|
import gradio as gr |
|
import openai |
|
import json |
|
from graphviz import Digraph |
|
from PIL import Image |
|
import io |
|
import requests |
|
from bs4 import BeautifulSoup |
|
from ast import literal_eval |
|
|
|
|
|
def scrape_text_from_url(url): |
|
response = requests.get(url) |
|
if response.status_code != 200: |
|
return "Error: Could not retrieve content from URL." |
|
soup = BeautifulSoup(response.text, "html.parser") |
|
paragraphs = soup.find_all("p") |
|
text = " ".join([p.get_text() for p in paragraphs]) |
|
return text |
|
|
|
def generate_knowledge_graph(api_key, user_input): |
|
openai.api_key = api_key |
|
|
|
|
|
if user_input.startswith("http://") or user_input.startswith("https://"): |
|
user_input = scrape_text_from_url(user_input) |
|
|
|
|
|
completion = openai.ChatCompletion.create( |
|
model="gpt-3.5-turbo-16k", |
|
messages=[ |
|
{ |
|
"role": "user", |
|
"content": f"Help me understand following by describing as a detailed knowledge graph: {user_input}", |
|
} |
|
], |
|
functions=[ |
|
{ |
|
"name": "knowledge_graph", |
|
"description": "Generate a knowledge graph with entities and relationships. Use the colors to help differentiate between different node or edge types/categories. Always provide light pastel colors that work well with black font.", |
|
"parameters": { |
|
"type": "object", |
|
"properties": { |
|
"metadata": { |
|
"type": "object", |
|
"properties": { |
|
"createdDate": {"type": "string"}, |
|
"lastUpdated": {"type": "string"}, |
|
"description": {"type": "string"}, |
|
}, |
|
}, |
|
"nodes": { |
|
"type": "array", |
|
"items": { |
|
"type": "object", |
|
"properties": { |
|
"id": {"type": "string"}, |
|
"label": {"type": "string"}, |
|
"type": {"type": "string"}, |
|
"color": {"type": "string"}, |
|
"properties": { |
|
"type": "object", |
|
"description": "Additional attributes for the node", |
|
}, |
|
}, |
|
"required": [ |
|
"id", |
|
"label", |
|
"type", |
|
"color", |
|
], |
|
}, |
|
}, |
|
"edges": { |
|
"type": "array", |
|
"items": { |
|
"type": "object", |
|
"properties": { |
|
"from": {"type": "string"}, |
|
"to": {"type": "string"}, |
|
"relationship": {"type": "string"}, |
|
"direction": {"type": "string"}, |
|
"color": {"type": "string"}, |
|
"properties": { |
|
"type": "object", |
|
"description": "Additional attributes for the edge", |
|
}, |
|
}, |
|
"required": [ |
|
"from", |
|
"to", |
|
"relationship", |
|
"color", |
|
], |
|
}, |
|
}, |
|
}, |
|
"required": ["nodes", "edges"], |
|
}, |
|
} |
|
], |
|
function_call={"name": "knowledge_graph"}, |
|
) |
|
|
|
response_data = completion.choices[0]["message"]["function_call"]["arguments"] |
|
|
|
try: |
|
if isinstance(response_data, str): |
|
response_data = literal_eval(response_data) |
|
except (ValueError, SyntaxError) as e: |
|
print(f"Error in decoding JSON or literal_eval: {e}") |
|
return "Error in decoding JSON" |
|
|
|
if not isinstance(response_data, dict): |
|
print("Unexpected data type for response_data") |
|
return "Error: Unexpected data type" |
|
|
|
dot = Digraph(comment="Knowledge Graph", format='png') |
|
dot.attr(dpi='300') |
|
dot.attr(bgcolor='white') |
|
dot.attr('node', shape='box', style='filled', fillcolor='lightblue', fontcolor='black') |
|
|
|
for node in response_data.get("nodes", []): |
|
dot.node(node["id"], f"{node['label']} ({node['type']})", color=node.get("color", "lightblue")) |
|
|
|
dot.attr('edge', color='black', fontcolor='black') |
|
|
|
for edge in response_data.get("edges", []): |
|
dot.edge(edge["from"], edge["to"], label=edge["relationship"], color=edge.get("color", "black")) |
|
|
|
image_data = dot.pipe() |
|
image = Image.open(io.BytesIO(image_data)) |
|
|
|
return image |
|
|
|
title_and_description = """ |
|
ChatGPT - BPMN - Generator |
|
|
|
""" |
|
|
|
|
|
with gr.Blocks() as app: |
|
gr.Markdown(title_and_description) |
|
|
|
with gr.Row(): |
|
with gr.Column(): |
|
result_image = gr.Image(type="pil", label="OUT - BPMN") |
|
|
|
with gr.Row(): |
|
with gr.Column(): |
|
api_key = gr.Textbox(label="Ключ OpenAI API", type="password") |
|
user_input = gr.Textbox(label="Желаемая концепция", type="text") |
|
run_btn = gr.Button("Сгенерировать BPMN") |
|
|
|
run_btn.click( |
|
generate_knowledge_graph, |
|
inputs=[api_key, user_input], |
|
outputs=[result_image] |
|
) |
|
|
|
app.queue(concurrency_count=10) |
|
|
|
print("Iniciando a interface Gradio...") |
|
app.launch() |
