discovery-engine-api 0.1.9__py3-none-any.whl → 0.1.24__py3-none-any.whl

discovery/__init__.py

@@ -1,6 +1,6 @@
 """Discovery Engine Python SDK."""
 
-__version__ = "0.1.9"
+__version__ = "0.1.24"
 
 from discovery.client import Engine
 from discovery.types import (

discovery/client.py

@@ -103,8 +103,21 @@ class Engine:
         return self._client
 
     async def _get_client_with_org(self) -> httpx.AsyncClient:
-        """Get HTTP client (no longer needs org header for dashboard API)."""
-        return await self._get_client()
+        """
+        Get HTTP client with organization header set.
+
+        The organization ID is required for API requests to identify which
+        organization the user belongs to (multi-tenancy support).
+        """
+        client = await self._get_client()
+
+        # Ensure we have an organization ID
+        org_id = await self._ensure_organization_id()
+
+        # Set the organization header
+        client.headers["X-Organization-ID"] = org_id
+
+        return client
 
     async def close(self):
         """Close the HTTP client."""
@@ -124,18 +137,24 @@ class Engine:
         """
         Get the organizations you belong to.
 
-        Note: This is no longer needed for the simplified SDK workflow,
-        but kept for backwards compatibility.
-
         Returns:
             List of organizations with id, name, and slug
 
         Raises:
             ValueError: If the API request fails
         """
-        # Organizations are handled automatically by the dashboard API
-        # Return empty list for now - not needed for report creation
-        return []
+        client = await self._get_client()
+
+        try:
+            response = await client.get("/v1/me/organizations")
+            response.raise_for_status()
+            return response.json()
+        except httpx.HTTPStatusError as e:
+            raise ValueError(
+                f"Failed to fetch organizations: {e.response.status_code} {e.response.text}"
+            ) from e
+        except httpx.RequestError as e:
+            raise ValueError(f"Failed to connect to API: {str(e)}") from e
 
     async def upload_file(
         self, file: Union[str, Path, "pd.DataFrame"], filename: Optional[str] = None
@@ -346,7 +365,7 @@ class Engine:
         Returns:
             EngineResult with complete analysis data
         """
-        client = await self._get_client()
+        client = await self._get_client_with_org()
 
         # Call dashboard API for results
         response = await client.get(f"/api/runs/{run_id}/results")
@@ -443,6 +462,7 @@ class Engine:
         title: Optional[str] = None,
         description: Optional[str] = None,
         column_descriptions: Optional[Dict[str, str]] = None,
+        excluded_columns: Optional[List[str]] = None,
         task: Optional[str] = None,
         visibility: str = "public",
         timeseries_groups: Optional[List[Dict[str, Any]]] = None,
@@ -467,6 +487,7 @@ class Engine:
             title: Optional dataset title
             description: Optional dataset description
             column_descriptions: Optional dict mapping column names to descriptions
+            excluded_columns: Optional list of column names to exclude from analysis
             task: Task type (regression, binary, multiclass) - auto-detected if None
             visibility: Dataset visibility ("public" or "private", default: "public")
             timeseries_groups: Optional list of timeseries column groups
@@ -480,7 +501,7 @@ class Engine:
         Returns:
             EngineResult with run_id and (if wait=True) complete results
         """
-        client = await self._get_client()
+        client = await self._get_client_with_org()
 
         # Prepare file for upload
         if pd is not None and isinstance(file, pd.DataFrame):
@@ -526,6 +547,8 @@ class Engine:
             data["source_url"] = source_url
         if column_descriptions:
             data["column_descriptions"] = json.dumps(column_descriptions)
+        if excluded_columns:
+            data["excluded_columns"] = json.dumps(excluded_columns)
         if timeseries_groups:
             data["timeseries_groups"] = json.dumps(timeseries_groups)
 
@@ -588,6 +611,7 @@ class Engine:
         title: Optional[str] = None,
         description: Optional[str] = None,
         column_descriptions: Optional[Dict[str, str]] = None,
+        excluded_columns: Optional[List[str]] = None,
         task: Optional[str] = None,
         visibility: str = "public",
         timeseries_groups: Optional[List[Dict[str, Any]]] = None,
@@ -611,6 +635,7 @@ class Engine:
             title: Optional dataset title
             description: Optional dataset description
             column_descriptions: Optional dict mapping column names to descriptions
+            excluded_columns: Optional list of column names to exclude from analysis
             task: Task type (regression, binary_classification, multiclass_classification) - auto-detected if None
             visibility: Dataset visibility ("public" or "private", default: "public")
             timeseries_groups: Optional list of timeseries column groups
@@ -632,6 +657,7 @@ class Engine:
             title=title,
             description=description,
             column_descriptions=column_descriptions,
+            excluded_columns=excluded_columns,
             task=task,
             visibility=visibility,
             timeseries_groups=timeseries_groups,

