AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-14 03:25:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs(api/core/tools/docs/en_US/tool_scale_out.md): Format by markdownlint. (#5903)

Browse Source
This commit is contained in:
-LAN- 2024-07-03 13:13:38 +08:00 committed by GitHub
parent e3006f98c9
commit e7494d632c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 28 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
api/core/tools/docs/en_US/tool_scale_out.md
View File

@ -5,6 +5,7 @@ Here, we will use GoogleSearch as an example to demonstrate how to quickly integ
## 1. Prepare the Tool Provider yaml ## 1. Prepare the Tool Provider yaml
### Introduction ### Introduction
This yaml declares a new tool provider, and includes information like the provider's name, icon, author, and other details that are fetched by the frontend for display. This yaml declares a new tool provider, and includes information like the provider's name, icon, author, and other details that are fetched by the frontend for display.
### Example ### Example
@ -28,9 +29,11 @@ identity: # Basic information of the tool provider
- search - search
``` ```
- The `identity` field is mandatory, it contains the basic information of the tool provider, including author, name, label, description, icon, etc. - The `identity` field is mandatory, it contains the basic information of the tool provider, including author, name, label, description, icon, etc.
- The icon needs to be placed in the `_assets` folder of the current module, you can refer to [here](../../provider/builtin/google/_assets/icon.svg). - The icon needs to be placed in the `_assets` folder of the current module, you can refer to [here](../../provider/builtin/google/_assets/icon.svg).
- The `tags` field is optional, it is used to classify the provider, and the frontend can filter the provider according to the tag, for all tags, they have been listed below: - The `tags` field is optional, it is used to classify the provider, and the frontend can filter the provider according to the tag, for all tags, they have been listed below:
```python ```python
class ToolLabelEnum(Enum): class ToolLabelEnum(Enum):
SEARCH = 'search' SEARCH = 'search'
@ -56,6 +59,7 @@ identity: # Basic information of the tool provider
Google, as a third-party tool, uses the API provided by SerpApi, which requires an API Key to use. This means that this tool needs a credential to use. For tools like `wikipedia`, there is no need to fill in the credential field, you can refer to [here](../../provider/builtin/wikipedia/wikipedia.yaml). Google, as a third-party tool, uses the API provided by SerpApi, which requires an API Key to use. This means that this tool needs a credential to use. For tools like `wikipedia`, there is no need to fill in the credential field, you can refer to [here](../../provider/builtin/wikipedia/wikipedia.yaml).
After configuring the credential field, the effect is as follows: After configuring the credential field, the effect is as follows:
```yaml ```yaml
identity: identity:
author: Dify author: Dify
@ -87,6 +91,7 @@ credentials_for_provider: # Credential field
- `type`: Credential field type, currently can be either `secret-input`, `text-input`, or `select` , corresponding to password input box, text input box, and drop-down box, respectively. If set to `secret-input`, it will mask the input content on the frontend, and the backend will encrypt the input content. - `type`: Credential field type, currently can be either `secret-input`, `text-input`, or `select` , corresponding to password input box, text input box, and drop-down box, respectively. If set to `secret-input`, it will mask the input content on the frontend, and the backend will encrypt the input content.
## 3. Prepare Tool yaml ## 3. Prepare Tool yaml
A provider can have multiple tools, each tool needs a yaml file to describe, this file contains the basic information, parameters, output, etc. of the tool. A provider can have multiple tools, each tool needs a yaml file to describe, this file contains the basic information, parameters, output, etc. of the tool.
Still taking GoogleSearch as an example, we need to create a `tools` module under the `google` module, and create `tools/google_search.yaml`, the content is as follows. Still taking GoogleSearch as an example, we need to create a `tools` module under the `google` module, and create `tools/google_search.yaml`, the content is as follows.
@ -155,6 +160,7 @@ parameters: # Parameter list
- `form` Form type, currently supports `llm`, `form` two types, corresponding to Agent self-inference and frontend filling - `form` Form type, currently supports `llm`, `form` two types, corresponding to Agent self-inference and frontend filling
## 4. Add Tool Logic ## 4. Add Tool Logic
After completing the tool configuration, we can start writing the tool code that defines how it is invoked. After completing the tool configuration, we can start writing the tool code that defines how it is invoked.
Create `google_search.py` under the `google/tools` module, the content is as follows. Create `google_search.py` under the `google/tools` module, the content is as follows.
@ -176,7 +182,7 @@ class GoogleSearchTool(BuiltinTool):
query = tool_parameters['query'] query = tool_parameters['query']
result_type = tool_parameters['result_type'] result_type = tool_parameters['result_type']
api_key = self.runtime.credentials['serpapi_api_key'] api_key = self.runtime.credentials['serpapi_api_key']
# TODO: search with serpapi # Search with serpapi
result = SerpAPI(api_key).run(query, result_type=result_type) result = SerpAPI(api_key).run(query, result_type=result_type)
if result_type == 'text': if result_type == 'text':
@ -185,12 +191,15 @@ class GoogleSearchTool(BuiltinTool):
``` ```
### Parameters ### Parameters
The overall logic of the tool is in the `_invoke` method, this method accepts two parameters: `user_id` and `tool_parameters`, which represent the user ID and tool parameters respectively The overall logic of the tool is in the `_invoke` method, this method accepts two parameters: `user_id` and `tool_parameters`, which represent the user ID and tool parameters respectively
### Return Data ### Return Data
When the tool returns, you can choose to return one message or multiple messages, here we return one message, using `create_text_message` and `create_link_message` can create a text message or a link message. When the tool returns, you can choose to return one message or multiple messages, here we return one message, using `create_text_message` and `create_link_message` can create a text message or a link message.
## 5. Add Provider Code ## 5. Add Provider Code
Finally, we need to create a provider class under the provider module to implement the provider's credential verification logic. If the credential verification fails, it will throw a `ToolProviderCredentialValidationError` exception. Finally, we need to create a provider class under the provider module to implement the provider's credential verification logic. If the credential verification fails, it will throw a `ToolProviderCredentialValidationError` exception.
Create `google.py` under the `google` module, the content is as follows. Create `google.py` under the `google` module, the content is as follows.
@ -227,6 +236,7 @@ class GoogleProvider(BuiltinToolProviderController):
``` ```
## Completion ## Completion
After the above steps are completed, we can see this tool on the frontend, and it can be used in the Agent. After the above steps are completed, we can see this tool on the frontend, and it can be used in the Agent.
Of course, because google_search needs a credential, before using it, you also need to input your credentials on the frontend. Of course, because google_search needs a credential, before using it, you also need to input your credentials on the frontend.