Upload 2 files

app.py

@@ -1,63 +1,87 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import threading
+import time
+import subprocess
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+print("Expanding user path for Ollama")
+OLLAMA = os.path.expanduser("~/ollama")
 
+print("Checking if Ollama exists at the path")
+if not os.path.exists(OLLAMA):
+    print("Ollama not found, downloading it")
+    subprocess.run("curl -L https://ollama.com/download/ollama-linux-amd64 -o ~/ollama", shell=True)
+    os.chmod(OLLAMA, 0o755)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def ollama_service_thread():
+    print("Starting Ollama service thread")
+    subprocess.run("~/ollama serve", shell=True)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+print("Creating and starting Ollama service thread")
+OLLAMA_SERVICE_THREAD = threading.Thread(target=ollama_service_thread)
+OLLAMA_SERVICE_THREAD.start()
 
-    messages.append({"role": "user", "content": message})
+print("Giving Ollama serve a moment to start")
+time.sleep(10)
 
-    response = ""
+print("Setting model to 'gemma2'")
+model = "gemma2"
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+print(f"Pulling model {model}")
+subprocess.run(f"~/ollama pull {model}", shell=True)
 
-        response += token
-        yield response
+################################################
+################################################
+import copy
+import gradio as gr
+from ollama import Client
 
+print("Initializing Ollama client")
+client = Client(host='http://localhost:11434', timeout=120)
+
+print("Getting Hugging Face token and model ID from environment variables")
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+MODEL_ID = os.environ.get("MODEL_ID", "google/gemma-2-9b-it")
+MODEL_NAME = MODEL_ID.split("/")[-1]
+
+print("Setting up title and description for Gradio interface")
+TITLE = "<h1><center>ollama-Chat</center></h1>"
+DESCRIPTION = f"""
+<h3>MODEL: <a href="https://hf.co/{MODEL_ID}">{MODEL_NAME}</a></h3>
+<p>Running on Ollama backend.</p>
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+
+
+CSS = """
+.duplicate-button {
+    margin: auto !important;
+    color: white !important;
+    background: black !important;
+    border-radius: 100vh !important;
+}
+h3 {
+    text-align: center;
+}
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+import gradio as gr
+from llama_index.llms.ollama import Ollama
 
+# Initialize the Ollama model
+llm = Ollama(model="llama3", request_timeout=120.0)
+
+# Define the function to get the response from Ollama
+def get_response(question):
+    resp = llm.complete(question)
+    return resp
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=get_response,
+    inputs="text",
+    outputs="text",
+    title="Ask Paul Graham",
+    description="Enter a question to learn more about Paul Graham."
+)
 
+# Launch the Gradio app
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.22.2
+ollama
+streamlit
+llama_index.llms.ollama