Update app.py

app.py

@@ -1,64 +1,108 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import json
+from openai import OpenAI
+from dotenv import load_dotenv
 
-"""
-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")
+# Load environment variables
+load_dotenv()
 
+# Initialize OpenAI client
+openai_client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
+ragie_api_key = os.getenv('RAGIE_API_KEY')
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+async def get_ragie_chunks(query):
+    """Retrieve chunks using Ragie's documented method"""
+    import aiohttp
+    
+    async with aiohttp.ClientSession() as session:
+        async with session.post(
+            "https://api.ragie.ai/retrievals",
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {ragie_api_key}"
+            },
+            json={
+                "query": query,
+                "filter": {
+                    "scope": "tutorial"  # Adjust this to match your Ragie scope
+                }
+            }
+        ) as response:
+            if response.status != 200:
+                return []
+            data = await response.json()
+            return [chunk["text"] for chunk in data.get("scored_chunks", [])]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def create_system_prompt(chunks):
+    """Create system prompt following Ragie's format"""
+    return f"""These are very important to follow:
+You are "Ragie AI", a professional but friendly AI chatbot working as an assistant.
+Your current task is to help the user based on all of the information available to you.
+Answer informally, directly, and concisely without a heading or greeting but include details.
+Use richtext Markdown when appropriate including bold, italic, paragraphs, and lists.
+If using LaTeX, use double $$ as delimiter instead of single $. Use $$....$$ instead of $..$$.
+Organize information into multiple sections or points when appropriate.
+Don't include raw item IDs or other raw fields from the source.
+Don't use XML or other markup unless requested by the user.
 
-    messages.append({"role": "user", "content": message})
+Here is all of the information available to answer the user:
+===
+{chr(10).join(chunks)}
+===
 
-    response = ""
+If the user asked for a search and there are no results, make sure to let the user know
+and what they might be able to do to find the information they need."""
 
-    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
+async def respond(message, history, temperature):
+    """Main response function following Ragie's integration approach"""
+    try:
+        # Get chunks from Ragie using their method
+        chunks = await get_ragie_chunks(message)
+        
+        # Create messages array following their format
+        messages = [{"role": "system", "content": create_system_prompt(chunks)}]
+        
+        # Add conversation history
+        for human, assistant in history:
+            messages.append({"role": "user", "content": human})
+            messages.append({"role": "assistant", "content": assistant})
+        
+        # Add current message
+        messages.append({"role": "user", "content": message})
+        
+        # Get streaming response from OpenAI
+        response = ""
+        stream = openai_client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=messages,
+            temperature=temperature,
+            stream=True
+        )
+        
+        for chunk in stream:
+            if chunk.choices[0].delta.content is not None:
+                response += chunk.choices[0].delta.content
+                yield response
+                
+    except Exception as e:
+        yield f"I apologize, but I encountered an error: {str(e)}"
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the Gradio interface
 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)",
+            minimum=0.0,
+            maximum=2.0,
+            value=0.7,
+            step=0.1,
+            label="Temperature"
         ),
     ],
+    title="Ragie-Powered Chatbot",
+    description="A chatbot that combines Ragie's retrieval system with OpenAI's language capabilities."
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()