shaped 2.0.1__py3-none-any.whl → 2.0.4__py3-none-any.whl

shaped/autogen/models/whitespace_tokenizer.py

@@ -0,0 +1,97 @@
+# coding: utf-8
+
+"""
+    Shaped API
+
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
+
+    The version of the OpenAPI document: 2.0.4
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, StrictStr, field_validator
+from typing import Any, ClassVar, Dict, List, Optional
+from typing import Optional, Set
+from typing_extensions import Self
+
+class WhitespaceTokenizer(BaseModel):
+    """
+    A simple tokenizer that splits on whitespace.
+    """ # noqa: E501
+    type: Optional[StrictStr] = Field(default='whitespace', description="Tokenizer type discriminator.")
+    __properties: ClassVar[List[str]] = ["type"]
+
+    @field_validator('type')
+    def type_validate_enum(cls, value):
+        """Validates the enum"""
+        if value is None:
+            return value
+
+        if value not in set(['whitespace']):
+            raise ValueError("must be one of enum values ('whitespace')")
+        return value
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of WhitespaceTokenizer from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of WhitespaceTokenizer from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "type": obj.get("type") if obj.get("type") is not None else 'whitespace'
+        })
+        return _obj
+
+

shaped/autogen/models/window_size.py

@@ -0,0 +1,136 @@
+# coding: utf-8
+
+"""
+    Shaped API
+
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
+
+    The version of the OpenAPI document: 2.0.4
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import json
+import pprint
+import re  # noqa: F401
+from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr, ValidationError, field_validator
+from typing import Optional
+from shaped.autogen.models.tunable_int import TunableInt
+from typing import Union, Any, List, Set, TYPE_CHECKING, Optional, Dict
+from typing_extensions import Literal, Self
+from pydantic import Field
+
+WINDOWSIZE_ANY_OF_SCHEMAS = ["TunableInt", "int"]
+
+class WindowSize(BaseModel):
+    """
+    Context window size for predicting items in sequences.
+    """
+
+    # data type: int
+    anyof_schema_1_validator: Optional[StrictInt] = None
+    # data type: TunableInt
+    anyof_schema_2_validator: Optional[TunableInt] = None
+    if TYPE_CHECKING:
+        actual_instance: Optional[Union[TunableInt, int]] = None
+    else:
+        actual_instance: Any = None
+    any_of_schemas: Set[str] = { "TunableInt", "int" }
+
+    model_config = {
+        "validate_assignment": True,
+        "protected_namespaces": (),
+    }
+
+    def __init__(self, *args, **kwargs) -> None:
+        if args:
+            if len(args) > 1:
+                raise ValueError("If a position argument is used, only 1 is allowed to set `actual_instance`")
+            if kwargs:
+                raise ValueError("If a position argument is used, keyword arguments cannot be used.")
+            super().__init__(actual_instance=args[0])
+        else:
+            super().__init__(**kwargs)
+
+    @field_validator('actual_instance')
+    def actual_instance_must_validate_anyof(cls, v):
+        instance = WindowSize.model_construct()
+        error_messages = []
+        # validate data type: int
+        try:
+            instance.anyof_schema_1_validator = v
+            return v
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # validate data type: TunableInt
+        if not isinstance(v, TunableInt):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `TunableInt`")
+        else:
+            return v
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when setting the actual_instance in WindowSize with anyOf schemas: TunableInt, int. Details: " + ", ".join(error_messages))
+        else:
+            return v
+
+    @classmethod
+    def from_dict(cls, obj: Dict[str, Any]) -> Self:
+        return cls.from_json(json.dumps(obj))
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Self:
+        """Returns the object represented by the json string"""
+        instance = cls.model_construct()
+        error_messages = []
+        # deserialize data into int
+        try:
+            # validation
+            instance.anyof_schema_1_validator = json.loads(json_str)
+            # assign value to actual_instance
+            instance.actual_instance = instance.anyof_schema_1_validator
+            return instance
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # anyof_schema_2_validator: Optional[TunableInt] = None
+        try:
+            instance.actual_instance = TunableInt.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+             error_messages.append(str(e))
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when deserializing the JSON string into WindowSize with anyOf schemas: TunableInt, int. Details: " + ", ".join(error_messages))
+        else:
+            return instance
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the actual instance"""
+        if self.actual_instance is None:
+            return "null"
+
+        if hasattr(self.actual_instance, "to_json") and callable(self.actual_instance.to_json):
+            return self.actual_instance.to_json()
+        else:
+            return json.dumps(self.actual_instance)
+
+    def to_dict(self) -> Optional[Union[Dict[str, Any], TunableInt, int]]:
+        """Returns the dict representation of the actual instance"""
+        if self.actual_instance is None:
+            return None
+
+        if hasattr(self.actual_instance, "to_dict") and callable(self.actual_instance.to_dict):
+            return self.actual_instance.to_dict()
+        else:
+            return self.actual_instance
+
+    def to_str(self) -> str:
+        """Returns the string representation of the actual instance"""
+        return pprint.pformat(self.model_dump())
+
+

