generate and print response
+        response = generate_response(user_input)
+        print("\nLlama 2 Response:")
+        print(response)
+
+if __name__ == "__main__":
+    main() 

requirements.txt

@@ -0,0 +1,6 @@
+streamlit==1.32.0
+huggingface-hub==0.20.3
+requests==2.31.0
+aiohttp==3.9.1
+typing-extensions==4.8.0
+gradio==4.19.2