File size: 3,629 Bytes
7b203d7 b6a467a 54072ad 36f1be7 4e2c9cd 241003b b6a467a 5606667 54072ad 94a52b9 8353536 94a52b9 54072ad e63c0a3 54072ad b6a467a 54072ad b6a467a 54072ad b6a467a 54072ad b6a467a 54072ad b6a467a 54072ad b6a467a 36f1be7 4e2c9cd 54072ad b6a467a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 |
import os
import gradio as gr
from huggingface_hub import InferenceClient
from datasets import load_dataset
import time
import faiss
import numpy as np
# ✅ Install FAISS if missing
os.system("pip install faiss-cpu")
def log(message):
print(f"✅ {message}")
# ✅ Load the datasets
datasets = {
"sales": load_dataset("goendalf666/sales-conversations", trust_remote_code=True),
"blended": load_dataset("blended_skill_talk", trust_remote_code=True),
"dialog": load_dataset("daily_dialog", trust_remote_code=True),
"multiwoz": load_dataset("multi_woz_v22", trust_remote_code=True),
}
# Optional: Print dataset names and sizes
for name, dataset in datasets.items():
print(f"{name}: {len(dataset['train'])} examples")
# Initialize the model client (use correct model for chatbot)
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
# Chatbot response function
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
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})
response = ""
for message in client.chat_completions(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message["choices"][0]["delta"]["content"]
response += token
yield response
# Gradio interface for chatbot
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
def start_embedding():
# Include your embedding logic here (from embeddings.py)
log("Embedding started...")
time.sleep(2) # Simulating embedding process
log("Embedding process finished.")
# Create Gradio interface with a button to start the embedding
demo = gr.Interface(
fn=start_embedding,
inputs=None,
outputs="text",
live=True,
title="Embedding Trigger"
)
# ✅ Function to check FAISS index
def check_faiss():
index_path = "my_embeddings" # Adjust if needed
try:
index = faiss.read_index(index_path)
num_vectors = index.ntotal
dim = index.d
if num_vectors > 0:
sample_vectors = index.reconstruct_n(0, min(5, num_vectors)) # Get first 5 embeddings
return f"📊 FAISS index contains {num_vectors} vectors.\n✅ Embedding dimension: {dim}\n🧐 Sample: {sample_vectors[:2]} ..."
else:
return "⚠️ No embeddings found in FAISS index!"
except Exception as e:
return f"❌ ERROR: Failed to load FAISS index - {e}"
# ✅ Add a Gradio button to trigger FAISS check
with gr.Blocks() as demo:
gr.Markdown("### 🔍 FAISS Embedding Check")
check_button = gr.Button("🔎 Check FAISS Embeddings")
output_text = gr.Textbox(label="FAISS Status", interactive=False)
check_button.click(fn=check_faiss, outputs=output_text)
# Launch Gradio app
if __name__ == "__main__":
demo.launch()
|