Create appvector.py

appvector.py

@@ -0,0 +1,96 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+from typing import List, Tuple
+import fitz  # PyMuPDF
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# Placeholder for the app's state
+class MyApp:
+    def __init__(self) -> None:
+        self.documents = []
+        self.load_pdf("THEDIA1.pdf")
+
+    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 search_documents(self, query: str, k: int = 3) -> List[str]:
+        """Searches for relevant documents containing the query string."""
+        results = [doc["content"] for doc in self.documents if query.lower() in doc["content"].lower()]
+        return results[:k] if results else ["No relevant documents found."]
+
+app = MyApp()
+
+def respond(
+    message: str,
+    history: List[Tuple[str, str]],
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
+):
+    system_message = "You are a knowledgeable DBT coach. Use relevant documents to guide users through DBT exercises and provide helpful information."
+    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})
+
+    # 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,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+        response += token
+        yield response
+
+demo = gr.Blocks()
+
+with demo:
+    gr.Markdown("🧘‍♀️ **Dialectical Behaviour Therapy**")
+    gr.Markdown(
+        "Disclaimer: This chatbot is based on a DBT exercise book that is publicly available. "
+        "We are not medical practitioners, and the use of this chatbot is at your own responsibility."
+    )
+    
+    chatbot = gr.ChatInterface(
+        respond,
+        additional_inputs=[
+            gr.Textbox(value="You are a knowledgeable DBT coach. Use relevant documents to guide users through DBT exercises and provide helpful information.", 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=[
+            ["I feel overwhelmed with work."],
+            ["Can you guide me through a quick meditation?"],
+            ["How do I stop worrying about things I can't control?"],
+            ["What are some DBT skills for managing anxiety?"],
+            ["Can you explain mindfulness in DBT?"],
+            ["What is radical acceptance?"]
+        ],
+        title='DBT Coach 🧘‍♀️'
+    )
+
+if __name__ == "__main__":
+    demo.launch()