stackone-ai 2.7.0__tar.gz → 2.9.0__tar.gz

stackone_ai-2.9.0/.env.example

@@ -0,0 +1,6 @@
+# Required for all examples
+STACKONE_API_KEY=your-stackone-api-key
+STACKONE_ACCOUNT_ID=your-account-id
+
+# Required for OpenAI-based examples (openai_integration, langchain_integration, crewai_integration, search_tools)
+OPENAI_API_KEY=your-openai-api-key

{stackone_ai-2.7.0 → stackone_ai-2.9.0}/.gitignore

@@ -1,5 +1,6 @@
 .env
 .env.*
+!.env.example
 .venv
 
 .pytest_cache

stackone_ai-2.9.0/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "2.9.0"
+}

{stackone_ai-2.7.0 → stackone_ai-2.9.0}/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## [2.9.0](https://github.com/StackOneHQ/stackone-ai-python/compare/stackone-ai-v2.8.0...stackone-ai-v2.9.0) (2026-04-30)
+
+
+### Features
+
+* **integrations:** add native Pydantic AI support ([#184](https://github.com/StackOneHQ/stackone-ai-python/issues/184)) ([8216ab6](https://github.com/StackOneHQ/stackone-ai-python/commit/8216ab6c0776b0753cf3e68461bf5e8a9b044b06))
+
+## [2.8.0](https://github.com/StackOneHQ/stackone-ai-python/compare/stackone-ai-v2.7.0...stackone-ai-v2.8.0) (2026-04-20)
+
+
+### Features
+
+* **examples:** streamline examples, standardize auth patterns and migrate examples to Workday ([#179](https://github.com/StackOneHQ/stackone-ai-python/issues/179)) ([0bdc939](https://github.com/StackOneHQ/stackone-ai-python/commit/0bdc939e2844a0dae6bf527c8c8209df0a90d1f7))
+
 ## [2.7.0](https://github.com/StackOneHQ/stackone-ai-python/compare/stackone-ai-v2.6.0...stackone-ai-v2.7.0) (2026-04-14)
 
 

stackone_ai-2.7.0/README.md → stackone_ai-2.9.0/PKG-INFO

@@ -1,3 +1,38 @@
+Metadata-Version: 2.4
+Name: stackone-ai
+Version: 2.9.0
+Summary: agents performing actions on your SaaS
+Author-email: StackOne <support@stackone.com>
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: bm25s>=0.2.2
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: langchain-core>=0.1.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pydantic>=2.10.6
+Requires-Dist: typing-extensions>=4.0.0
+Provides-Extra: examples
+Requires-Dist: crewai>=0.102.0; extra == 'examples'
+Requires-Dist: langchain-openai>=1.1.14; extra == 'examples'
+Requires-Dist: langgraph>=1.1.6; extra == 'examples'
+Requires-Dist: openai>=2.32.0; extra == 'examples'
+Requires-Dist: pydantic-ai>=1.83.0; extra == 'examples'
+Requires-Dist: python-dotenv>=1.0.1; extra == 'examples'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.3.0; extra == 'mcp'
+Provides-Extra: pydantic-ai
+Requires-Dist: pydantic-ai-slim<2.0.0,>=1.83.0; extra == 'pydantic-ai'
+Description-Content-Type: text/markdown
+
 # StackOne AI SDK
 
 [![PyPI version](https://badge.fury.io/py/stackone-ai.svg)](https://badge.fury.io/py/stackone-ai)
@@ -26,6 +61,7 @@ StackOne AI provides a unified interface for accessing various SaaS tools throug
   - LangChain Tools
   - CrewAI Tools
   - LangGraph Tool Node
+  - Pydantic AI Toolset
 
