docs: add Taiga Tool integration docs (#30042)

This PR adds documentation for the langchain-taiga Tool integration,
including an example notebook at
'docs/docs/integrations/tools/taiga.ipynb' and updates to
'libs/packages.yml' to track the new package.

Issue:
N/A

Dependencies:
None

Twitter handle:
N/A

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
This commit is contained in:
Alexander Henlein
2025-03-04 18:51:20 +01:00
committed by GitHub
parent 5f0102242a
commit 417efa30a6
3 changed files with 359 additions and 0 deletions

View File

@@ -0,0 +1,49 @@
# Taiga
> [Taiga](https://docs.taiga.io/) is an open-source project management platform designed for agile teams, offering features like Kanban, Scrum, and issue tracking.
## Installation and Setup
Install the `langchain-taiga` package:
```bash
pip install langchain-taiga
```
You must provide a logins via environment variable so the tools can authenticate.
```bash
export TAIGA_URL="https://taiga.xyz.org/"
export TAIGA_API_URL="https://taiga.xyz.org/"
export TAIGA_USERNAME="username"
export TAIGA_PASSWORD="pw"
export OPENAI_API_KEY="OPENAI_API_KEY"
```
---
## Tools
See a [usage example](/docs/integrations/tools/taiga)
---
## Toolkit
`TaigaToolkit` groups multiple Taiga-related tools into a single interface.
```python
from langchain_taiga.toolkits import TaigaToolkit
toolkit = TaigaToolkit()
tools = toolkit.get_tools()
```
---
## Future Integrations
Check the [Taiga Developer Docs](https://docs.taiga.io/) for more information, and watch for updates or advanced usage examples in the [langchain_taiga GitHub repo](https://github.com/Shikenso-Analytics/langchain-taiga).

