Spaces:
Runtime error
Runtime error
File size: 4,449 Bytes
a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 a0b40ec a2cdd69 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | import gradio as gr
from huggingface_hub import InferenceClient
import pickle
import faiss
import numpy as np
import torch
import os
from transformers import AutoTokenizer, AutoModel
from openai import OpenAI
from dotenv import load_dotenv
load_dotenv()
api = os.getenv("OPENAI_API_KEY")
client = OpenAI(api_key=api)
# Load IndoLegalBERT
tokenizer = AutoTokenizer.from_pretrained("archi-ai/Indo-LegalBERT")
model = AutoModel.from_pretrained("archi-ai/Indo-LegalBERT")
# Pooling dengan mean pooling
def get_embedding(text):
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512, padding="max_length")
with torch.no_grad():
outputs = model(**inputs)
last_hidden = outputs.last_hidden_state
mask = inputs["attention_mask"].unsqueeze(-1).expand(last_hidden.size()).float()
masked = last_hidden * mask
summed = torch.sum(masked, 1)
counts = torch.clamp(mask.sum(1), min=1e-9)
mean_pooled = summed / counts
return mean_pooled.squeeze().numpy()
# Generate all embeddings
embeddings = np.array([get_embedding(text) for text in texts])
# 5. Simpan ke FAISS
dimension = embeddings.shape[1]
index = faiss.IndexFlatL2(dimension)
index.add(embeddings)
# 6. Simpan FAISS index dan metadata
faiss.write_index(index, "legal_index.faiss")
with open("legal_metadata.pkl", "wb") as f:
pickle.dump(titles, f)
# 2. Load FAISS index dan metadata
index = faiss.read_index("legal_index.faiss")
with open("legal_metadata.pkl", "rb") as f:
metadata = pickle.load(f)
# 4. Fungsi pencarian pasal hukum terkait
def search_laws(query, top_k=3):
vec = get_embedding(query).reshape(1, -1)
D, I = index.search(vec, top_k)
results = []
for i in I[0]:
if i < len(metadata):
results.append(f"- {metadata[i]}\n{texts[i]}")
return results
# 5. Fungsi untuk membentuk prompt ke OpenAI
def build_prompt(query, contexts):
context_text = "\n\n".join(contexts)
return f"""
Anda adalah asisten hukum berbasis hukum Indonesia.
Permintaan pengguna:
\"{query}\"
Gunakan konteks hukum berikut:
{context_text}
Berikan penjelasan hukum yang sistematis dan profesional. Sebutkan pasal hukum jika ada.
"""
# 6. Fungsi untuk interaksi LLM (pakai GPT-3.5 Turbo)
openai.api_key = "YOUR_OPENAI_API_KEY" # <- Ganti dengan API key milikmu
def ask_llm(query):
contexts = search_laws(query)
prompt = build_prompt(query, contexts)
response = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "Anda adalah ahli hukum Indonesia."},
{"role": "user", "content": prompt}
],
temperature=0.2,
# max_tokens=512,
)
return response.choices[0].message.content
# Gradio UI
# Fungsi simulasi RAG Legal Agent
def rag_legal_analysis(document_text, issue_type):
if issue_type == "Analisis Syarat Sah Perjanjian":
return ask_llm(document_text)
elif issue_type == "Deteksi Klausul Bermasalah":
return ask_llm(document_text)
elif issue_type == "Risiko Hukum Pihak Tertentu":
return ask_llm(document_text)
else:
return "Silakan pilih jenis analisis hukum yang ingin dilakukan."
# Gradio UI
with gr.Blocks(title="Naraya Smart Legal Assitant") as demo:
gr.Markdown("# 🤖 Naraya Smart Legal Assitant")
gr.Markdown("Masukkan isi perjanjian atau kontrak, lalu pilih jenis analisis hukum.")
document_input = gr.Textbox(
label="Isi Dokumen Kontrak",
lines=10,
placeholder="Masukkan isi kontrak di sini atau upload dokumen")
#document_input = gr.MultimodalTextbox(
# interactive=True,
# label="Isi Dokumen Kontrak",
# lines=10,
# placeholder="Masukkan isi kontrak di sini atau upload dokumen")
issue_type = gr.Radio(
label="Jenis Analisis Hukum",
choices=[
"Analisis Syarat Sah Perjanjian",
"Deteksi Klausul Bermasalah",
"Risiko Hukum Pihak Tertentu"
]
)
output = gr.Textbox(label="Hasil Analisis Hukum", lines=20)
analyze_button = gr.Button("🔍 Analisa Sekarang")
analyze_button.click(fn=rag_legal_analysis, inputs=[document_input, issue_type], outputs=output)
if __name__ == "__main__":
demo.launch()
|