Create app,py

app,py

@@ -0,0 +1,139 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+from typing import List, Tuple
+import fitz  # PyMuPDF
+from sentence_transformers import SentenceTransformer
+import numpy as np
+import faiss
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+#client = InferenceClient("meta-llama/Llama-2-7b-chat-hf")
+
+# Placeholder for the app's state
+class MyApp:
+    def __init__(self) -> None:
+        self.documents = []
+        self.embeddings = None
+        self.index = None
+
+    def load_pdfs(self, file_paths: List[str]) -> None:
+        """Extracts text from multiple PDF files and stores it in the app's documents."""
+        self.documents = []
+        for file_path in file_paths:
+            doc = fitz.open(file_path)
+            for page_num in range(len(doc)):
+                page = doc[page_num]
+                text = page.get_text()
+                self.documents.append({"page": page_num + 1, "content": text, "file": file_path})
+        print("PDFs processed successfully!")
+
+    def build_vector_db(self) -> None:
+        """Builds a vector database using the content of the PDFs."""
+        model = SentenceTransformer('all-MiniLM-L6-v2')
+        self.embeddings = model.encode([doc["content"] for doc in self.documents], show_progress_bar=True)
+        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], show_progress_bar=False)
+        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 preprocess_response(response: str) -> str:
+    """Preprocesses the response to make it more polished and empathetic."""
+    response = response.strip()
+    response = response.replace("\n\n", "\n")
+    response = response.replace(" ,", ",")
+    response = response.replace(" .", ".")
+    response = " ".join(response.split())
+    if not any(word in response.lower() for word in ["sorry", "apologize", "empathy"]):
+        response = "I'm here to help. " + response
+    return response
+
+def shorten_response(response: str) -> str:
+    """Uses the Zephyr model to shorten and refine the response."""
+    messages = [{"role": "system", "content": "Greet, Shorten and refine this response in a supportive and empathetic manner."}, {"role": "user", "content": response}]
+    result = client.chat_completion(messages, max_tokens=512, temperature=0.5, top_p=0.9)
+    return result.choices[0].message['content'].strip()
+
+def respond(message: str, history: List[Tuple[str, str]], system_message: str):
+    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 if the query suggests exercises or specific information
+    if any(keyword in message.lower() for keyword in ["exercise", "technique", "information", "guide", "help", "how to"]):
+        retrieved_docs = app.search_documents(message)
+        context = "\n".join(retrieved_docs)
+        if context.strip():
+            messages.append({"role": "system", "content": "Relevant documents: " + context})
+
+    response = client.chat_completion(messages, max_tokens=1024, temperature=0.7, top_p=0.9)
+    response_content = "".join([choice.message['content'] for choice in response.choices if 'content' in choice.message])
+
+    polished_response = preprocess_response(response_content)
+    shortened_response = shorten_response(polished_response)
+
+    history.append((message, shortened_response))
+    return history, ""
+
+with gr.Blocks() as 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.Chatbot()
+
+    with gr.Row():
+        pdf_input = gr.File(label="Upload PDFs (minimum 5)", file_count="multiple", type="file")
+        txt_input = gr.Textbox(
+            show_label=False,
+            placeholder="Type your message here...",
+            lines=1
+        )
+        system_input = gr.Textbox(
+            label="System Message",
+            placeholder="Enter a system message here...",
+            lines=2
+        )
+        submit_btn = gr.Button("Submit", scale=1)
+        refresh_btn = gr.Button("Refresh Chat", scale=1, variant="secondary")
+
+    example_questions = [
+        ["What are some ways to cope with stress using DBT?"],
+        ["Can you guide me through a grounding exercise?"],
+        ["How do I use DBT skills to handle intense emotions?"],
+        ["What are some self-soothing techniques I can practice?"]
+    ]
+
+    gr.Examples(examples=example_questions, inputs=[txt_input])
+
+    def load_and_build_pdfs(pdfs):
+        file_paths = [pdf.name for pdf in pdfs]
+        if len(file_paths) < 5:
+            return [], "Please upload at least 5 PDFs."
+        app.load_pdfs(file_paths)
+        app.build_vector_db()
+        return []
+
+    submit_btn.click(fn=load_and_build_pdfs, inputs=[pdf_input], outputs=[])
+
+    submit_btn.click(fn=respond, inputs=[txt_input, chatbot, system_input], outputs=[chatbot, txt_input])
+    refresh_btn.click(lambda: [], None, chatbot)
+
+if __name__ == "__main__":
+    demo.launch()