File size: 2,585 Bytes
fb43022 f544c85 fb43022 |
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 |
import gradio as gr
import os
from huggingface_hub import InferenceClient
from sentence_transformers import SentenceTransformer
import faiss
# Load text from stored data
with open("verilog.txt", "r", encoding="utf-8") as f:
data = f.read()
# Simple chunking
chunks = data.split("\n\n")
embedder = SentenceTransformer('all-MiniLM-L6-v2')
embeddings = embedder.encode(chunks)
# Create Faiss index
dimension = embeddings.shape[1]
index = faiss.IndexFlatL2(dimension)
index.add(embeddings)
def rag_retrieve(query, top_k=3):
query_emb = embedder.encode([query])
distances, indices = index.search(query_emb, top_k)
retrieved_chunks = [chunks[i] for i in indices[0]]
return "\n".join(retrieved_chunks)
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
hf_token: gr.OAuthToken,
):
retrieved_context = rag_retrieve(message)
rag_augmented_system = (
f"{system_message}\n\n"
"Relevant technical specifications and Verilog implementation details:\n"
f"{retrieved_context}\n\n"
"Use this information while responding clearly and politely."
)
client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
messages = [{"role": "system", "content": rag_augmented_system}]
messages.extend(history)
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
choices = message.choices
token = ""
if len(choices) and choices[0].delta.content:
token = choices[0].delta.content
response += token
yield response
chatbot = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are an AI based knowledge base of the ICT project of 16-bit RISC processor built in verilog by Hashir Ehtisham, Abdullah Ikram and Hadi Khan Lodhi.", label="System message"),
gr.Slider(minimum=1, maximum=4096, value=2048, 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)",
),
],
)
with gr.Blocks() as demo:
with gr.Sidebar():
gr.LoginButton()
chatbot.render()
if __name__ == "__main__":
demo.launch()
|