Update app.py

app.py

@@ -1,21 +1,59 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from typing import List, Tuple
+import fitz  # PyMuPDF
+from sentence_transformers import SentenceTransformer, util
+import numpy as np
+import faiss
 
-"""
-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")
 
+# Placeholder for the app's state
+class MyApp:
+    def __init__(self) -> None:
+        self.documents = []
+        self.embeddings = None
+        self.index = None
+        self.load_pdf("jsr-17-task-002_aiforhealthandhealthcare12122017.pdf")
+        self.build_vector_db()
+
+    def load_pdf(self, file_path: str) -> None:
+        """Extracts text from a PDF file and stores it in the app's documents."""
+        doc = fitz.open(file_path)
+        self.documents = []
+        for page_num in range(len(doc)):
+            page = doc[page_num]
+            text = page.get_text()
+            self.documents.append({"page": page_num + 1, "content": text})
+        print("PDF processed successfully!")
+
+    def build_vector_db(self) -> None:
+        """Builds a vector database using the content of the PDF."""
+        model = SentenceTransformer('all-MiniLM-L6-v2')
+        self.embeddings = model.encode([doc["content"] for doc in self.documents])
+        self.index = faiss.IndexFlatL2(self.embeddings.shape[1])
+        self.index.add(np.array(self.embeddings))
+        print("Vector database built successfully!")
+
+    def search_documents(self, query: str, k: int = 3) -> List[str]:
+        """Searches for relevant documents using vector similarity."""
+        model = SentenceTransformer('all-MiniLM-L6-v2')
+        query_embedding = model.encode([query])
+        D, I = self.index.search(np.array(query_embedding), k)
+        results = [self.documents[i]["content"] for i in I[0]]
+        return results if results else ["No relevant documents found."]
+
+app = MyApp()
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    message: str,
+    history: List[Tuple[str, str]],
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
-    system_message = "AI for healthcare offers the ability to process and analyze vast amounts of medical data far beyond human capacity. This capability was instrumental in diagnosing diseases, predicting outcomes, and recommending treatments. The scope of AI in healthcare amplifies diagnostic precision and expedites decision-making processes, facilitating a seamless workflow that ultimately enhances patient care outcomes."
+    system_message = "How computer-based decision procedures, under the broad umbrella of artificial intelligence (AI), can assist in improving health and health care?"
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -26,46 +64,41 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # RAG - Retrieve relevant documents
+    retrieved_docs = app.search_documents(message)
+    context = "\n".join(retrieved_docs)
+    messages.append({"role": "system", "content": "Relevant documents: " + context})
 
+    response = ""
     for message in client.chat_completion(
         messages,
-        max_tokens=max_tokens,
+        max_tokens=100,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        temperature=0.98,
+        top_p=0.7,
     ):
         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 = "AI for healthcare offers the ability to process and analyze vast amounts of medical data far beyond human capacity. This capability was instrumental in diagnosing diseases, predicting outcomes, and recommending treatments. The scope of AI in healthcare amplifies diagnostic precision and expedites decision-making processes, facilitating a seamless workflow that ultimately enhances patient care outcomes.", 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)",
-        ),
-    ],
-
-    examples = [ 
-        ["What are the primary applications of AI in healthcare?"],
-        ["How does AI improve diagnostic accuracy?"],
-        ["How can AI help in early disease detection?"]
-    ],
-    title = 'AI in Healthcare'
-)
+demo = gr.Blocks()
 
+with demo:
+    gr.Markdown(
+        
+    )
+    
+    chatbot = gr.ChatInterface(
+        respond,
+        examples=[
+            ["How AI can assist in improving health and healthcare?"],
+            ["Is the recent level of interest in AI just another period of hype within the cycles of excitement that have arisen around AI?"],
+            ["How AI will be used to power many health-related mobile monitoring devices and apps"],
+            ["How AI Track developments in foreign health care systems,"],
+            ["What are advances in AI Applications for Medical Imaging"],
+        ],
+        title='AI in Healthcare'
+    )
 
 if __name__ == "__main__":
     demo.launch()