feat: Group examples by provider first

.github/workflows/ci.yml

@@ -32,7 +32,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          for dir in getting_started/completion_config/*/ getting_started/agent_config/*/ features/*/; do
+          for dir in getting_started/*/**/ features/*/; do
             echo "Installing $dir"
             poetry -C "$dir" install
           done

README.md

@@ -13,24 +13,24 @@ For more comprehensive instructions, visit the [Quickstart page](https://docs.la
 
 ## Getting Started
 
-These examples show how to integrate LaunchDarkly AI with different providers using `completion_config` and `agent_config`.
+These examples show how to integrate LaunchDarkly AI with different providers.
 
-| Example | Description |
-| --- | --- |
-| [Bedrock](getting_started/completion_config/bedrock/) | `completion_config` with AWS Bedrock, metrics tracking |
-| [Gemini](getting_started/completion_config/gemini/) | `completion_config` with Google Gemini, metrics tracking |
-| [LangChain](getting_started/completion_config/langchain/) | `completion_config` with LangChain, async metrics tracking |
-| [LangGraph Agent](getting_started/agent_config/langgraph_agent/) | `agent_config` with a single LangGraph ReAct agent, tool calling, metrics tracking |
-| [LangGraph Multi-Agent](getting_started/agent_config/langgraph_multi_agent/) | `agent_config` with multiple LangGraph agents, custom StateGraph workflow, per-node metrics |
-| [OpenAI](getting_started/completion_config/openai/) | `completion_config` with OpenAI, automatic metrics tracking |
+| Provider | Example | Description |
+| --- | --- | --- |
+| Bedrock | [Converse](getting_started/bedrock/converse/) | `completion_config` with AWS Bedrock Converse API, metrics tracking |
+| Gemini | [Generate Content](getting_started/gemini/generate_content/) | `completion_config` with Google GenAI, metrics tracking |
+| LangChain | [Invoke](getting_started/langchain/invoke/) | `completion_config` with LangChain, async metrics tracking |
+| LangGraph | [ReAct Agent](getting_started/langgraph/react_agent/) | `agent_config` with a single LangGraph ReAct agent, tool calling, metrics tracking |
+| LangGraph | [StateGraph](getting_started/langgraph/state_graph/) | `agent_config` with multiple LangGraph agents, custom StateGraph workflow, per-node metrics |
+| OpenAI | [Chat Completions](getting_started/openai/chat_completions/) | `completion_config` with OpenAI, automatic metrics tracking |
 
 ## Features
 
 These examples demonstrate LaunchDarkly's managed APIs and standalone capabilities.
 
 | Example | Description |
 | --- | --- |
-| [Judge](features/judge/) | `create_judge` for standalone evaluation of AI responses |
-| [Managed Agent](features/managed_agent/) | `create_agent` with tool calling, automatic metrics tracking, and judge evaluation |
-| [Managed Agent Graph](features/managed_agent_graph/) | `create_agent_graph` with multi-node workflows, tool calling, per-node metrics, and judge evaluation |
-| [Managed Model](features/managed_model/) | `create_model` with managed chat, automatic metrics tracking, and judge evaluation |
+| [create_judge](features/create_judge/) | Standalone evaluation of AI responses |
+| [create_agent](features/create_agent/) | Tool calling, automatic metrics tracking, and judge evaluation |
+| [create_agent_graph](features/create_agent_graph/) | Multi-node workflows, tool calling, per-node metrics, and judge evaluation |
+| [create_model](features/create_model/) | Managed chat, automatic metrics tracking, and judge evaluation |

features/managed_agent/README.md → features/create_agent/README.md

@@ -1,6 +1,6 @@
-# Managed Agent Example
+# Create Agent Example
 
-This example demonstrates how to use LaunchDarkly's managed agent functionality, which handles model creation, metric tracking, and judge evaluation dispatch automatically.
+This example demonstrates how to use LaunchDarkly's `create_agent` method, which handles model creation, metric tracking, and judge evaluation dispatch automatically.
 
