智能文档抽取

private static final String APP_ID      = "your-app-id";
private static final String SECRET_CODE = "your-secret-code";
private static final String API_URL     = "https://api.textin.com/ai/service/v2/entity_extraction";

private static Headers authHeaders() {
    return new Headers.Builder()
            .add("x-ti-app-id", APP_ID)
            .add("x-ti-secret-code", SECRET_CODE)
            .build();
}

private static String encodeFile(String filePath) throws IOException {
    byte[] bytes = Files.readAllBytes(new File(filePath).toPath());
    return Base64.getEncoder().encodeToString(bytes);
}

private static JsonObject callApi(String filePath, JsonObject body,
        Map<String, String> urlParams) throws IOException {
    body.addProperty("file", encodeFile(filePath));
    HttpUrl.Builder urlBuilder = Objects.requireNonNull(HttpUrl.parse(API_URL)).newBuilder();
    if (urlParams != null) urlParams.forEach(urlBuilder::addQueryParameter);
    Request req = new Request.Builder().url(urlBuilder.build()).headers(authHeaders())
            .post(RequestBody.create(GSON.toJson(body), JSON_TYPE)).build();
    try (Response resp = HTTP.newCall(req).execute()) {
        JsonObject result = JsonParser.parseString(resp.body().string()).getAsJsonObject();
        if (result.get("code").getAsInt() != 200)
            throw new RuntimeException("API 错误：" + result.get("message").getAsString());
        return result;
    }
}

JsonObject body = new JsonObject();
body.addProperty("prompt", "请抽取发票号码、开票日期、购买方名称、销售方名称、合计金额");

Map<String, String> params = Map.of("parse_mode", "scan");

JsonObject result = callApi("invoice.pdf", body, params);
JsonObject res = result.getAsJsonObject("result");

// llm_json：大模型直接返回的键值对，方便直接使用
JsonElement llmJson = res.get("llm_json");
System.out.println(GSON.toJson(llmJson));
// 示例输出：{"发票号码": "044031900211", "开票日期": "2024-03-15", "合计金额": "1500.00"}

// usage：token 消耗统计
JsonObject usage = res.getAsJsonObject("usage");
System.out.println("Token 消耗：" + usage.get("total_tokens").getAsInt());

JsonObject body = new JsonObject();

// 单值字段
JsonArray fields = new JsonArray();
for (String name : new String[]{"发票号码", "开票日期", "购买方名称", "销售方名称", "合计金额"}) {
    JsonObject f = new JsonObject();
    f.addProperty("name", name);
    fields.add(f);
}
body.add("fields", fields);

// 表格字段
JsonArray tableFields = new JsonArray();
JsonObject table = new JsonObject();
table.addProperty("title", "货物明细");
table.addProperty("description", "发票中的货物或服务明细表格");
JsonArray cols = new JsonArray();
for (String col : new String[]{"项目名称", "数量", "单价", "金额"}) {
    JsonObject c = new JsonObject(); c.addProperty("name", col); cols.add(c);
}
table.add("fields", cols);
tableFields.add(table);
body.add("table_fields", tableFields);

JsonObject result = callApi("invoice.pdf", body, Map.of("parse_mode", "scan"));
JsonObject details = result.getAsJsonObject("result").getAsJsonObject("details");

// 读取单值字段
System.out.println(details.getAsJsonObject("发票号码").get("value").getAsString());

// 读取表格行
JsonArray rows = details.getAsJsonArray("row");
for (JsonElement row : rows) System.out.println(row);