 ## Requirements
 
@@ -52,17 +88,18 @@ uv add 'stackone-ai[mcp,examples]'
 ## Quick Start
 
 ```python
+import os
 from stackone_ai import StackOneToolSet
 
-# Initialize with API key
-toolset = StackOneToolSet()  # Uses STACKONE_API_KEY env var
-# Or explicitly: toolset = StackOneToolSet(api_key="your-api-key")
+# Initialize — reads STACKONE_API_KEY from environment
+toolset = StackOneToolSet()
 
-# Get HRIS-related tools with glob patterns
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+# Fetch tools — pass account ID from STACKONE_ACCOUNT_ID env var
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 
 # Use a specific tool with the call method
-employee_tool = tools.get_tool("bamboohr_get_employee")
+employee_tool = tools.get_tool("workday_get_worker")
 # Call with keyword arguments
 employee = employee_tool.call(id="employee-id")
 # Or with traditional execute method
@@ -86,7 +123,7 @@ toolset = StackOneToolSet()
 tools = toolset.fetch_tools(account_ids=["acc-123", "acc-456"])
 
 # Filter by providers (case-insensitive)
-tools = toolset.fetch_tools(providers=["hibob", "bamboohr"])
+tools = toolset.fetch_tools(providers=["hibob", "workday"])
 
 # Filter by action patterns with glob support
 tools = toolset.fetch_tools(actions=["*_list_employees"])
@@ -106,11 +143,11 @@ tools = toolset.fetch_tools(providers=["hibob"])
 **Filtering Options:**
 
 - **`account_ids`**: Filter tools by account IDs. Tools will be loaded for each specified account.
-- **`providers`**: Filter by provider names (e.g., `["hibob", "bamboohr"]`). Case-insensitive matching.
+- **`providers`**: Filter by provider names (e.g., `["hibob", "workday"]`). Case-insensitive matching.
 - **`actions`**: Filter by action patterns with glob support:
-  - Exact match: `["bamboohr_list_employees"]`
+  - Exact match: `["workday_list_workers"]`
   - Glob pattern: `["*_list_employees"]` matches all tools ending with `_list_employees`
-  - Provider prefix: `["bamboohr_*"]` matches all BambooHR tools
+  - Provider prefix: `["workday_*"]` matches all Workday tools
 
 ## Implicit Feedback (Beta)
 
@@ -165,18 +202,20 @@ When two calls for the same session happen within a few seconds, the SDK emits a
 StackOne tools work seamlessly with LangChain, enabling powerful AI agent workflows:
 
 ```python
+import os
 from langchain_openai import ChatOpenAI
 from stackone_ai import StackOneToolSet
 
 # Initialize StackOne tools
 toolset = StackOneToolSet()
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 
 # Convert to LangChain format
 langchain_tools = tools.to_langchain()
 
 # Use with LangChain models
-model = ChatOpenAI(model="gpt-4o-mini")
+model = ChatOpenAI(model="gpt-5.4")
 model_with_tools = model.bind_tools(langchain_tools)
 
 # Execute AI-driven tool calls
@@ -192,6 +231,43 @@ for tool_call in response.tool_calls:
 
 </details>
 
+<details>
+<summary>Pydantic AI Integration</summary>
+
+StackOne tools convert to Pydantic AI `Tool` instances via `.to_pydantic_ai()`, parallel to `.to_openai()` and `.to_langchain()`:
+
+Prerequisites:
+
+```bash
+pip install 'stackone-ai[pydantic-ai]'
+```
+
+```python
+import os
+from pydantic_ai import Agent
+from stackone_ai import StackOneToolSet
+
+toolset = StackOneToolSet()
+tools = toolset.fetch_tools(
+    actions=["workday_list_workers", "workday_get_worker"],
+    account_ids=[os.environ["STACKONE_ACCOUNT_ID"]],
+).to_pydantic_ai()
+
+agent = Agent("openai:gpt-5.4", tools=tools)
+result = agent.run_sync("List the first 5 employees")
+print(result.output)
+```
+
+For the full catalog (or the meta search/execute tools), use the `.pydantic_ai()` method on `StackOneToolSet` — parallel to `.openai()` / `.langchain()`:
+
+```python
+toolset = StackOneToolSet()
+tools = toolset.pydantic_ai(account_ids=[os.environ["STACKONE_ACCOUNT_ID"]])
+# or pydantic_ai(mode="search_and_execute") for agent-driven discovery
+```
+
+</details>
+
 <details>
 <summary>LangGraph Integration</summary>
 
@@ -204,6 +280,7 @@ pip install langgraph langchain-openai
 ```
 
 ```python
+import os
 from langchain_openai import ChatOpenAI
 from typing import Annotated
 from typing_extensions import TypedDict
@@ -217,7 +294,8 @@ from stackone_ai.integrations.langgraph import to_tool_node, bind_model_with_too
 