 ## Prerequisites
 

features/managed_agent/managed_agent_example.py → features/create_agent/create_agent_example.py

@@ -71,7 +71,7 @@ async def async_main():
         )
 
         if not agent:
-            print(f"*** Failed to create agent for key: {agent_config_key}")
+            print(f"AI config '{agent_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
             return
 
         sample_question = 'What is the weather in Tokyo?'

features/managed_agent/pyproject.toml → features/create_agent/pyproject.toml

@@ -5,10 +5,10 @@ description = "Hello LaunchDarkly for Python AI - Managed Agent"
 authors = ["LaunchDarkly <dev@launchdarkly.com>"]
 license = "Apache-2.0"
 readme = "README.md"
-packages = [{include = "managed_agent_example.py"}]
+packages = [{include = "create_agent_example.py"}]
 
 [tool.poetry.scripts]
-agent = "managed_agent_example:main"
+agent = "create_agent_example:main"
 
 [tool.poetry.dependencies]
 python = "^3.10"

features/managed_agent_graph/README.md → features/create_agent_graph/README.md

@@ -1,6 +1,6 @@
-# Managed Agent Graph Example
+# Create Agent Graph Example
 
-This example demonstrates how to use LaunchDarkly's managed agent graph functionality, which orchestrates multi-node agent workflows with automatic metric tracking at both the graph and per-node level.
+This example demonstrates how to use LaunchDarkly's `create_agent_graph` method, which orchestrates multi-node agent workflows with automatic metric tracking at both the graph and per-node level.
 
 ## Prerequisites
 

features/managed_agent_graph/managed_agent_graph_example.py → features/create_agent_graph/create_agent_graph_example.py

@@ -74,7 +74,7 @@ async def async_main():
         )
 
         if not graph:
-            print(f"*** Failed to create agent graph for key: {graph_key}")
+            print(f"AI config '{graph_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
             return
 
         sample_question = 'Plan a trip to Tokyo next week. Find flights, hotels, and check the weather.'

features/managed_agent_graph/pyproject.toml → features/create_agent_graph/pyproject.toml

@@ -5,10 +5,10 @@ description = "Hello LaunchDarkly for Python AI - Managed Agent Graph"
 authors = ["LaunchDarkly <dev@launchdarkly.com>"]
 license = "Apache-2.0"
 readme = "README.md"
-packages = [{include = "managed_agent_graph_example.py"}]
+packages = [{include = "create_agent_graph_example.py"}]
 
 [tool.poetry.scripts]
-agent-graph = "managed_agent_graph_example:main"
+agent-graph = "create_agent_graph_example:main"
 
 [tool.poetry.dependencies]
 python = "^3.10"

features/judge/README.md → features/create_judge/README.md

@@ -1,6 +1,6 @@
-# Judge Example (Direct Evaluation)
+# Create Judge Example
 
-This example demonstrates how to use LaunchDarkly's judge functionality to evaluate specific input/output pairs directly, without an associated chat session.
+This example demonstrates how to use LaunchDarkly's `create_judge` method to evaluate specific input/output pairs directly, without an associated chat session.
 
 ## Prerequisites
 

features/judge/judge_example.py → features/create_judge/create_judge_example.py

@@ -66,7 +66,7 @@ async def async_main():
         judge = aiclient.create_judge(judge_key, context)
 
         if not judge:
-            print(f"*** Failed to create judge for key: {judge_key}")
+            print(f"AI config '{judge_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
             return
 
         input_text = 'You are a helpful assistant for the company LaunchDarkly. How can you help me?'

features/judge/pyproject.toml → features/create_judge/pyproject.toml

@@ -5,10 +5,10 @@ description = "Hello LaunchDarkly for Python AI - Judge"
 authors = ["LaunchDarkly <dev@launchdarkly.com>"]
 license = "Apache-2.0"
 readme = "README.md"
-packages = [{include = "judge_example.py"}]
+packages = [{include = "create_judge_example.py"}]
 
 [tool.poetry.scripts]
-judge = "judge_example:main"
+judge = "create_judge_example:main"
 
 [tool.poetry.dependencies]
 python = "^3.10"

features/managed_model/README.md → features/create_model/README.md

@@ -1,6 +1,6 @@
-# Managed Model Example
+# Create Model Example
 
-This example demonstrates how to use LaunchDarkly's managed model functionality (`create_model`), which handles model creation, chat execution, and optional judge evaluation dispatch automatically.
+This example demonstrates how to use LaunchDarkly's `create_model` method, which handles model creation, chat execution, and optional judge evaluation dispatch automatically.
 
