Update app.py

app.py

@@ -1,63 +1,89 @@
+import os
+from openai import OpenAI
+import requests
 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]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    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 += token
-        yield response
-
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+# Initialize OpenAI client
+client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
+
+# Vector database search function
+def search_document(query, k=5):
+    url = "http://154.12.226.68:8000/search"
+    
+    payload = {
+        "text": query,
+        "k": k
+    }
+    
+    headers = {
+        "Content-Type": "application/json"
+    }
+    
+    try:
+        response = requests.post(url, json=payload, headers=headers)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        return f"An error occurred: {e}"
+
+# Function to query OpenAI
+def query_openai(prompt):
+    try:
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant. Answer the question based on the provided context."},
+                {"role": "user", "content": prompt}
+            ]
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"An error occurred while querying OpenAI: {e}"
+
+# Function to perform vector search and format results
+def vector_search(query):
+    results = search_document(query)
+    if isinstance(results, str):  # Error occurred
+        return results
+    if not isinstance(results, dict) or 'results' not in results:
+        return "Unexpected format in vector database response."
+    
+    formatted_results = ""
+    for i, result in enumerate(results['results'], 1):
+        content = result['metadata']['content']
+        source = f"Source {i}: {result['metadata'].get('source', 'Unknown source')}, page {result['metadata'].get('page', 'Unknown page')}"
+        metadata = ", ".join([f"{k}: {v}" for k, v in result['metadata'].items() if k != 'content'])
+        formatted_results += f"{source}\nMetadata: {metadata}\nContent: {content}\n\n"
+    
+    return formatted_results
+
+# Combined function for search and query
+def search_and_query(question):
+    # First, perform the vector search
+    search_results = vector_search(question)
+    
+    # Then, use these results to query OpenAI
+    prompt = f"""Given the following context and question, provide a comprehensive and accurate answer. Use ONLY the information provided in the context to answer. If the context doesn't contain relevant information to answer the question, state that clearly.
+
+Context:
+{search_results}
+
+Question: {question}
+
+Answer:"""
+    
+    openai_response = query_openai(prompt)
+    
+    # Return both the search results and the OpenAI response
+    return search_results, openai_response
+
+# Gradio interface
+with gr.Blocks() as demo:
+    question_input = gr.Textbox(label="Enter your question")
+    search_output = gr.Textbox(label="Vector Search Results")
+    answer_output = gr.Textbox(label="OpenAI Answer")
+    query_button = gr.Button("Get Answer")
+    
+    query_button.click(search_and_query, inputs=question_input, outputs=[search_output, answer_output])
+
+demo.launch()