Upload 2 files

src/app.py

@@ -0,0 +1,81 @@
+# Import necessary libraries
+
+import streamlit as st
+import os
+from openai import OpenAI
+import json
+
+working_dir = os.path.dirname(os.path.abspath(__file__))
+endpoint_data = json.load(open(f"{working_dir}/model_info.json"))
+
+def clear_chat():
+    st.session_state.messages = []
+
+def get_api_key():
+    # Retrieve API key from environment variable or prompt user
+    return os.getenv("OPENAI_API_KEY") or st.text_input("Enter your API Key", type="password")    
+
+st.title("Alphadata AIaaS on Intel® Gaudi®")
+
+# Extract endpoint and model names from JSON data
+endpoint = endpoint_data['endpoint']
+model_names = endpoint_data['models']
+
+
+with st.sidebar:
+    modelname = st.selectbox("Select a LLM model (Running on Intel® Gaudi®) ", model_names)
+    st.write(f"You selected: {modelname}")
+    st.button("Start New Chat", on_click=clear_chat)
+
+    # Add a text input for the API key
+    api_key = get_api_key()
+    if api_key:
+        st.session_state.api_key = api_key    
+
+# Check if the API key is provided
+if "api_key" not in st.session_state or not st.session_state.api_key:
+    st.error("Please enter your API Key in the sidebar.")
+else:
+    try:
+        api_key = st.session_state.api_key
+        base_url = endpoint
+        client = OpenAI(api_key=api_key, base_url=base_url)
+
+        print(f"Selected Model --> {modelname}")
+        st.write(f"**Model Info:** `{modelname}`")
+
+        if "messages" not in st.session_state:
+            st.session_state.messages = []
+
+        for message in st.session_state.messages:
+            with st.chat_message(message["role"]):
+                st.markdown(message["content"])
+
+        if prompt := st.chat_input("What is up?"):
+            st.session_state.messages.append({"role": "user", "content": prompt})
+            with st.chat_message("user"):
+                st.markdown(prompt)
+
+            with st.chat_message("assistant"):
+                try:
+                    stream = client.chat.completions.create(
+                        model=modelname,
+                        messages=[
+                            {"role": m["role"], "content": m["content"]}
+                            for m in st.session_state.messages
+                        ],
+                        max_tokens=1024,
+						temperature=0,
+                        stream=True,
+                    )
+                    
+                    response = st.write_stream(stream)
+                except Exception as e:
+                    st.error(f"An error occurred while generating the response: {e}")
+                    response = "An error occurred while generating the response."
+
+            st.session_state.messages.append({"role": "assistant", "content": response})
+    except KeyError as e:
+        st.error(f"Key error: {e}")
+    except Exception as e:
+        st.error(f"An unexpected error occurred: {e}")

src/model_info.json

@@ -0,0 +1,6 @@
+{
+    "endpoint": "https://inference-api-demo.edgecollaborate.com/ALLaM-7B-Instruct-preview/v1/",
+    "models": [
+        "ALLaM-AI/ALLaM-7B-Instruct-preview"
+    ]
+}