Spaces:
Runtime error
Runtime error
File size: 2,426 Bytes
9c29d05 1db403f 9c29d05 9745196 9c29d05 1db403f 9c29d05 249493d 9c29d05 bcbbf70 249493d 9c29d05 bcbbf70 29c6402 bcbbf70 |
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 |
import gradio as gr
import random
from huggingface_hub import InferenceClient
from sentence_transformers import SentenceTransformer
import torch
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", provider='hf-inference')
#loading and processing knowledge base
with open("bookbans.txt", "r", encoding="utf-8") as file:
book_bans_text = file.read()
#cleaning and chunking text
cleaned_text = book_bans_text.strip()
chunks = cleaned_text.split("\n")
cleaned_chunks = []
for chunk in chunks:
stripped_chunk = chunk.strip()
if stripped_chunk:
cleaned_chunks.append(stripped_chunk)
#importing model for embeddings
model = SentenceTransformer('all-MiniLM-L6-v2')
chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
#function to get top chunks that are most similar to query by calculating similarity scores based off of embeddings
def get_top_chunk(message):
query_embedding = model.encode(message, convert_to_tensor=True)
query_embedding_normalized = query_embedding / query_embedding.norm()
chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
top_indices = torch.topk(similarities, k=1).indices
top_chunks = []
for i in top_indices:
chunk = chunks[i]
top_chunks.append(chunk)
return top_chunks
def respond(message, history):
system_message = "You are a knowledgable and friendly chatbot that gives good information."
context = get_top_chunk(message)
messages = [{"role": "system", "content": system_message}]
if history:
messages.extend(history)
user_context = f"{message}\nInformation: {context}"
messages.append({"role": "user", "content": user_context})
response = ""
for message in client.chat_completion(
messages,
max_tokens=300,
temperature=1.3,
top_p=0.4,
stream=True
):
token = message.choices[0].delta.content
response += token
yield response
chatbot = gr.ChatInterface(respond, type='messages', title= "Ask me about AI!",description="An AI assistant to keep you updated on recent book banning news!",examples=["What are the most common genres of book bans?", "Where in the US are the most book banning actions?", "How many books were banned in 2024?"], theme='shivi/calm_seafoam')
chatbot.launch()
|