 # Prepare tools
 toolset = StackOneToolSet()
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 langchain_tools = tools.to_langchain()
 
 class State(TypedDict):
@@ -228,7 +306,7 @@ graph = StateGraph(State)
 graph.add_node("tools", to_tool_node(langchain_tools))
 
 def call_llm(state: dict):
-    llm = ChatOpenAI(model="gpt-4o-mini")
+    llm = ChatOpenAI(model="gpt-5.4")
     llm = bind_model_with_tools(llm, langchain_tools)
     resp = llm.invoke(state["messages"])  # returns AIMessage with optional tool_calls
     return {"messages": state["messages"] + [resp]}
@@ -250,12 +328,14 @@ _ = app.invoke({"messages": [("user", "Get employee with id emp123") ]})
 CrewAI uses LangChain tools natively, making integration seamless:
 
 ```python
+import os
 from crewai import Agent, Crew, Task
 from stackone_ai import StackOneToolSet
 
 # Get tools and convert to LangChain format
 toolset = StackOneToolSet()
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 langchain_tools = tools.to_langchain()
 
 # Create CrewAI agent with StackOne tools
@@ -264,7 +344,7 @@ agent = Agent(
     goal="Analyze employee data and generate insights",
     backstory="Expert in HR analytics and employee management",
     tools=langchain_tools,
-    llm="gpt-4o-mini"
+    llm="gpt-5.4"
 )
 
 # Define task and execute
@@ -297,7 +377,7 @@ feedback_tool = tools.get_tool("tool_feedback")
 result = feedback_tool.call(
     feedback="The HRIS tools are working great! Very fast response times.",
     account_id="acc_123456",
-    tool_names=["bamboohr_list_employees", "bamboohr_get_employee"]
+    tool_names=["workday_list_workers", "workday_get_worker"]
 )
 ```
 
@@ -313,9 +393,12 @@ Search for tools using natural language queries. Works with both semantic (cloud
 ### Basic Usage
 
 ```python
+import os
+
 # Get a callable search tool
 toolset = StackOneToolSet()
-all_tools = toolset.fetch_tools(account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+all_tools = toolset.fetch_tools(account_ids=[account_id])
 search_tool = toolset.get_search_tool()
 
 # Search for relevant tools — returns a Tools collection
@@ -327,15 +410,17 @@ tools[0](limit=10)
 
 ## Semantic Search
 
-Discover tools using natural language instead of exact names. Queries like "onboard new hire" resolve to the right actions even when the tool is called `bamboohr_create_employee`.
+Discover tools using natural language instead of exact names. Queries like "onboard new hire" resolve to the right actions even when the tool is called `workday_create_employee`.
 
 ```python
+import os
 from stackone_ai import StackOneToolSet
 
 toolset = StackOneToolSet()
 
 # Search by intent — returns Tools collection ready for any framework
-tools = toolset.search_tools("manage employee records", account_ids=["your-account-id"], top_k=5)
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.search_tools("manage employee records", account_ids=[account_id], top_k=5)
 openai_tools = tools.to_openai()
 
