Skip to Content
模型用法GPT結構化輸出與 PDF

GPT 結構化輸出與 PDF

本頁說明 GPT 系列的結構化輸出與 PDF 輸入寫法；模型 ID 與介面設定請見 GPT 系列概覽。

結構化輸出

透過 response_format 傳入 JSON Schema，strict: true 時輸出會嚴格符合 Schema：

gpt_json_schema.py
import json
import os
from openai import OpenAI
 
client = OpenAI(base_url="https://api.ofox.ai/v1", api_key=os.environ["OFOX_API_KEY"])
 
resp = client.chat.completions.create(
    model="openai/gpt-5.4-mini",
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "price",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {"price": {"type": "number"}, "currency": {"type": "string"}},
                "required": ["price", "currency"],
                "additionalProperties": False,
            },
        },
    },
    messages=[{"role": "user", "content": "球拍和球共 1.10 美元，球拍比球貴 1 美元，球多少錢？"}],
)
print(json.loads(resp.choices[0].message.content))

更多寫法請見結構化輸出。

PDF 輸入

gpt_pdf.py
import base64
import os
from openai import OpenAI
 
client = OpenAI(base_url="https://api.ofox.ai/v1", api_key=os.environ["OFOX_API_KEY"])
pdf_b64 = base64.b64encode(open("invoice.pdf", "rb").read()).decode()
 
resp = client.chat.completions.create(
    model="openai/gpt-5.4-mini",
    messages=[{"role": "user", "content": [
        {"type": "file", "file": {"filename": "invoice.pdf", "file_data": f"data:application/pdf;base64,{pdf_b64}"}},
        {"type": "text", "text": "這張發票的總金額是多少？"},
    ]}],
)
print(resp.choices[0].message.content)

其他錯誤請見常見錯誤。

最後更新於
推理