{discovery_engine_api-0.1.9.dist-info → discovery_engine_api-0.1.24.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: discovery-engine-api
-Version: 0.1.9
+Version: 0.1.24
 Summary: Python SDK for the Discovery Engine API
 Project-URL: Homepage, https://github.com/leap-laboratories/discovery
 Project-URL: Documentation, https://github.com/leap-laboratories/discovery
@@ -75,6 +75,7 @@ result = engine.run(
     target_column="diagnosis",
     mode="fast",
     description="Rare diseases dataset",
+    excluded_columns=["patient_id"],  # Exclude ID column from analysis
     wait=True  # Wait for completion and return full results
 )
 
@@ -103,6 +104,7 @@ result = engine.run(
         "age": "Patient age in years",
         "heart rate": None
     },
+    excluded_columns=["id", "timestamp"],  # Exclude ID and timestamp columns from analysis
     wait=True
 )
 ```
@@ -172,6 +174,7 @@ The `run()` and `run_async()` methods accept the following parameters:
 | `title` | `str` | `None` | Optional dataset title |
 | `description` | `str` | `None` | Optional dataset description |
 | `column_descriptions` | `Dict[str, str]` | `None` | Optional column name -> description mapping |
+| `excluded_columns` | `List[str]` | `None` | Optional list of column names to exclude from analysis (e.g., IDs, timestamps) |
 | `visibility` | `"public"` / `"private"` | `"public"` | Dataset visibility (private requires credits) |
 | `auto_report_use_llm_evals` | `bool` | `True` | Use LLM for pattern descriptions |
 | `author` | `str` | `None` | Optional dataset author attribution |
@@ -185,7 +188,7 @@ The `run()` and `run_async()` methods accept the following parameters:
 - **Public datasets**: Free (0 credits required)
 - **Private datasets**: 
   - Fast mode: 1 credit per MB
-  - Deep mode: 3 credits per MB
+  - Deep mode: (number of columns × 0.1) credits per MB (minimum 3× fast mode cost)
 
 If you don't have enough credits for a private run, the SDK will raise an `httpx.HTTPStatusError` with an error message like:
 ```

discovery_engine_api-0.1.24.dist-info/RECORD

@@ -0,0 +1,6 @@
+discovery/__init__.py,sha256=9YuAELQB1dqkdnYZXdgB-qt3TI7pMaG-J1Y4iJ4EUZA,586
+discovery/client.py,sha256=Io1vGqiEGrPPwOFxBDMaFbKlARj_Xg0izyWoRmoQy-c,30802
+discovery/types.py,sha256=4Z3gKdxWnOpymEjBGCzAeUGjwRT2A0aCpmuwctbE4w0,6008
+discovery_engine_api-0.1.24.dist-info/METADATA,sha256=6Tmt9cCbe_s-P8Id_zS5o7mac706Mb5d9h6g1EzuBYA,12867
+discovery_engine_api-0.1.24.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+discovery_engine_api-0.1.24.dist-info/RECORD,,

discovery_engine_api-0.1.9.dist-info/RECORD

@@ -1,6 +0,0 @@
-discovery/__init__.py,sha256=MKz5NmDXau4PIU5e_sQmEboCag5L3bAG-1b6HANwlpQ,585
-discovery/client.py,sha256=i2WX59IgZ-olmn96oAQOgeObeqP0C1EjxewGLlQLcO0,29784
-discovery/types.py,sha256=4Z3gKdxWnOpymEjBGCzAeUGjwRT2A0aCpmuwctbE4w0,6008
-discovery_engine_api-0.1.9.dist-info/METADATA,sha256=21I33FLHiGKysw-iGguSmreZLMN1P5de5ziFvU24f8Q,12521
-discovery_engine_api-0.1.9.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-discovery_engine_api-0.1.9.dist-info/RECORD,,