Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from huggingface_hub import InferenceClient | |
| from sentence_transformers import SentenceTransformer | |
| import torch | |
| # Load knowledge | |
| with open("recipesplease.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 demo: | |
| gr.Markdown("## 🧠🍴 The BiteBot") | |
| theme = gr.themes.Monochrome( | |
| primary_hue="orange", | |
| secondary_hue="zinc", | |
| neutral_hue=gr.themes.Color(c100="rgba(255, 227.4411088400613, 206.9078947368421, 1)", c200="rgba(255, 229.53334184977007, 218.0921052631579, 1)", c300="rgba(255, 234.91658150229947, 213.6184210526316, 1)", c400="rgba(189.603125, 154.41663986650488, 133.88641721491229, 1)", c50="#f3d1bbff", c500="rgba(170.2125, 139.18781968574348, 118.70082236842106, 1)", c600="rgba(193.32187499999998, 129.35648241888094, 111.07528782894737, 1)", c700="rgba(184.13125000000002, 141.9707339039346, 106.60230263157897, 1)", c800="rgba(156.06796875, 104.12209005333418, 69.81988075657894, 1)", c900="rgba(156.39999999999998, 117.22008175779253, 80.2578947368421, 1)", c950="rgba(158.43203125, 125.1788770279765, 97.28282620614036, 1)"), | |
| text_size="sm", | |
| spacing_size="md", | |
| radius_size="sm", | |
| ).set( | |
| body_background_fill='*primary_50', | |
| body_background_fill_dark='*primary_50' | |
| ) | |
| with gr.Blocks(theme=theme) as chatbot: | |
| gr.ChatInterface( | |
| fn=respond, | |
| type="messages", | |
| ) | |
| chatbot.launch() | |