View File

@@ -0,0 +1,306 @@
{
"cells": [
{
"cell_type": "raw",
"id": "10238e62-3465-4973-9279-606cbb7ccf16",
"metadata": {},
"source": [
"---\n",
"sidebar_label: Taiga\n",
"---"
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": [
"# Taiga\n",
"\n",
"This notebook provides a quick overview for getting started with Taiga tooling in [langchain_taiga](https://github.com/Shikenso-Analytics/langchain-taiga/blob/main/docs/tools.ipynb). For more details on each tool and configuration, see the docstrings in your repository or relevant doc pages.\n",
"\n",
"\n",
"\n",
"## Overview\n",
"\n",
"### Integration details\n",
"\n",
"| Class | Package | Serializable | JS support | Package latest |\n",
"|:-----------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------| :---: |:------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------:|\n",
"| `create_entity_tool`, `search_entities_tool`, `get_entity_by_ref_tool`, `update_entity_by_ref_tool` , `add_comment_by_ref_tool`, `add_attachment_by_ref_tool` | [langchain-taiga](https://github.com/Shikenso-Analytics/langchain-taiga) | N/A | TBD | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-taiga?style=flat-square&label=%20) |\n",
"\n",
"### Tool features\n",
"\n",
"- **`create_entity_tool`**: Creates user stories, tasks and issues in Taiga.\n",
"- **`search_entities_tool`**: Searches for user stories, tasks and issues in Taiga.\n",
"- **`get_entity_by_ref_tool`**: Gets a user story, task or issue by reference.\n",
"- **`update_entity_by_ref_tool`**: Updates a user story, task or issue by reference.\n",
"- **`add_comment_by_ref_tool`**: Adds a comment to a user story, task or issue.\n",
"- **`add_attachment_by_ref_tool`**: Adds an attachment to a user story, task or issue.\n",
"\n",
"## Setup\n",
"\n",
"The integration lives in the `langchain-taiga` package."
],
"id": "41616bfd02d989a6"
},
{
"cell_type": "code",
"id": "f85b4089",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-28T12:43:23.290414Z",
"start_time": "2025-02-28T12:43:23.162563Z"
}
},
"source": "%pip install --quiet -U langchain-taiga",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/home/henlein/Workspace/PyCharm/langchain/.venv/bin/python: No module named pip\r\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"execution_count": 3
},
{
"cell_type": "markdown",
"id": "b15e9266",
"metadata": {},
"source": [
"### Credentials\n",
"\n",
"This integration requires you to set `TAIGA_URL`, `TAIGA_API_URL`, `TAIGA_USERNAME`, `TAIGA_PASSWORD` and `OPENAI_API_KEY` as environment variables to authenticate with Taiga.\n",
"\n",
"```bash\n",
"export TAIGA_URL=\"https://taiga.xyz.org/\"\n",
"export TAIGA_API_URL=\"https://taiga.xyz.org/\"\n",
"export TAIGA_USERNAME=\"username\"\n",
"export TAIGA_PASSWORD=\"pw\"\n",
"export OPENAI_API_KEY=\"OPENAI_API_KEY\"\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "bc5ab717-fd27-4c59-b912-bdd099541478",
"metadata": {},
"source": [
"It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability:"
]
},
{
"cell_type": "code",
"id": "a6c2f136-6367-4f1f-825d-ae741e1bf281",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-28T12:43:23.295879Z",
"start_time": "2025-02-28T12:43:23.293809Z"
}
},
"source": [
"# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
"# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
],
"outputs": [],
"execution_count": 4
},
{
"metadata": {},
"cell_type": "markdown",
"source": [
"## Instantiation\n",
"\n",
"Below is an example showing how to instantiate the Taiga tools in `langchain_taiga`. Adjust as needed for your specific usage."
],
"id": "d6eab61edeeb40a5"
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"source": [
"from langchain_taiga.tools.discord_read_messages import create_entity_tool\n",
"from langchain_taiga.tools.discord_send_messages import search_entities_tool\n",
"\n",
"create_tool = create_entity_tool\n",
"search_tool = search_entities_tool"
],
"id": "8ae97a3413cd040e"
},
{
"cell_type": "markdown",
"id": "74147a1a",
"metadata": {},
"source": [
"## Invocation\n",
"\n",
"### Direct invocation with args\n",
"\n",
"Below is a simple example of calling the tool with keyword arguments in a dictionary."
]
},
{
"cell_type": "code",
"id": "65310a8b-eb0c-4d9e-a618-4f4abe2414fc",
"metadata": {},
"source": [
"from langchain_taiga.tools.taiga_tools import (\n",
" add_attachment_by_ref_tool,\n",
" add_comment_by_ref_tool,\n",
" create_entity_tool,\n",
" get_entity_by_ref_tool,\n",
" search_entities_tool,\n",
" update_entity_by_ref_tool,\n",
")\n",
"\n",
"response = create_entity_tool.invoke(\n",
" {\n",
" \"project_slug\": \"slug\",\n",
" \"entity_type\": \"us\",\n",
" \"subject\": \"subject\",\n",
" \"status\": \"new\",\n",
" \"description\": \"desc\",\n",
" \"parent_ref\": 5,\n",
" \"assign_to\": \"user\",\n",
" \"due_date\": \"2022-01-01\",\n",
" \"tags\": [\"tag1\", \"tag2\"],\n",
" }\n",
")\n",
"\n",
"response = search_entities_tool.invoke(\n",
" {\"project_slug\": \"slug\", \"query\": \"query\", \"entity_type\": \"task\"}\n",
")\n",
"\n",
"response = get_entity_by_ref_tool.invoke(\n",
" {\"entity_type\": \"user_story\", \"project_id\": 1, \"ref\": \"1\"}\n",
")\n",
"\n",
"response = update_entity_by_ref_tool.invoke(\n",
" {\"project_slug\": \"slug\", \"entity_ref\": 555, \"entity_type\": \"us\"}\n",
")\n",
"\n",
"\n",
"response = add_comment_by_ref_tool.invoke(\n",
" {\"project_slug\": \"slug\", \"entity_ref\": 3, \"entity_type\": \"us\", \"comment\": \"new\"}\n",
")\n",
"\n",
"response = add_attachment_by_ref_tool.invoke(\n",
" {\n",
" \"project_slug\": \"slug\",\n",
" \"entity_ref\": 3,\n",
" \"entity_type\": \"us\",\n",
" \"attachment_url\": \"url\",\n",
" \"content_type\": \"png\",\n",
" \"description\": \"desc\",\n",
" }\n",
")"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"id": "d6e73897",
"metadata": {},
"source": [
"### Invocation with ToolCall\n",
"\n",
"If you have a model-generated `ToolCall`, pass it to `tool.invoke()` in the format shown below."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f90e33a7",
"metadata": {},
"outputs": [],
"source": [
"# This is usually generated by a model, but we'll create a tool call directly for demo purposes.\n",
"model_generated_tool_call = {\n",
" \"args\": {\"project_slug\": \"slug\", \"query\": \"query\", \"entity_type\": \"task\"},\n",
" \"id\": \"1\",\n",
" \"name\": search_entities_tool.name,\n",
" \"type\": \"tool_call\",\n",
"}\n",
"tool.invoke(model_generated_tool_call)"
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": [
"## Chaining\n",
"\n",
"Below is a more complete example showing how you might integrate the `create_entity_tool` and `search_entities_tool` tools in a chain or agent with an LLM. This example assumes you have a function (like `create_react_agent`) that sets up a LangChain-style agent capable of calling tools when appropriate.\n",
"\n",
"\n",
"```python\n",
"# Example: Using Taiga Tools in an Agent\n",
"\n",
"from langgraph.prebuilt import create_react_agent\n",
"from langchain_taiga.tools.taiga_tools import create_entity_tool, search_entities_tool\n",
"\n",
"# 1. Instantiate or configure your language model\n",
"# (Replace with your actual LLM, e.g., ChatOpenAI(temperature=0))\n",
"llm = ...\n",
"\n",
"# 2. Build an agent that has access to these tools\n",
"agent_executor = create_react_agent(llm, [create_entity_tool, search_entities_tool])\n",
"\n",
"# 4. Formulate a user query that may invoke one or both tools\n",
"example_query = \"Please create a new user story with the subject 'subject' in slug project: 'slug'\"\n",
"\n",
"# 5. Execute the agent in streaming mode (or however your code is structured)\n",
"events = agent_executor.stream(\n",
" {\"messages\": [(\"user\", example_query)]},\n",
" stream_mode=\"values\",\n",
")\n",
"\n",
"# 6. Print out the model's responses (and any tool outputs) as they arrive\n",
"for event in events:\n",
" event[\"messages\"][-1].pretty_print()\n",
"```\n"
],
"id": "8cafefef7c8bd43e"
},
{
"metadata": {},
"cell_type": "markdown",
"source": [
"## API reference\n",
"\n",
"See the docstrings in:\n",
"- [taiga_tools.py](https://github.com/Shikenso-Analytics/langchain-taiga/blob/main/langchain_taiga/tools/taiga_tools.py)\n",
"- [toolkits.py](https://github.com/Shikenso-Analytics/langchain-taiga/blob/main/langchain_taiga/toolkits.py)\n",
"\n",
"for usage details, parameters, and advanced configurations."
],
"id": "4ac8146c"
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@@ -470,3 +470,7 @@ packages:
repo: writer/langchain-writer
downloads: 0
downloads_updated_at: '2025-02-24T13:19:19.816059+00:00'
- name: langchain-taiga
name_title: Taiga
path: .
repo: Shikenso-Analytics/langchain-taiga