new-block

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Read

docs/platform/block-sdk-guide.md

first for the full guide.

请先阅读

docs/platform/block-sdk-guide.md

获取完整指南。

Provider config (if external service): create
```
_config.py
```
with
```
ProviderBuilder
```
Block file in
```
backend/blocks/
```
(from
```
autogpt_platform/backend/
```
):
- Generate a UUID once with
```
uuid.uuid4()
```
  , then hard-code that string as
```
id
```
  (IDs must be stable across imports)
- ```
Input(BlockSchema)
```
  and
```
Output(BlockSchema)
```
  classes
- ```
async def run
```
  that
```
yield
```
  s output fields
Files: use
```
store_media_file()
```
with
```
"for_block_output"
```
for outputs

Test:

poetry run pytest 'backend/blocks/test/test_block.py::test_available_blocks[MyBlock]' -xvs

提供者配置（若对接外部服务）：创建包含
```
ProviderBuilder
```
的
```
_config.py
```
文件
块文件（位于
```
autogpt_platform/backend/
```
下的
```
backend/blocks/
```
目录中）：
- 使用
```
uuid.uuid4()
```
  生成一个UUID，然后将该字符串硬编码为
```
id
```
  （ID在导入过程中必须保持稳定）
- 定义
```
Input(BlockSchema)
```
  和
```
Output(BlockSchema)
```
  类
- 编写
```
async def run
```
  方法，通过
```
yield
```
  返回输出字段
文件处理：对于输出内容，使用带有
```
"for_block_output"
```
参数的
```
store_media_file()
```
方法

测试：执行

poetry run pytest 'backend/blocks/test/test_block.py::test_available_blocks[MyBlock]' -xvs

进行测试

Analyze interfaces: do inputs/outputs connect well with other blocks in a graph?
Use top-level imports, avoid duck typing
Always use
```
for_block_output
```
for block outputs