Simplify Python Client page: trim features, reorder use cases

Remove verbose usage examples (reference client README instead),
simplify feature list, move Data Apps above CLI use case, and
clarify Python/JS Data Apps availability.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: jordanrburger

kai/python-client.md

@@ -11,12 +11,10 @@ The [Kai Python Client](https://github.com/keboola/kai-client) is an official Py
 ## Features
 
 - **Command-line interface** for quick interactions without writing code
-- **Async/await support** using `httpx`
-- **Server-Sent Events (SSE) streaming** for real-time chat responses
-- **Type-safe models** with Pydantic v2
-- **Comprehensive error handling** with custom exception classes
-- **Session management** for chat conversations
-- **Full API coverage** including chat, history, and voting endpoints
+- **Real-time streaming** — see responses as they arrive
+- **Conversation management** — maintain context across multiple messages
+- **Tool approval flows** — review and approve Kai actions programmatically
+- **Full API coverage** — chat, history, and feedback
 
 ## Installation
 
@@ -95,120 +93,44 @@ In interactive mode, type your messages and press Enter. Type `exit`, `quit`, or
 
 **Tool approval:** When Kai calls a write tool (e.g., `update_descriptions`, `run_job`, `create_config`), the CLI pauses and asks you to approve or deny. Use `--auto-approve` to skip this prompt.
 
-## Usage Examples
+For more usage examples (non-streaming chat, conversations, tool calls, tool approval, error handling), see the [client README](https://github.com/keboola/kai-client#readme).
 
-### Simple Chat (Non-Streaming)
+## Use Cases
 
-```python
-async with KaiClient(
-    storage_api_token="your-master-token",
-    storage_api_url="https://connection.keboola.com"
-) as client:
-    chat_id, response = await client.chat("What is 2 + 2?")
-    print(response)
-```
+### Integrating Kai into Data Apps
 
-### Continuing a Conversation
+The Kai Python Client can be embedded into Keboola [Data Apps](/data-apps/) to provide AI-powered chat interfaces for your end users.
 
-```python
-async with KaiClient(
-    storage_api_token="your-master-token",
-    storage_api_url="https://connection.keboola.com"
-) as client:
-    chat_id = client.new_chat_id()
-
-    # First message
-    async for event in client.send_message(chat_id, "Hello!"):
-        if event.type == "text":
-            print(event.text, end="")
-    print()
-
-    # Continue the conversation (reuse same chat_id)
-    async for event in client.send_message(chat_id, "What did I just say?"):
-        if event.type == "text":
-            print(event.text, end="")
-    print()
-```
+#### Python/JS Data Apps
 
-### Handling Tool Calls
+You can integrate Kai into [Python/JS Data Apps](/data-apps/python-js/) today using the Kai Python Client directly. A dedicated plugin with ready-made patterns will be available soon to simplify the setup.
 
-```python
-async with KaiClient(
-    storage_api_token="your-master-token",
-    storage_api_url="https://connection.keboola.com"
-) as client:
-    chat_id = client.new_chat_id()
-
-    async for event in client.send_message(chat_id, "List my Keboola tables"):
-        match event.type:
-            case "text":
-                print(event.text, end="")
-            case "tool-call":
-                if event.state == "input-available":
-                    print(f"\n[Calling {event.tool_name} with {event.input}]")
-                elif event.state == "output-available":
-                    print(f"\n[{event.tool_name} returned: {event.output}]")
-            case "finish":
-                print(f"\n[Done: {event.finish_reason}]")
-```
-
-### Tool Approval for Write Operations
+#### Streamlit Data Apps
 
-Some tools require explicit approval before execution. The server sends a `tool-approval-request` event with an `approval_id` that you use to approve or reject.
+The [kai-streamlit plugin](https://github.com/keboola/kai-client/tree/main/plugins/kai-streamlit) provides patterns and working code for building [Streamlit Data Apps](/data-apps/streamlit/) with an integrated Kai chat interface. It handles the async bridge between Streamlit's synchronous model and the KaiClient's async API, streaming responses into Streamlit containers, tool approval flows with interactive Approve/Deny buttons, and session state management across Streamlit reruns.
 