 # Lightweight: inspect results without fetching full tool definitions
@@ -357,19 +442,31 @@ tools = toolset.search_tools("manage employees", search="semantic")
 tools = toolset.search_tools("manage employees", search="local")
 ```
 
-Results are automatically scoped to connectors in your linked accounts. See [Semantic Search Example](examples/semantic_search_example.py) for `SearchTool` (`get_search_tool`) integration, OpenAI, and LangChain patterns.
+Results are automatically scoped to connectors in your linked accounts. See [Search Tools Example](examples/search_tools.py) for `SearchTool` (`get_search_tool`) integration, OpenAI, and LangChain patterns.
 
 ## Examples
 
 For more examples, check out the [examples/](examples/) directory:
 
-- [StackOne Account IDs](examples/stackone_account_ids.py)
-- [File Uploads](examples/file_uploads.py)
-- [OpenAI Integration](examples/openai_integration.py)
-- [LangChain Integration](examples/langchain_integration.py)
-- [CrewAI Integration](examples/crewai_integration.py)
-- [Search Tool](examples/search_tool_example.py)
-- [Semantic Search](examples/semantic_search_example.py)
+- [OpenAI Integration](examples/openai_integration.py) — OpenAI function calling
+- [LangChain Integration](examples/langchain_integration.py) — LangChain tools
+- [CrewAI Integration](examples/crewai_integration.py) — CrewAI agent
+- [Search Tools](examples/search_tools.py) — Tool discovery (semantic, local, auto search)
+- [Auth Management](examples/auth_management.py) — API key and account ID patterns
+
+### Running Examples
+
+```bash
+# 1. Set up credentials
+cp .env.example .env
+# Edit .env with your API keys
+
+# 2. Install dependencies
+uv sync --all-extras
+
+# 3. Run any example
+uv run examples/search_tools.py
+```
 
 ## Development
 

stackone_ai-2.7.0/PKG-INFO → stackone_ai-2.9.0/README.md

@@ -1,35 +1,3 @@
-Metadata-Version: 2.4
-Name: stackone-ai
-Version: 2.7.0
-Summary: agents performing actions on your SaaS
-Author-email: StackOne <support@stackone.com>
-License-File: LICENSE
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.10
-Requires-Dist: bm25s>=0.2.2
-Requires-Dist: httpx>=0.28.0
-Requires-Dist: langchain-core>=0.1.0
-Requires-Dist: numpy>=1.24.0
-Requires-Dist: pydantic>=2.10.6
-Requires-Dist: typing-extensions>=4.0.0
-Provides-Extra: examples
-Requires-Dist: crewai>=0.102.0; extra == 'examples'
-Requires-Dist: langchain-openai>=0.3.6; extra == 'examples'
-Requires-Dist: langgraph>=0.2.0; extra == 'examples'
-Requires-Dist: openai>=1.63.2; extra == 'examples'
-Requires-Dist: python-dotenv>=1.0.1; extra == 'examples'
-Provides-Extra: mcp
-Requires-Dist: mcp>=1.3.0; extra == 'mcp'
-Description-Content-Type: text/markdown
-
 # StackOne AI SDK
 
 [![PyPI version](https://badge.fury.io/py/stackone-ai.svg)](https://badge.fury.io/py/stackone-ai)
@@ -58,6 +26,7 @@ StackOne AI provides a unified interface for accessing various SaaS tools throug
   - LangChain Tools
   - CrewAI Tools
   - LangGraph Tool Node
+  - Pydantic AI Toolset
 
 ## Requirements
 
@@ -84,17 +53,18 @@ uv add 'stackone-ai[mcp,examples]'
 ## Quick Start
 
 ```python
+import os
 from stackone_ai import StackOneToolSet
 
-# Initialize with API key
-toolset = StackOneToolSet()  # Uses STACKONE_API_KEY env var
-# Or explicitly: toolset = StackOneToolSet(api_key="your-api-key")
+# Initialize — reads STACKONE_API_KEY from environment
+toolset = StackOneToolSet()
 
-# Get HRIS-related tools with glob patterns
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+# Fetch tools — pass account ID from STACKONE_ACCOUNT_ID env var
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 
 # Use a specific tool with the call method
-employee_tool = tools.get_tool("bamboohr_get_employee")
+employee_tool = tools.get_tool("workday_get_worker")
 # Call with keyword arguments
 employee = employee_tool.call(id="employee-id")
 # Or with traditional execute method
@@ -118,7 +88,7 @@ toolset = StackOneToolSet()
 tools = toolset.fetch_tools(account_ids=["acc-123", "acc-456"])
 
 # Filter by providers (case-insensitive)
-tools = toolset.fetch_tools(providers=["hibob", "bamboohr"])
+tools = toolset.fetch_tools(providers=["hibob", "workday"])
 
 # Filter by action patterns with glob support
 tools = toolset.fetch_tools(actions=["*_list_employees"])
@@ -138,11 +108,11 @@ tools = toolset.fetch_tools(providers=["hibob"])
 **Filtering Options:**
 
