Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import openai | |
| import json | |
| from graphviz import Digraph | |
| from PIL import Image | |
| import io | |
| import requests | |
| from bs4 import BeautifulSoup | |
| # Function to generate a knowledge graph from text | |
| def generate_knowledge_graph_from_text(api_key, user_input): | |
| # Ensure the API key and user input are provided | |
| if not api_key or not user_input: | |
| raise ValueError("Please provide both the OpenAI API Key and User Input") | |
| # Process user input | |
| response_data = process_user_input(api_key, user_input) | |
| return generate_knowledge_graph(response_data) | |
| # Function to generate a knowledge graph from a URL | |
| def generate_knowledge_graph_from_url(api_key, url): | |
| # Ensure the API key and URL are provided | |
| if not api_key or not url: | |
| raise ValueError("Please provide both the OpenAI API Key and a URL") | |
| # Scrape text from the provided URL | |
| text = scrape_text_from_url(url) | |
| # Process the scraped text | |
| response_data = process_user_input(api_key, text) | |
| return generate_knowledge_graph(response_data) | |
| # Function to process user input and call OpenAI API | |
| def process_user_input(api_key, user_input): | |
| openai.api_key = api_key | |
| # Call the OpenAI API | |
| 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"}, # Added color property | |
| "properties": { | |
| "type": "object", | |
| "description": "Additional attributes for the node", | |
| }, | |
| }, | |
| "required": [ | |
| "id", | |
| "label", | |
| "type", | |
| "color", | |
| ], # Added color to required | |
| }, | |
| }, | |
| "edges": { | |
| "type": "array", | |
| "items": { | |
| "type": "object", | |
| "properties": { | |
| "from": {"type": "string"}, | |
| "to": {"type": "string"}, | |
| "relationship": {"type": "string"}, | |
| "direction": {"type": "string"}, | |
| "color": {"type": "string"}, # Added color property | |
| "properties": { | |
| "type": "object", | |
| "description": "Additional attributes for the edge", | |
| }, | |
| }, | |
| "required": [ | |
| "from", | |
| "to", | |
| "relationship", | |
| "color", | |
| ], # Added color to required | |
| }, | |
| }, | |
| }, | |
| "required": ["nodes", "edges"], | |
| }, | |
| } | |
| ], | |
| function_call={"name": "knowledge_graph"}, | |
| ) | |
| response_data = completion.choices[0]["message"]["function_call"]["arguments"] | |
| return response_data | |
| # Function to generate a knowledge graph from response data | |
| def generate_knowledge_graph(response_data): | |
| # Visualizar o conhecimento usando Graphviz | |
| dot = Digraph(comment="Knowledge Graph", format='png') | |
| dot.attr(dpi='300') | |
| dot.attr(bgcolor='white') # Set background color to white | |
| # Estilizar os nós | |
| 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")) | |
| # Estilizar as arestas | |
| 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")) | |
| # Renderizar para o formato PNG | |
| image_data = dot.pipe() | |
| image = Image.open(io.BytesIO(image_data)) | |
| return image | |
| # Function to scrape text from a website | |
| 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 | |
| # Define a title and description for the Gradio interface using Markdown | |
| title_and_description = """ | |
| # Instagraph - Knowledge Graph Generator | |
| **Created by [ArtificialGuyBR](https://twitter.com/ArtificialGuyBR)** | |
| This interactive knowledge graph generator allows you to input either text or a URL. | |
| If you provide text, it will generate a knowledge graph based on the text you provide. | |
| If you provide a URL, it will scrape the content from the webpage and generate a knowledge graph from that. | |
| To get started, enter your OpenAI API Key and either your text or a URL. | |
| """ | |
| # Create the Gradio interface with queueing enabled and concurrency_count set to 10 | |
| iface = gr.Interface( | |
| fn=generate_knowledge_graph_from_text, | |
| inputs=[ | |
| gr.inputs.Textbox(label="OpenAI API Key", type="password"), | |
| gr.inputs.Textbox(label="Text or URL", type="text"), | |
| ], | |
| outputs=gr.outputs.Image(type="pil", label="Generated Knowledge Graph"), | |
| live=False, | |
| title=title_and_description, | |
| ) | |
| # Enable queueing system for multiple users | |
| iface.queue(concurrency_count=10) | |
| print("Iniciando a interface Gradio...") | |
| iface.launch() | |