> ## Documentation Index
> Fetch the complete documentation index at: https://clickhouse.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# كيفية إنشاء وكيل ذكاء اصطناعي باستخدام LangChain/LangGraph وخادم ClickHouse MCP.

> تعرّف على كيفية إنشاء وكيل ذكاء اصطناعي باستخدام LangChain/LangGraph يمكنه التفاعل مع SQL playground في ClickHouse باستخدام خادم ClickHouse MCP.

في هذا الدليل، ستتعلّم كيفية إنشاء وكيل ذكاء اصطناعي باستخدام [LangChain/LangGraph](https://github.com/langchain-ai/langgraph)
يمكنه التفاعل مع [SQL playground في ClickHouse](https://sql.clickhouse.com/) باستخدام [خادم ClickHouse MCP](https://github.com/ClickHouse/mcp-clickhouse).

<Info>
  **مثال على دفتر ملاحظات**

  يمكن العثور على هذا المثال على شكل دفتر ملاحظات في [مستودع examples](https://github.com/ClickHouse/examples/blob/main/ai/mcp/langchain/langchain.ipynb).
</Info>

<div id="prerequisites">
  ## المتطلبات الأساسية
</div>

* ستحتاج إلى أن يكون بايثون مثبتًا على نظامك.
* ستحتاج إلى أن يكون `pip` مثبتًا على نظامك.
* ستحتاج إلى مفتاح API من Anthropic، أو مفتاح API من موفّر LLM آخر

يمكنك تنفيذ الخطوات التالية إما من خلال بايثون REPL أو عبر برنامج نصي.

<Steps>
  <Step title="تثبيت المكتبات" id="install-libraries">
    ثبّت المكتبات المطلوبة بتنفيذ الأوامر التالية:

    ```python theme={null}
    pip install -q --upgrade pip
    pip install -q langchain-mcp-adapters langgraph "langchain[anthropic]"
    ```
  </Step>

  <Step title="إعداد بيانات الاعتماد" id="setup-credentials">
    بعد ذلك، ستحتاج إلى إدخال مفتاح واجهة برمجة تطبيقات Anthropic الخاص بك:

    ```python theme={null}
    import os, getpass
    os.environ["ANTHROPIC_API_KEY"] = getpass.getpass("Enter Anthropic API Key:")
    ```

    ```response title="Response" theme={null}
    Enter Anthropic API Key: ········
    ```

    <Info>
      **استخدام موفّر LLM آخر**

      إذا لم يكن لديك مفتاح واجهة برمجة تطبيقات من Anthropic، وكنت تريد استخدام موفّر LLM آخر،
      يمكنك العثور على إرشادات إعداد بيانات الاعتماد في [مستندات Langchain Providers](https://python.langchain.com/docs/integrations/providers/)
    </Info>
  </Step>

  <Step title="تهيئة خادم MCP" id="initialize-mcp-and-agent">
    الآن، قم بتكوين خادم ClickHouse MCP بحيث يشير إلى ClickHouse SQL playground:

    ```python theme={null}
    from mcp import ClientSession, StdioServerParameters
    from mcp.client.stdio import stdio_client

    server_params = StdioServerParameters(
        command="uv",
        args=[
            "run",
            "--with", "mcp-clickhouse",
            "--python", "3.13",
            "mcp-clickhouse"
        ],
        env={
            "CLICKHOUSE_HOST": "sql-clickhouse.clickhouse.com",
            "CLICKHOUSE_PORT": "8443",
            "CLICKHOUSE_USER": "demo",
            "CLICKHOUSE_PASSWORD": "",
            "CLICKHOUSE_SECURE": "true"
        }
    )
    ```
  </Step>

  <Step title="تهيئة معالج التدفق" id="configure-the-stream-handler">
    عند العمل مع Langchain وClickHouse MCP server، غالبًا ما تُعاد نتائج
    الاستعلام على هيئة بيانات متدفقة بدلًا من استجابة واحدة. ومع مجموعات البيانات الكبيرة أو
    الاستعلامات التحليلية المعقدة التي قد تستغرق وقتًا في المعالجة، من المهم تهيئة
    معالج للتدفق. ومن دون معالجة مناسبة، قد يصعب
    التعامل مع هذا المخرج المتدفق في تطبيقك.