 - **`account_ids`**: Filter tools by account IDs. Tools will be loaded for each specified account.
-- **`providers`**: Filter by provider names (e.g., `["hibob", "bamboohr"]`). Case-insensitive matching.
+- **`providers`**: Filter by provider names (e.g., `["hibob", "workday"]`). Case-insensitive matching.
 - **`actions`**: Filter by action patterns with glob support:
-  - Exact match: `["bamboohr_list_employees"]`
+  - Exact match: `["workday_list_workers"]`
   - Glob pattern: `["*_list_employees"]` matches all tools ending with `_list_employees`
-  - Provider prefix: `["bamboohr_*"]` matches all BambooHR tools
+  - Provider prefix: `["workday_*"]` matches all Workday tools
 
 ## Implicit Feedback (Beta)
 
@@ -197,18 +167,20 @@ When two calls for the same session happen within a few seconds, the SDK emits a
 StackOne tools work seamlessly with LangChain, enabling powerful AI agent workflows:
 
 ```python
+import os
 from langchain_openai import ChatOpenAI
 from stackone_ai import StackOneToolSet
 
 # Initialize StackOne tools
 toolset = StackOneToolSet()
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 
 # Convert to LangChain format
 langchain_tools = tools.to_langchain()
 
 # Use with LangChain models
-model = ChatOpenAI(model="gpt-4o-mini")
+model = ChatOpenAI(model="gpt-5.4")
 model_with_tools = model.bind_tools(langchain_tools)
 
 # Execute AI-driven tool calls
@@ -224,6 +196,43 @@ for tool_call in response.tool_calls:
 
 </details>
 
+<details>
+<summary>Pydantic AI Integration</summary>
+
+StackOne tools convert to Pydantic AI `Tool` instances via `.to_pydantic_ai()`, parallel to `.to_openai()` and `.to_langchain()`:
+
+Prerequisites:
+
+```bash
+pip install 'stackone-ai[pydantic-ai]'
+```
+
+```python
+import os
+from pydantic_ai import Agent
+from stackone_ai import StackOneToolSet
+
+toolset = StackOneToolSet()
+tools = toolset.fetch_tools(
+    actions=["workday_list_workers", "workday_get_worker"],
+    account_ids=[os.environ["STACKONE_ACCOUNT_ID"]],
+).to_pydantic_ai()
+
+agent = Agent("openai:gpt-5.4", tools=tools)
+result = agent.run_sync("List the first 5 employees")
+print(result.output)
+```
+
+For the full catalog (or the meta search/execute tools), use the `.pydantic_ai()` method on `StackOneToolSet` — parallel to `.openai()` / `.langchain()`:
+
+```python
+toolset = StackOneToolSet()
+tools = toolset.pydantic_ai(account_ids=[os.environ["STACKONE_ACCOUNT_ID"]])
+# or pydantic_ai(mode="search_and_execute") for agent-driven discovery
+```
+
+</details>
+
 <details>
 <summary>LangGraph Integration</summary>
 
@@ -236,6 +245,7 @@ pip install langgraph langchain-openai
 ```
 
 ```python
+import os
 from langchain_openai import ChatOpenAI
 from typing import Annotated
 from typing_extensions import TypedDict
@@ -249,7 +259,8 @@ from stackone_ai.integrations.langgraph import to_tool_node, bind_model_with_too
 
 # Prepare tools
 toolset = StackOneToolSet()
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 langchain_tools = tools.to_langchain()
 
 class State(TypedDict):
@@ -260,7 +271,7 @@ graph = StateGraph(State)
 graph.add_node("tools", to_tool_node(langchain_tools))
 
 def call_llm(state: dict):
-    llm = ChatOpenAI(model="gpt-4o-mini")
+    llm = ChatOpenAI(model="gpt-5.4")
     llm = bind_model_with_tools(llm, langchain_tools)
     resp = llm.invoke(state["messages"])  # returns AIMessage with optional tool_calls
     return {"messages": state["messages"] + [resp]}
@@ -282,12 +293,14 @@ _ = app.invoke({"messages": [("user", "Get employee with id emp123") ]})
 CrewAI uses LangChain tools natively, making integration seamless:
 
 ```python
+import os
 from crewai import Agent, Crew, Task
 from stackone_ai import StackOneToolSet
 
