Spaces:
Sleeping
Sleeping
File size: 1,768 Bytes
4777736 cece503 c583b68 cece503 4777736 57c34bf 4777736 cece503 4777736 cece503 4777736 cece503 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
from sentence_transformers import SentenceTransformer
import torch
# Load knowledge
with open("food_recipe.txt", "r", encoding="utf-8") as file:
knowledge = file.read()
cleaned_chunks = [chunk.strip() for chunk in knowledge.strip().split("\n") if chunk.strip()]
model = SentenceTransformer('all-MiniLM-L6-v2')
chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
def get_top_chunks(query):
query_embedding = model.encode(query, convert_to_tensor=True)
query_embedding_normalized = query_embedding / query_embedding.norm()
similarities = torch.matmul(chunk_embeddings, query_embedding_normalized)
top_indices = torch.topk(similarities, k=5).indices.tolist()
return [cleaned_chunks[i] for i in top_indices]
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
def respond(message, history):
response = ""
top_chunks = get_top_chunks(message)
context = "\n".join(top_chunks)
messages = [
{
"role": "system",
"content": f"You are a friendly chatbot that responds to the user with this context {context}"
}
]
if history:
messages.extend(history)
messages.append({"role": "user", "content": message})
stream = client.chat_completion(
messages,
max_tokens=300,
temperature=1.2,
stream=True,
)
for message in stream:
token = message.choices[0].delta.content
if token is not None:
response += token
yield response
with gr.Blocks() as chatbot:
gr.ChatInterface(
fn=respond,
type="messages",
)
chatbot.launch()
|