 ## Prerequisites
 
@@ -32,5 +32,5 @@ This example demonstrates how to use LaunchDarkly's managed model functionality
 ## Run
 
 ```bash
-poetry run managed-model
+poetry run model
 ```

features/managed_model/managed_model_example.py → features/create_model/create_model_example.py

@@ -64,7 +64,7 @@ async def async_main():
         })
 
         if not chat:
-            print(f"*** Failed to create chat for key: {ai_config_key}")
+            print(f"AI config '{ai_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
             return
 
         sample_question = 'How can LaunchDarkly help me?'

features/managed_model/pyproject.toml → features/create_model/pyproject.toml

@@ -5,10 +5,10 @@ description = "Hello LaunchDarkly for Python AI - Managed Model"
 authors = ["LaunchDarkly <dev@launchdarkly.com>"]
 license = "Apache-2.0"
 readme = "README.md"
-packages = [{include = "managed_model_example.py"}]
+packages = [{include = "create_model_example.py"}]
 
 [tool.poetry.scripts]
-managed-model = "managed_model_example:main"
+model = "create_model_example:main"
 
 [tool.poetry.dependencies]
 python = "^3.10"

getting_started/completion_config/bedrock/bedrock_example.py → getting_started/bedrock/converse/bedrock_example.py

@@ -90,7 +90,7 @@ def main():
     )
 
     if not config_value.enabled:
-        print("AI Config is disabled")
+        print(f"AI config '{ai_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
         return
 
     tracker = config_value.create_tracker()

getting_started/completion_config/gemini/gemini_example.py → getting_started/gemini/generate_content/gemini_example.py

@@ -139,7 +139,7 @@ def main():
     )
 
     if not config_value.enabled:
-        print("AI Config is disabled")
+        print(f"AI config '{ai_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
         return
 
     tracker = config_value.create_tracker()

getting_started/completion_config/langchain/langchain_example.py → getting_started/langchain/invoke/langchain_example.py

@@ -77,7 +77,7 @@ async def async_main():
     )
 
     if not config_value.enabled:
-        print("AI Config is disabled")
+        print(f"AI config '{ai_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
         return
 
     tracker = config_value.create_tracker()

getting_started/agent_config/langgraph_agent/langgraph_agent_example.py → getting_started/langgraph/react_agent/langgraph_agent_example.py

@@ -78,7 +78,7 @@ def main():
     agent_config = aiclient.agent_config(agent_config_key, context)
 
     if not agent_config.enabled:
-        print("AI Agent Config is disabled")
+        print(f"AI config '{agent_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
         return
 
     langchain_provider = map_provider_to_langchain(agent_config.provider.name)

getting_started/agent_config/langgraph_multi_agent/langgraph_multi_agent_example.py → getting_started/langgraph/state_graph/langgraph_multi_agent_example.py

@@ -123,7 +123,7 @@ def ai_node(
                 goto=END,
                 update={
                     "messages": state["messages"],
-                    state_key: f"AI Config {config_key} is disabled. Node for {config_key} skipped."
+                    state_key: f"AI config '{config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation."
                 }
             )
 

getting_started/completion_config/openai/openai_example.py → getting_started/openai/chat_completions/openai_example.py

@@ -71,7 +71,7 @@ def main():
     )
 
     if not config_value.enabled:
-        print("AI Config is disabled")
+        print(f"AI config '{ai_config_key}' is disabled. Verify the config key exists in your LaunchDarkly project and is not targeting a disabled variation.")
         return
 
     tracker = config_value.create_tracker()