-```python
-from kai_client import KaiClient
+To get started, install the dependencies:
 
-async with KaiClient(
-    storage_api_token="your-master-token",
-    storage_api_url="https://connection.keboola.com"
-) as client:
-    chat_id = client.new_chat_id()
-    pending_approval_id = None
-
-    async for event in client.send_message(chat_id, "Create a new bucket"):
-        if event.type == "tool-approval-request":
-            pending_approval_id = event.approval_id
-
-    # Approve the pending tool
-    if pending_approval_id:
-        async for event in client.approve_tool(
-            chat_id=chat_id,
-            approval_id=pending_approval_id,
-        ):
-            if event.type == "text":
-                print(event.text, end="")
+```bash
+pip install kai-client streamlit
 ```
 
-### Error Handling
+Then use the `run_async` bridge pattern to call KaiClient from Streamlit:
 
 ```python
-from kai_client import (
-    KaiClient,
-    KaiError,
-    KaiAuthenticationError,
-    KaiRateLimitError,
-    KaiNotFoundError,
-)
-
-async with KaiClient(
-    storage_api_token="your-master-token",
-    storage_api_url="https://connection.keboola.com"
-) as client:
+import asyncio
+from kai_client import KaiClient
+
+def run_async(coro):
+    """Run an async coroutine from sync Streamlit code."""
+    loop = asyncio.new_event_loop()
     try:
-        async for event in client.send_message("chat-id", "Hello"):
-            print(event)
-    except KaiAuthenticationError:
-        print("Authentication failed")
-    except KaiRateLimitError:
-        print("Rate limited, try again later")
-    except KaiNotFoundError:
-        print("Chat not found")
-    except KaiError as e:
-        print(f"API error: {e.code} - {e.message}")
+        return loop.run_until_complete(coro)
+    finally:
+        loop.close()
 ```
 
-## Use Cases
+See the [plugin repository](https://github.com/keboola/kai-client/tree/main/plugins/kai-streamlit) for a complete working example with streaming, tool approval, and suggested action buttons.
 
 ### Kai via CLI with Claude Code
 
@@ -234,41 +156,6 @@ ln -s "$(pwd)/kai-client/plugins/kai-cli" ~/.claude/plugins/kai-cli
 
 Once installed, ask Claude to "use kai" or "help me with kai cli" to activate the skill. Claude can then run `kai chat`, `kai history`, `kai ping`, and other CLI commands on your behalf.
 
-### Integrating Kai into Data Apps
-
-The Kai Python Client can be embedded into Keboola [Data Apps](/data-apps/) to provide AI-powered chat interfaces for your end users.
-
-#### Streamlit Data Apps
-
-The [kai-streamlit plugin](https://github.com/keboola/kai-client/tree/main/plugins/kai-streamlit) provides patterns and working code for building [Streamlit Data Apps](/data-apps/streamlit/) with an integrated Kai chat interface. It handles the async bridge between Streamlit's synchronous model and the KaiClient's async API, streaming responses into Streamlit containers, tool approval flows with interactive Approve/Deny buttons, and session state management across Streamlit reruns.
-
-To get started, install the dependencies:
-
-```bash
-pip install kai-client streamlit
-```
-
-Then use the `run_async` bridge pattern to call KaiClient from Streamlit:
-
-```python
-import asyncio
-from kai_client import KaiClient
-
-def run_async(coro):
-    """Run an async coroutine from sync Streamlit code."""
-    loop = asyncio.new_event_loop()
-    try:
-        return loop.run_until_complete(coro)
-    finally:
-        loop.close()
-```
-
-See the [plugin repository](https://github.com/keboola/kai-client/tree/main/plugins/kai-streamlit) for a complete working example with streaming, tool approval, and suggested action buttons.
-
-#### Python/JS Data Apps
-
-Support for integrating Kai into [Python/JS Data Apps](/data-apps/python-js/) is coming soon. A dedicated plugin will be available to simplify embedding Kai chat into custom Python and JavaScript-based data applications.
-
 ## Resources
 
 - [GitHub Repository](https://github.com/keboola/kai-client)