|
import gradio as gr |
|
import openai |
|
import json |
|
from graphviz import Digraph |
|
from PIL import Image |
|
import io |
|
|
|
def generate_knowledge_graph(api_key, user_input): |
|
openai.api_key = api_key |
|
|
|
|
|
print("Chamando a API da OpenAI...") |
|
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"] |
|
print(response_data) |
|
print("Type of response_data:", type(response_data)) |
|
print("Value of response_data:", response_data) |
|
|
|
|
|
if isinstance(response_data, str): |
|
response_data = json.loads(response_data) |
|
|
|
|
|
print("Gerando o conhecimento usando Graphviz...") |
|
dot = Digraph(comment="Knowledge Graph") |
|
for node in response_data.get("nodes", []): |
|
dot.node(node["id"], f"{node['label']} ({node['type']})", color=node.get("color", "lightblue")) |
|
for edge in response_data.get("edges", []): |
|
dot.edge(edge["from"], edge["to"], label=edge["relationship"], color=edge.get("color", "black")) |
|
|
|
|
|
print("Renderizando o gráfico para o formato PNG...") |
|
dot.format = "png" |
|
image_data = dot.pipe(format="png") |
|
image = Image.open(io.BytesIO(image_data)) |
|
|
|
print("Gráfico gerado com sucesso!") |
|
|
|
return image |
|
|
|
iface = gr.Interface( |
|
fn=generate_knowledge_graph, |
|
inputs=[ |
|
gr.inputs.Textbox(label="OpenAI API Key", type="password"), |
|
gr.inputs.Textbox(label="User Input for Graph"), |
|
], |
|
outputs=gr.outputs.Image(type="pil", label="Generated Knowledge Graph"), |
|
live=False, |
|
) |
|
|
|
print("Iniciando a interface Gradio...") |
|
iface.launch() |
