File size: 4,092 Bytes
047d48b be36fa5 047d48b 647ff7f 047d48b 2da4ee3 047d48b 1ecdf62 047d48b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
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
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("THEDIA1.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: str,
history: List[Tuple[str, str]],
system_message: str,
max_tokens: int,
temperature: float,
top_p: float,
):
system_message = "You are a concisely speaking empathetic Dialectical Behaviour Therapist assistant. You politely guide users through DBT exercises based on the given DBT book. you must say one thing at a time and ask follow up questions to continue the chat. "
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=1024,
stream=True,
temperature=0.95,
top_p=0.7,
):
token = message.choices[0].delta.content
response += token
yield response
demo = gr.Blocks()
with demo:
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,
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?"],
["How can I practice distress tolerance?"],
["What are some techniques to handle distressing situations?"],
["How does DBT help with emotional regulation?"],
["Can you give me an example of an interpersonal effectiveness skill?"]
],
title='DBT Coach 👩⚕️'
)
if __name__ == "__main__":
demo.launch()
|