scmcp-shared 0.6.0__tar.gz → 0.6.2__tar.gz

{scmcp_shared-0.6.0 → scmcp_shared-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scmcp_shared
-Version: 0.6.0
+Version: 0.6.2
 Summary: A shared function libray for scmcphub
 Project-URL: Homepage, http://scmcphub.org/
 Project-URL: Repository, https://github.com/scmcphub/scmcp-shared

scmcp_shared-0.6.2/src/scmcp_shared/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.6.2"

{scmcp_shared-0.6.0 → scmcp_shared-0.6.2}/src/scmcp_shared/agent.py

@@ -4,7 +4,7 @@ import os
 
 from agno.agent import Agent
 from agno.models.openai import OpenAILike
-from scmcp_shared.kb import load_kb
+from .kb import load_kb
 
 model = OpenAILike(
     id=os.getenv("MODEL"),
@@ -13,13 +13,16 @@ model = OpenAILike(
 )
 
 
-def rag_agent(task, software=None):
+def rag_agent(task, software="scmcp"):
     knowledge_base = load_kb(software=software)
     agent = Agent(
         model=model,
         knowledge=knowledge_base,
         show_tool_calls=True,
         search_knowledge=True,
+        instructions="""
+        MUST query the knowledge base, and return the code example that can be used to solve the task.
+        """,
     )
     query = f"""
     <task>

scmcp_shared-0.6.2/src/scmcp_shared/kb.py

@@ -0,0 +1,109 @@
+from agno.document.chunking.agentic import AgenticChunking
+from agno.embedder.openai import OpenAIEmbedder
+from agno.models.deepseek import DeepSeek
+from agno.vectordb.lancedb import LanceDb
+from agno.knowledge.agent import AgentKnowledge
+import os
+import requests
+import zipfile
+from pathlib import Path
+import logging
+
+logger = logging.getLogger(__name__)
+
+embedder_id = os.getenv("EMBEDDER_MODEL")
+embedder_api_key = os.getenv("EMBEDDER_API_KEY")
+embedder_base_url = os.getenv("EMBEDDER_BASE_URL")
+model_id = os.getenv("MODEL")
+model_api_key = os.getenv("API_KEY")
+model_base_url = os.getenv("BASE_URL")
+
+
+def download_vector_db(source="huggingface"):
+    """
+    下载向量数据库文件
+
+    Args:
+        source: 下载源 ("huggingface" 或 "github")
+    """
+
+    local_dir = Path(__file__).parent
+    local_dir.mkdir(exist_ok=True)
+
+    # 检查是否已存在
+    if (local_dir / "scmcp.lance").exists():
+        logger.info("Vector database already exists locally")
+        return str(local_dir)
+
+    logger.info(f"Downloading vector database from {source}...")
+
+    # 下载文件
+    if source == "huggingface":
+        url = "https://huggingface.co/datasets/huangshing/scmcp_vector_db/resolve/main/vector_db.zip"
+    else:
+        raise ValueError(f"Unsupported source: {source}")
+
+    logger.info(f"Downloading from: {url}")
+    response = requests.get(url, stream=True)
+    response.raise_for_status()
+
+    # 下载到目标目录
+    zip_path = local_dir / "vector_db.zip"
+    with open(zip_path, "wb") as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            f.write(chunk)
+
+    # 解压文件
+    logger.info("Extracting downloaded archive...")
+    with zipfile.ZipFile(zip_path, "r") as zip_ref:
+        zip_ref.extractall(local_dir)
+
+    # 删除zip文件
+    zip_path.unlink()
+
+    logger.info(f"Vector database downloaded and extracted to: {local_dir}")
+    return str(local_dir)
+
+
+def load_kb(software=None, auto_download=True, download_source="huggingface"):
+    """
+    加载知识库
+
+    Args:
+        software: 软件名称
+        auto_download: 是否自动下载向量数据库
+        download_source: 下载源 ("huggingface" 或 "github")
+    """
+    # 获取向量数据库路径
+    vector_db_path = Path(__file__).parent / "vector_db"
+
+    # 如果不存在且允许自动下载，则下载
+    if not (vector_db_path / "scmcp.lance").exists():
+        if auto_download:
+            logger.info("Vector database not found, downloading...")
+            download_vector_db(download_source)
+        else:
+            raise FileNotFoundError(
+                "Vector database not found. Set auto_download=True to download automatically."
+            )
+
+    vector_db = LanceDb(
+        table_name=software,
+        uri=vector_db_path,
+        embedder=OpenAIEmbedder(
+            id=embedder_id,
+            base_url=embedder_base_url,
+            api_key=embedder_api_key,
+        ),
+    )
+    model = DeepSeek(
+        id=model_id,
+        base_url=model_base_url,
+        api_key=model_api_key,
+    )
+    knowledge_base = AgentKnowledge(
+        chunking_strategy=AgenticChunking(model=model),
+        vector_db=vector_db,
+    )
+
+    return knowledge_base

