added gradio

.gitignore

@@ -0,0 +1 @@
+/myenv

app.py

@@ -1,63 +1,44 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+import yaml
+import openai
+from pathlib import Path
+
+# Load settings
+settings_path = Path(__file__).parent / "settings.yaml"
+with open(settings_path, "r") as f:
+    settings = yaml.safe_load(f)
+
+# Configure OpenAI client
+openai.api_key = settings["openai_api_key"]
+openai.api_base = settings["openai_base_url"]
+
+def chatbot(message, history):
+    messages = [{"role": "system", "content": "You are a helpful assistant answering question concerning Air Force Personnel Center material. You also try your best to cite the source of your answer."}]
+    
+    for human, assistant in history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": assistant})
+    
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    client = openai.OpenAI(
+        api_key=settings["openai_api_key"],
+        base_url=settings["openai_base_url"]
+    )
 
-    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
+    response = client.chat.completions.create(
+        model=settings["openai_model"],
+        messages=messages
+    )
 
-        response += token
-        yield response
+    return response.choices[0].message.content
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 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)",
-        ),
-    ],
+    fn=chatbot,
+    examples=["Hello!", "How are you?", "What's the weather like?"],
+    title="Mistral AI Chatbot",
+    description="AFPC Fine-Tuned Chatbot",
 )
 
-
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+openai
+gradio
+pyyaml

settings.yaml

@@ -0,0 +1,3 @@
+openai_model: "ft:open-mistral-nemo:c29ab469:20240912:aed96422"
+openai_api_key: "4mQCQFQMjHj3BXwyRILexMXvvu3KcjX9"
+openai_base_url: "https://api.mistral.ai/v1"