add streamlit app.py and requirements

.env.example

@@ -0,0 +1,5 @@
+# HuggingFace API Token
+HF_TOKEN=your_huggingface_token_here
+
+# Inference Endpoint URL
+INFERENCE_ENDPOINT=your_inference_endpoint_url_here

.gitignore

@@ -0,0 +1,41 @@
+# Environment variables
+.env
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Streamlit
+.streamlit/

requirements.txt

@@ -1,3 +1,3 @@
-altair
-pandas
-streamlit
+streamlit
+huggingface_hub
+requests

src/streamlit_app.py

@@ -1,40 +1,172 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import requests
+import os
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Page configuration
+st.set_page_config(
+    page_title="Med-Gemma Chat",
+    page_icon="🏥",
+    layout="centered"
+)
+
+# Title
+st.title("🏥 Med-Gemma Medical Assistant")
+st.markdown("Ask medical questions and get informed responses from Med-Gemma")
+
+# Sidebar for configuration
+with st.sidebar:
+    st.header("Configuration")
+
+    # Get HuggingFace API token from environment or user input
+    hf_token = os.environ.get("HF_TOKEN", "")
+    if not hf_token:
+        hf_token = st.text_input(
+            "HuggingFace API Token",
+            type="password",
+            help="Enter your HuggingFace API token to access the inference endpoint"
+        )
+    else:
+        st.success("✓ API Token loaded from environment")
+
+    # Inference endpoint URL
+    default_endpoint = os.environ.get("INFERENCE_ENDPOINT", "")
+    endpoint_url = st.text_input(
+        "Inference Endpoint URL",
+        value=default_endpoint,
+        help="Your HuggingFace Inference Endpoint URL (e.g., https://xxx.endpoints.huggingface.cloud)"
+    )
+
+    st.info("💡 Make sure your token was created by the same account that owns the endpoint!")
+
+    # Model parameters
+    st.subheader("Model Parameters")
+    max_tokens = st.slider("Max Tokens", 50, 2048, 512)
+    temperature = st.slider("Temperature", 0.0, 2.0, 0.7, 0.1)
+    top_p = st.slider("Top P", 0.0, 1.0, 0.95, 0.05)
+
+    if st.button("Clear Chat History"):
+        st.session_state.messages = []
+        st.rerun()
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# Function to call the inference endpoint
+def query_model(prompt, endpoint_url, token, max_tokens, temperature, top_p):
+    """Send a request to the HuggingFace Inference Endpoint"""
+    headers = {
+        "Authorization": f"Bearer {token}",
+        "Content-Type": "application/json"
+    }
+
+    # vLLM endpoints use OpenAI-compatible chat format
+    base_url = endpoint_url.rstrip('/')
+    api_url = f"{base_url}/v1/chat/completions"
+
+    payload = {
+        "model": "google/medgemma-27b-text-it",
+        "messages": [
+            {
+                "role": "user",
+                "content": prompt
+            }
+        ],
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p
+    }
+
+    try:
+        response = requests.post(api_url, headers=headers, json=payload, timeout=60)
+
+        # Debug: Show status code if there's an error
+        if response.status_code != 200:
+            error_detail = response.text
+            return f"❌ Error {response.status_code}: {error_detail}\n\nCalled URL: {api_url}\n\n💡 Troubleshooting:\n- Make sure your token was created by the account that owns this endpoint\n- Check that the endpoint is 'Running' (not Paused)\n- Verify the endpoint URL is exactly: https://npbufgk80gff6voc.us-east-1.aws.endpoints.huggingface.cloud"
+
+        result = response.json()
+
+        # Handle OpenAI-compatible chat completion format
+        if isinstance(result, dict) and "choices" in result:
+            if len(result["choices"]) > 0:
+                return result["choices"][0]["message"]["content"]
+            else:
+                return "No response generated"
+        else:
+            return str(result)
+
+    except requests.exceptions.RequestException as e:
+        return f"❌ Error connecting to the model: {str(e)}\n\nMake sure your endpoint URL is correct and the endpoint is running."
+    except Exception as e:
+        return f"❌ Error processing response: {str(e)}"
+
+# Chat input
+if prompt := st.chat_input("Ask a medical question..."):
+    # Validate configuration
+    if not hf_token:
+        st.error("⚠️ Please provide your HuggingFace API Token in the sidebar")
+        st.stop()
+
+    if not endpoint_url:
+        st.error("⚠️ Please provide your Inference Endpoint URL in the sidebar")
+        st.stop()
+
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    # Display user message
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    # Display assistant response
+    with st.chat_message("assistant"):
+        message_placeholder = st.empty()
+        message_placeholder.markdown("Thinking... 🤔")
+
+        # Query the model
+        response = query_model(
+            prompt=prompt,
+            endpoint_url=endpoint_url,
+            token=hf_token,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p
+        )
+
+        # Display the response
+        message_placeholder.markdown(response)
+
+    # Add assistant response to chat history
+    st.session_state.messages.append({"role": "assistant", "content": response})
+
+# Information footer
+with st.expander("ℹ️ How to use"):
+    st.markdown("""
+    ### Getting Started:
+
+    1. **Get your HuggingFace API Token:**
+       - Go to [HuggingFace Settings](https://huggingface.co/settings/tokens)
+       - Create a new token with 'read' permissions
+       - Copy the token
+
+    2. **Get your Inference Endpoint URL:**
+       - Go to your [HuggingFace Inference Endpoints](https://ui.endpoints.huggingface.co/)
+       - Copy the endpoint URL (it looks like: `https://xxx.endpoints.huggingface.cloud`)
+
+    3. **Enter credentials:**
+       - Paste both in the sidebar configuration
+       - Or set them as environment variables: `HF_TOKEN` and `INFERENCE_ENDPOINT`
+
+    4. **Start chatting:**
+       - Type your medical question in the chat input
+       - Wait for Med-Gemma to respond
+
+    ### Note:
+    This is an AI assistant for informational purposes only. Always consult healthcare professionals for medical advice.
+    """)