{scmcp_shared-0.6.0 → scmcp_shared-0.6.2}/src/scmcp_shared/server/rag.py

@@ -9,5 +9,5 @@ rag_mcp = FastMCP("RAG-Server")
 def retrieve_knowledge(
     task: str = Field(description="The tasks or questions that needs to be solved"),
 ):
-    """search function and parameters that can be used to solve the user's tasks or questions"""
+    """search guide or code example that can be used to solve the user's tasks or questions"""
     return rag_agent(task, software="scmcp")

scmcp_shared-0.6.0/src/scmcp_shared/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.6.0"

scmcp_shared-0.6.0/src/scmcp_shared/kb.py

@@ -1,139 +0,0 @@
-from agno.document.chunking.agentic import AgenticChunking
-from agno.embedder.openai import OpenAIEmbedder
-from agno.models.deepseek import DeepSeek
-from agno.vectordb.lancedb import LanceDb
-from agno.knowledge.agent import AgentKnowledge
-import importlib.resources
-import os
-import requests
-import zipfile
-import tempfile
-import shutil
-from pathlib import Path
-import logging
-
-logger = logging.getLogger(__name__)
-
-embedder_id = os.getenv("EMBEDDER_MODEL")
-embedder_api_key = os.getenv("EMBEDDER_API_KEY")
-embedder_base_url = os.getenv("EMBEDDER_BASE_URL")
-model_id = os.getenv("MODEL")
-model_api_key = os.getenv("API_KEY")
-model_base_url = os.getenv("BASE_URL")
-
-# 配置信息
-config = {
-    "local_dir": "vector_db",
-    "huggingface_url": "https://huggingface.co/datasets/huangshing/scmcp_vector_db/resolve/main/vector_db.zip",
-}
-
-
-def download_vector_db(source="huggingface"):
-    """
-    下载向量数据库文件
-
-    Args:
-        source: 下载源 ("huggingface" 或 "github")
-    """
-
-    # 获取本地存储路径
-    package_path = importlib.resources.path("scmcp_shared", "")
-    local_dir = Path(package_path) / config["local_dir"]
-    local_dir.mkdir(exist_ok=True)
-
-    # 检查是否已存在
-    if (local_dir / "scmcp.lance").exists():
-        logger.info("Vector database already exists locally")
-        return str(local_dir)
-
-    logger.info(f"Downloading vector database from {source}...")
-
-    # 创建临时目录用于下载和解压
-    with tempfile.TemporaryDirectory() as temp_dir:
-        temp_path = Path(temp_dir)
-        zip_path = temp_path / "vector_db.zip"
-
-        try:
-            # 下载文件
-            if source == "huggingface":
-                url = config["huggingface_url"]
-            else:
-                raise ValueError(f"Unsupported source: {source}")
-
-            logger.info(f"Downloading from: {url}")
-            response = requests.get(url, stream=True)
-            response.raise_for_status()
-
-            with open(zip_path, "wb") as f:
-                for chunk in response.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            # 解压文件
-            logger.info("Extracting downloaded archive...")
-            _extract_archive(zip_path, local_dir)
-
-            logger.info(f"Vector database downloaded and extracted to: {local_dir}")
-            return str(local_dir)
-
-        except requests.RequestException as e:
-            raise RuntimeError(f"Failed to download vector database: {e}")
-        except Exception as e:
-            raise RuntimeError(f"Failed to process vector database: {e}")
-
-
-def _extract_archive(archive_path, extract_dir):
-    """解压归档文件"""
-    with zipfile.ZipFile(archive_path, "r") as zip_ref:
-        zip_ref.extractall(extract_dir)
-
-    # 如果解压后只有一个子目录，移动内容到目标目录
-    extracted_items = list(Path(extract_dir).iterdir())
-    if len(extracted_items) == 1 and extracted_items[0].is_dir():
-        subdir = extracted_items[0]
-        for item in subdir.iterdir():
-            shutil.move(str(item), str(extract_dir / item.name))
-        subdir.rmdir()
-
-
-def load_kb(software=None, auto_download=True, download_source="huggingface"):
-    """
-    加载知识库
-
-    Args:
-        software: 软件名称
-        auto_download: 是否自动下载向量数据库
-        download_source: 下载源 ("huggingface" 或 "github")
-    """
-    # 获取向量数据库路径
-    try:
-        vector_db_path = importlib.resources.path("scmcp_shared", "vector_db")
-    except FileNotFoundError:
-        if auto_download:
-            logger.info("Vector database not found in package, attempting download...")
-            vector_db_path = download_vector_db(download_source)
-        else:
-            raise FileNotFoundError(
-                "Vector database not found. Set auto_download=True to download automatically, "
-                "or manually place the vector database in the scmcp_shared package."
-            )
-
-    vector_db = LanceDb(
-        table_name=software,
-        uri=vector_db_path,
-        embedder=OpenAIEmbedder(
-            id=embedder_id,
-            base_url=embedder_base_url,
-            api_key=embedder_api_key,
-        ),
-    )
-    model = DeepSeek(
-        id=model_id,
-        base_url=model_base_url,
-        api_key=model_api_key,
-    )
-    knowledge_base = AgentKnowledge(
-        chunking_strategy=AgenticChunking(model=model),
-        vector_db=vector_db,
-    )
-
-    return knowledge_base