table profiling功能开发

app/models.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from datetime import datetime
 from enum import Enum
 from typing import Any, Dict, List, Optional, Union
 
@@ -135,3 +136,89 @@ class DataImportAnalysisJobRequest(BaseModel):
 class DataImportAnalysisJobAck(BaseModel):
     import_record_id: str = Field(..., description="Echo of the import record identifier")
     status: str = Field("accepted", description="Processing status acknowledgement.")
+
+
+class TableProfilingJobRequest(BaseModel):
+    table_id: str = Field(..., description="Unique identifier for the table to profile.")
+    version_ts: str = Field(
+        ...,
+        pattern=r"^\d{14}$",
+        description="Version timestamp expressed as fourteen digit string (yyyyMMddHHmmss).",
+    )
+    callback_url: HttpUrl = Field(
+        ...,
+        description="Callback endpoint invoked after each pipeline action completes.",
+    )
+    table_schema: Optional[Any] = Field(
+        None,
+        description="Schema structure snapshot for the current table version.",
+    )
+    table_schema_version_id: Optional[str] = Field(
+        None,
+        description="Identifier for the schema snapshot provided in table_schema.",
+    )
+    table_link_info: Optional[Dict[str, Any]] = Field(
+        None,
+        description=(
+            "Information describing how to locate the source table for profiling. "
+            "For example: {'type': 'sql', 'connection_string': 'mysql+pymysql://user:pass@host/db', "
+            "'table': 'schema.table_name'}."
+        ),
+    )
+    table_access_info: Optional[Dict[str, Any]] = Field(
+        None,
+        description=(
+            "Credentials or supplemental parameters required to access the table described in table_link_info. "
+            "These values can be merged into the connection string using Python format placeholders."
+        ),
+    )
+    ge_batch_request: Optional[Dict[str, Any]] = Field(
+        None,
+        description="Optional Great Expectations batch request payload used for profiling.",
+    )
+    ge_expectation_suite_name: Optional[str] = Field(
+        None,
+        description="Expectation suite name used during profiling. Created automatically when absent.",
+    )
+    ge_data_context_root: Optional[str] = Field(
+        None,
+        description="Custom root directory for the Great Expectations data context. Defaults to project ./gx.",
+    )
+    ge_datasource_name: Optional[str] = Field(
+        None,
+        description="Datasource name registered inside the GE context when batch_request is not supplied.",
+    )
+    ge_data_asset_name: Optional[str] = Field(
+        None,
+        description="Data asset reference used when inferring batch request from datasource configuration.",
+    )
+    ge_profiler_type: str = Field(
+        "user_configurable",
+        description="Profiler implementation identifier. Currently supports 'user_configurable' or 'data_assistant'.",
+    )
+    llm_model: Optional[str] = Field(
+        None,
+        description="Default LLM model spec applied to prompt-based actions when overrides are omitted.",
+    )
+    result_desc_model: Optional[str] = Field(
+        None,
+        description="LLM model override used for GE result description (action 2).",
+    )
+    snippet_model: Optional[str] = Field(
+        None,
+        description="LLM model override used for snippet generation (action 3).",
+    )
+    snippet_alias_model: Optional[str] = Field(
+        None,
+        description="LLM model override used for snippet alias enrichment (action 4).",
+    )
+    extra_options: Optional[Dict[str, Any]] = Field(
+        None,
+        description="Miscellaneous execution flags applied across pipeline steps.",
+    )
+
+
+class TableProfilingJobAck(BaseModel):
+    table_id: str = Field(..., description="Echo of the table identifier.")
+    version_ts: str = Field(..., description="Echo of the profiling version timestamp (yyyyMMddHHmmss).")
+    status: str = Field("accepted", description="Processing acknowledgement status.")