Update app.py

app.py

@@ -2,14 +2,11 @@ import gradio as gr
 import openai
 import json
 from graphviz import Digraph
-import base64
-from PIL import Image
 
 def generate_knowledge_graph(api_key, user_input):
-    print("Setting OpenAI API key...")
     openai.api_key = api_key
 
-    print("Making API call to OpenAI...")
+    # Chamar a API da OpenAI
     completion = openai.ChatCompletion.create(
         model="gpt-3.5-turbo-16k",
         messages=[
@@ -17,65 +14,32 @@ def generate_knowledge_graph(api_key, user_input):
                 "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.",
-                "parameters": {
-                    "type": "object",
-                    "properties": {
-                        "metadata": {"type": "object"},
-                        "nodes": {"type": "array"},
-                        "edges": {"type": "array"}
-                    },
-                    "required": ["nodes", "edges"]
-                }
-            }
-        ],
-        function_call={"name": "knowledge_graph"}
+        ]
     )
+    response_data = completion.choices[0].message.to_dict()
+    response_data = json.loads(response_data['content'])
 
-    print("Received response from OpenAI.")
-    response_data = completion.choices[0]["message"]["function_call"]["arguments"]
-    print(f"Response data: {response_data}")
-
-    print("Converting response to JSON...")
-    response_dict = json.loads(response_data)
-
-    print("Generating knowledge graph using Graphviz...")
+    # Visualizar o conhecimento usando Graphviz
     dot = Digraph(comment="Knowledge Graph")
-
-    # Add nodes to the graph
-    for node in response_dict.get("nodes", []):
+    for node in response_data.get("nodes", []):
         dot.node(node["id"], f"{node['label']} ({node['type']})")
-
-    # Add edges to the graph
-    for edge in response_dict.get("edges", []):
+    for edge in response_data.get("edges", []):
         dot.edge(edge["from"], edge["to"], label=edge["relationship"])
 
-    # Render to PNG format
-    print("Rendering graph to PNG format...")
+    # Renderizar para o formato PNG
     dot.format = "png"
     dot.render(filename="knowledge_graph", cleanup=True)
 
-    # Convert PNG to base64 to display in Gradio
-    print("Converting PNG to base64...")
-    with open("knowledge_graph.png", "rb") as img_file:
-        img_base64 = base64.b64encode(img_file.read()).decode()
-
-    print("Returning base64 image to Gradio interface.")
-    return f"data:image/png;base64,{img_base64}"
+    return "knowledge_graph.png"
 
 iface = gr.Interface(
-    fn=generate_knowledge_graph,
+    fn=generate_knowledge_graph, 
     inputs=[
         gr.inputs.Textbox(label="OpenAI API Key", type="password"),
-        gr.inputs.Textbox(label="Text to Generate Knowledge Graph")
-    ],
-    outputs=gr.outputs.Image(type="pil", label="Generated Knowledge Graph"),
+        gr.inputs.Textbox(label="User Input for Graph")
+    ], 
+    outputs=gr.outputs.Image(label="Generated Knowledge Graph"),
     live=False
 )
 
-print("Launching Gradio interface...")
 iface.launch()