 # Get tools and convert to LangChain format
 toolset = StackOneToolSet()
-tools = toolset.fetch_tools(actions=["bamboohr_*"], account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.fetch_tools(actions=["workday_*"], account_ids=[account_id])
 langchain_tools = tools.to_langchain()
 
 # Create CrewAI agent with StackOne tools
@@ -296,7 +309,7 @@ agent = Agent(
     goal="Analyze employee data and generate insights",
     backstory="Expert in HR analytics and employee management",
     tools=langchain_tools,
-    llm="gpt-4o-mini"
+    llm="gpt-5.4"
 )
 
 # Define task and execute
@@ -329,7 +342,7 @@ feedback_tool = tools.get_tool("tool_feedback")
 result = feedback_tool.call(
     feedback="The HRIS tools are working great! Very fast response times.",
     account_id="acc_123456",
-    tool_names=["bamboohr_list_employees", "bamboohr_get_employee"]
+    tool_names=["workday_list_workers", "workday_get_worker"]
 )
 ```
 
@@ -345,9 +358,12 @@ Search for tools using natural language queries. Works with both semantic (cloud
 ### Basic Usage
 
 ```python
+import os
+
 # Get a callable search tool
 toolset = StackOneToolSet()
-all_tools = toolset.fetch_tools(account_ids=["your-account-id"])
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+all_tools = toolset.fetch_tools(account_ids=[account_id])
 search_tool = toolset.get_search_tool()
 
 # Search for relevant tools — returns a Tools collection
@@ -359,15 +375,17 @@ tools[0](limit=10)
 
 ## Semantic Search
 
-Discover tools using natural language instead of exact names. Queries like "onboard new hire" resolve to the right actions even when the tool is called `bamboohr_create_employee`.
+Discover tools using natural language instead of exact names. Queries like "onboard new hire" resolve to the right actions even when the tool is called `workday_create_employee`.
 
 ```python
+import os
 from stackone_ai import StackOneToolSet
 
 toolset = StackOneToolSet()
 
 # Search by intent — returns Tools collection ready for any framework
-tools = toolset.search_tools("manage employee records", account_ids=["your-account-id"], top_k=5)
+account_id = os.getenv("STACKONE_ACCOUNT_ID")
+tools = toolset.search_tools("manage employee records", account_ids=[account_id], top_k=5)
 openai_tools = tools.to_openai()
 
 # Lightweight: inspect results without fetching full tool definitions
@@ -389,19 +407,31 @@ tools = toolset.search_tools("manage employees", search="semantic")
 tools = toolset.search_tools("manage employees", search="local")
 ```
 
-Results are automatically scoped to connectors in your linked accounts. See [Semantic Search Example](examples/semantic_search_example.py) for `SearchTool` (`get_search_tool`) integration, OpenAI, and LangChain patterns.
+Results are automatically scoped to connectors in your linked accounts. See [Search Tools Example](examples/search_tools.py) for `SearchTool` (`get_search_tool`) integration, OpenAI, and LangChain patterns.
 
 ## Examples
 
 For more examples, check out the [examples/](examples/) directory:
 
-- [StackOne Account IDs](examples/stackone_account_ids.py)
-- [File Uploads](examples/file_uploads.py)
-- [OpenAI Integration](examples/openai_integration.py)
-- [LangChain Integration](examples/langchain_integration.py)
-- [CrewAI Integration](examples/crewai_integration.py)
-- [Search Tool](examples/search_tool_example.py)
-- [Semantic Search](examples/semantic_search_example.py)
+- [OpenAI Integration](examples/openai_integration.py) — OpenAI function calling
+- [LangChain Integration](examples/langchain_integration.py) — LangChain tools
+- [CrewAI Integration](examples/crewai_integration.py) — CrewAI agent
+- [Search Tools](examples/search_tools.py) — Tool discovery (semantic, local, auto search)
+- [Auth Management](examples/auth_management.py) — API key and account ID patterns
+
+### Running Examples
+
+```bash
+# 1. Set up credentials
+cp .env.example .env
+# Edit .env with your API keys
+
+# 2. Install dependencies
+uv sync --all-extras
+
+# 3. Run any example
+uv run examples/search_tools.py
+```
 
 ## Development