    هيّئ المعالج للمخرج المتدفق بحيث يسهل استهلاكه:

    ```python theme={null}
    class UltraCleanStreamHandler:
        def __init__(self):
            self.buffer = ""
            self.in_text_generation = False
            self.last_was_tool = False
            
        def handle_chunk(self, chunk):
            event = chunk.get("event", "")
            
            if event == "on_chat_model_stream":
                data = chunk.get("data", {})
                chunk_data = data.get("chunk", {})
                
                # Only handle actual text content, skip tool invocation streams
                if hasattr(chunk_data, 'content'):
                    content = chunk_data.content
                    if isinstance(content, str) and not content.startswith('{"'):
                        # Add space after tool completion if needed
                        if self.last_was_tool:
                            print(" ", end="", flush=True)
                            self.last_was_tool = False
                        print(content, end="", flush=True)
                        self.in_text_generation = True
                    elif isinstance(content, list):
                        for item in content:
                            if (isinstance(item, dict) and 
                                item.get('type') == 'text' and 
                                'partial_json' not in str(item)):
                                text = item.get('text', '')
                                if text and not text.startswith('{"'):
                                    # Add space after tool completion if needed
                                    if self.last_was_tool:
                                        print(" ", end="", flush=True)
                                        self.last_was_tool = False
                                    print(text, end="", flush=True)
                                    self.in_text_generation = True
                                    
            elif event == "on_tool_start":
                if self.in_text_generation:
                    print(f"\n🔧 {chunk.get('name', 'tool')}", end="", flush=True)
                    self.in_text_generation = False
                    
            elif event == "on_tool_end":
                print(" ✅", end="", flush=True)
                self.last_was_tool = True
    ```
  </Step>

  <Step title="استدعِ الوكيل" id="call-the-agent">
    أخيرًا، استدعِ وكيلك واسأله عمّن ساهم بأكبر قدر من الشيفرة البرمجية في ClickHouse:

    ```python theme={null}
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await load_mcp_tools(session)
            agent = create_react_agent("anthropic:claude-sonnet-4-0", tools)
            
            handler = UltraCleanStreamHandler()        
            async for chunk in agent.astream_events(
                {"messages": [{"role": "user", "content": "Who's committed the most code to ClickHouse?"}]}, 
                version="v1"
            ):
                handler.handle_chunk(chunk)
                
            print("\n")
    ```

    يُفترض أن ترى استجابة مشابهة لما يلي:

    ```response title="Response" theme={null}
    I'll help you find who has committed the most code to ClickHouse by exploring the available databases and tables to locate git commit data.
    🔧 list_databases ✅ I can see there's a `git` database which likely contains git commit information. Let me explore the tables in that database:
    🔧 list_tables ✅ Perfect! I can see the `clickhouse_commits` table in the git database contains ClickHouse commit data with 80,644 commits. This table has information about each commit including the author, lines added/deleted, files modified, etc. Let me query this table to find who has committed the most code based on different metrics.
    🔧 run_select_query ✅ Let me also look at just the lines added to see who has contributed the most new code:
    🔧 run_select_query ✅ Based on the ClickHouse git commit data, **Alexey Milovidov** has committed the most code to ClickHouse by several measures:

    ## Key Statistics:

    1. **Most Total Lines Changed**: Alexey Milovidov with **1,696,929 total lines changed** (853,049 added + 843,880 deleted)
    2. **Most Lines Added**: Alexey Milovidov with **853,049 lines added**
    3. **Most Commits**: Alexey Milovidov with **15,375 commits**
    4. **Most Files Changed**: Alexey Milovidov with **73,529 files changed**

    ## Top Contributors by Lines Added:

    1. **Alexey Milovidov**: 853,049 lines added (15,375 commits)
    2. **s-kat**: 541,609 lines added (50 commits) 
    3. **Nikolai Kochetov**: 219,020 lines added (4,218 commits)
    4. **alesapin**: 193,566 lines added (4,783 commits)
    5. **Vitaly Baranov**: 168,807 lines added (1,152 commits)

    Alexey Milovidov is clearly the most prolific contributor to ClickHouse, which makes sense as he is one of the original creators and lead developers of the project. His contribution dwarfs others both in terms of total code volume and number of commits, with nearly 16,000 commits and over 850,000 lines of code added to the project.
    ```
  </Step>
</Steps>
