本指南提供快速概览，帮助您开始使用 langchain_taiga中的 Taiga 工具。如需了解每个工具和配置的更多详情，请参阅代码库中的文档字符串或相关文档页面。

概述

集成详情

工具功能

• - **create_entity_tool**：在 Taiga 中创建用户故事、任务和问题。
• - **search_entities_tool**：在 Taiga 中搜索用户故事、任务和问题。
• - **get_entity_by_ref_tool**：通过引用获取用户故事、任务或问题。
• - **update_entity_by_ref_tool**：通过引用更新用户故事、任务或问题。
• - **add_comment_by_ref_tool**：向用户故事、任务或问题添加评论。
• - **add_attachment_by_ref_tool**：向用户故事、任务或问题添加附件。

设置

该集成位于 langchain-taiga package.

pip install --quiet -U langchain-taiga

凭据

此集成需要您将 TAIGA_URL, TAIGA_API_URL, TAIGA_USERNAME, TAIGA_PASSWORD 和 OPENAI_API_KEY 设置为环境变量以向 Taiga 进行身份验证。

设置 LangSmith 也很有帮助（但非必需），以便获得一流的可观测性：

os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

实例化

以下是展示如何实例化 Taiga 工具的示例 langchain_taiga。根据您的具体使用情况进行调整。

from langchain_taiga.tools.discord_read_messages import create_entity_tool
from langchain_taiga.tools.discord_send_messages import search_entities_tool

create_tool = create_entity_tool
search_tool = search_entities_tool

调用

使用参数直接调用

以下是使用字典中的关键字参数调用工具的简单示例。

from langchain_taiga.tools.taiga_tools import (
    add_attachment_by_ref_tool,
    add_comment_by_ref_tool,
    create_entity_tool,
    get_entity_by_ref_tool,
    search_entities_tool,
    update_entity_by_ref_tool,
)

response = create_entity_tool.invoke(
    {
        "project_slug": "slug",
        "entity_type": "us",
        "subject": "subject",
        "status": "new",
        "description": "desc",
        "parent_ref": 5,
        "assign_to": "user",
        "due_date": "2022-01-01",
        "tags": ["tag1", "tag2"],
    }
)

response = search_entities_tool.invoke(
    {"project_slug": "slug", "query": "query", "entity_type": "task"}
)

response = get_entity_by_ref_tool.invoke(
    {"entity_type": "user_story", "project_id": 1, "ref": "1"}
)

response = update_entity_by_ref_tool.invoke(
    {"project_slug": "slug", "entity_ref": 555, "entity_type": "us"}
)


response = add_comment_by_ref_tool.invoke(
    {"project_slug": "slug", "entity_ref": 3, "entity_type": "us", "comment": "new"}
)

response = add_attachment_by_ref_tool.invoke(
    {
        "project_slug": "slug",
        "entity_ref": 3,
        "entity_type": "us",
        "attachment_url": "url",
        "content_type": "png",
        "description": "desc",
    }
)

使用 ToolCall 调用

如果您有模型生成的 ToolCall，请将其传递给 tool.invoke() ，格式如下所示。

# This is usually generated by a model, but we'll create a tool call directly for demo purposes.
model_generated_tool_call = {
    "args": {"project_slug": "slug", "query": "query", "entity_type": "task"},
    "id": "1",
    "name": search_entities_tool.name,
    "type": "tool_call",
}
tool.invoke(model_generated_tool_call)

链接

以下是完整示例，展示如何在链式调用或代理中集成 create_entity_tool 和 search_entities_tool 工具与 LLM。此示例假设您有一个函数（如 create_agent）用于设置 LangChain 风格的代理，能够在适当时机调用工具。

# Example: Using Taiga Tools in an Agent

from langchain.agents import create_agent
from langchain_taiga.tools.taiga_tools import create_entity_tool, search_entities_tool


# 1. Instantiate or configure your language model
# (Replace with your actual LLM, e.g., ChatOpenAI(temperature=0))
model = ...

# 2. Build an agent that has access to these tools
agent_executor = create_agent(model, [create_entity_tool, search_entities_tool])

# 4. Formulate a user query that may invoke one or both tools
example_query = "Please create a new user story with the subject 'subject' in slug project: 'slug'"

# 5. Execute the agent in streaming mode (or however your code is structured)
stream = agent_executor.stream_events(
    {"messages": [("user", example_query)]},
    version="v3",
)

# 6. Print out the model's responses (and any tool outputs) as they arrive
for snapshot in stream.values:
    snapshot["messages"][-1].pretty_print()

API 参考

请参阅以下文档中的文档字符串：

• - taiga_tools.py
• - toolkits.py

了解使用详情、参数和高级配置。