smart_search
Search genomic data using natural language queries to find genes, proteins, and pathways based on semantic understanding of biological concepts.
Instructions
智能语义搜索 - 理解自然语言描述并执行相应查询
语义理解示例：
"breast cancer genes on chromosome 17" → 查找17号染色体上的乳腺癌基因
"TP53 protein interactions" → 查找TP53蛋白相互作用
"tumor suppressor genes" → 查找肿瘤抑制基因
"genes related to DNA repair" → 查找DNA修复相关基因
Args: description: 自然语言描述 context: 搜索上下文（genomics/proteomics/pathway） filters: 过滤条件 max_results: 最大结果数
Returns: 智能搜索结果
Examples: smart_search("breast cancer genes on chromosome 17") smart_search("TP53 protein interactions", context="proteomics") smart_search("DNA repair genes", filters={"species": "human"})
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | ||
| context | No | genomics | |
| filters | No | ||
| max_results | No |
Input Schema (JSON Schema)
{
"properties": {
"context": {
"default": "genomics",
"type": "string"
},
"description": {
"type": "string"
},
"filters": {
"additionalProperties": true,
"default": null,
"type": "object"
},
"max_results": {
"default": 20,
"type": "integer"
}
},
"required": [
"description"
],
"type": "object"
}
Implementation Reference
- src/genome_mcp/core/tools.py:427-498 (handler)The main execution logic for the 'smart_search' MCP tool. It validates inputs, applies filters, parses the natural language query, executes it using the query executor, augments the result with search metadata, and handles errors appropriately. Registered via @mcp.tool() decorator.@mcp.tool() async def smart_search( description: str, context: str = "genomics", filters: dict[str, Any] = None, max_results: int = 20, ) -> SearchResult: """ 智能语义搜索 - 理解自然语言描述并执行相应查询 语义理解示例： - "breast cancer genes on chromosome 17" → 查找17号染色体上的乳腺癌基因 - "TP53 protein interactions" → 查找TP53蛋白相互作用 - "tumor suppressor genes" → 查找肿瘤抑制基因 - "genes related to DNA repair" → 查找DNA修复相关基因 Args: description: 自然语言描述 context: 搜索上下文（genomics/proteomics/pathway） filters: 过滤条件 max_results: 最大结果数 Returns: 智能搜索结果 Examples: smart_search("breast cancer genes on chromosome 17") smart_search("TP53 protein interactions", context="proteomics") smart_search("DNA repair genes", filters={"species": "human"}) """ try: # 验证搜索参数 validated_description, validated_context, validated_max_results = ( validate_search_params( description=description, context=context, max_results=max_results ) ) # 智能解析查询意图 query = _apply_filters(validated_description, filters) # 根据上下文调整查询 if validated_context == "proteomics": query_type = "protein" elif validated_context == "pathway": query_type = "search" else: query_type = "auto" # 解析查询意图 parsed = QueryParser.parse(query, query_type) # 执行查询（直接使用查询执行器，避免MCP工具间调用） result = await _query_executor.execute( parsed, max_results=validated_max_results ) # 添加智能解析信息 result["smart_search_info"] = { "description": validated_description, "context": validated_context, "parsed_query": query, "filters_applied": filters is not None, } return result except ValidationError as e: return format_simple_error(e, query=description, operation="smart_search") except Exception as e: return format_simple_error(e, query=description, operation="smart_search")
- src/genome_mcp/core/types.py:42-49 (schema)TypedDict definition for SearchResult, which is the return type of the smart_search tool, defining the structure of the output.class SearchResult(TypedDict): """搜索结果类型""" query: str results: list[dict[str, Any]] total_count: int search_metadata: dict[str, Any]
- Input validation function specifically for smart_search parameters: description, context, max_results. Ensures valid values and raises ValidationError if invalid.def validate_search_params( description: str, context: str = "genomics", max_results: int = 20 ) -> tuple[str, str, int]: """ 验证搜索参数 Args: description: 搜索描述 context: 搜索上下文 max_results: 最大结果数 Returns: 验证后的参数元组 Raises: ValidationError: 搜索描述验证失败 """ if not description or not description.strip(): raise ValidationError("Search description cannot be empty") description = description.strip() # 验证context valid_contexts = {"genomics", "proteomics", "pathway"} if context not in valid_contexts: context = "genomics" # 验证max_results if not isinstance(max_results, int) or max_results < 1: max_results = 20 elif max_results > 50: max_results = 50 return description, context, max_results
- src/genome_mcp/main.py:40-41 (registration)Explicit registration of all MCP tools and resources by calling create_mcp_tools(mcp), which defines and registers the smart_search tool among others.create_mcp_resources(mcp) create_mcp_tools(mcp)
- src/genome_mcp/core/tools.py:88-112 (helper)Internal helper function used by smart_search to apply user-provided filters (e.g., species, gene_type) to the base query string, modifying it for more precise searching.def _apply_filters(query: str, filters: dict[str, Any] | None = None) -> str: """应用搜索过滤器""" if not filters: return query filter_parts = [] # 物种过滤 if "species" in filters: species = filters["species"].lower() if species != "human": filter_parts.append(f"{species}[organism]") # 基因类型过滤 if "gene_type" in filters: gene_type = filters["gene_type"] if gene_type == "protein_coding": filter_parts.append("protein_coding[Properties]") # 合并过滤器 if filter_parts: return f"{query} AND {' AND '.join(filter_parts)}" return query