shaped/autogen/rest.py

@@ -3,9 +3,9 @@
 """
     Shaped API
 
-    Welcome to Shaped's API reference docs. These provide a detailed view of the endpoints and CLI commands that Shaped provides and brief explanations of how they should be used.   Shaped's API is composed of 3 components:   1. **Dataset** - used to provision and manage 'Shaped Datasets', which are persisted     data views of external data. Shaped Datasets can be created from any of our     'Shaped connectors' (e.g. S3, Segment, Snowflake, etc.) and support both batch     ingestion (up to a 15min delay) and stream ingestion (up to a 30 second     delay) depending on the specific connector used. Shaped datasets can also be     created from local files, which is particularly useful for getting started     with a snapshot of data.    2. **Model Management** - used to provision and manage 'Shaped Models', which     represent a system of data pipelines, training and serving infrastructure for     your ranking use-case.    3. **Model Inference** - a high performance API that's used to make     user-understanding requests or ranking inferences to your 'Shaped Models'. For     example, the 'rank' endpoint can be used to determine for a given user id     query, what is the content that is most engaging to that user.    The recommended workflow to interact with the Shaped API is as follows:   1. First create 'Shaped Datasets' to sync over data that your Shaped     understanding models will need. The models at the minimum need interaction     data to understand behavior of your users, so start with that and add your item     and user catalog data later.   2. Then create 'Shaped Models' that use your created 'Shaped Datasets' as     input. Your Shaped Model will will start streaming, processing and training     from your connected data immediately. After a few hours your model will have     tuned all parameters based on your data and will deploy an active model.   3. You can now use the 'Model Inference' endpoints to make real-time     inferences to your model based on your use-case. 
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
 
-    The version of the OpenAPI document: 1.0.1
+    The version of the OpenAPI document: 2.0.4
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.
@@ -48,12 +48,17 @@ class RESTResponse(io.IOBase):
             self.data = self.response.data
         return self.data
 
+    @property
+    def headers(self):
+        """Returns a dictionary of response headers."""
+        return self.response.headers
+
     def getheaders(self):
-        """Returns a dictionary of the response headers."""
+        """Returns a dictionary of the response headers; use ``headers`` instead."""
         return self.response.headers
 
     def getheader(self, name, default=None):
-        """Returns a given response header."""
+        """Returns a given response header; use ``headers.get()`` instead."""
         return self.response.headers.get(name, default)
 
 
@@ -76,6 +81,7 @@ class RESTClientObject:
             "ca_certs": configuration.ssl_ca_cert,
             "cert_file": configuration.cert_file,
             "key_file": configuration.key_file,
+            "ca_cert_data": configuration.ca_cert_data,
         }
         if configuration.assert_hostname is not None:
             pool_args['assert_hostname'] = (

shaped/cli/shaped_cli.py

@@ -12,7 +12,7 @@ from tqdm import tqdm
 
 APP_NAME = "SHAPED_CLI"
 
-app = typer.Typer()
+app = typer.Typer(name="shaped")
 
 
 class Config(BaseModel):
@@ -25,14 +25,14 @@ def _write_config(config: Config):
     app_dir_path.mkdir(parents=True, exist_ok=True)
     config_path = app_dir_path / "config.json"
     with open(config_path, "w") as f:
-        f.write(config.json())
+        f.write(config.model_dump_json())
 
 
 def _read_config() -> Config:
     app_dir_path = Path(typer.get_app_dir(APP_NAME))
     config_path = app_dir_path / "config.json"
     with open(config_path, "r") as f:
-        config = Config.parse_raw(f.read())
+        config = Config.model_validate_json(f.read())
 
     return config
 
@@ -61,26 +61,92 @@ def _parse_response_as_yaml(content: str) -> str:
     return yaml.dump(json.loads(content), sort_keys=False)
 
 
+def _normalize_query_to_request(query_input: str) -> str:
+    """
+    Normalize query input to a QueryRequest JSON string.
+
+    The input can be:
+    - A SQL string (e.g., "SELECT * FROM table")
+    - A QueryConfig JSON object (e.g., {"type": "rank", ...})
+    - A full QueryRequest JSON object (e.g., {"query": "...", "return_metadata": true})
+    - Legacy format (e.g., {"sql": "SELECT * FROM table"})
+
+    Returns a JSON string representing a QueryRequest.
+
+    Raises:
+        ValueError: If the input is invalid or cannot be normalized.
+    """
+    if not query_input or not query_input.strip():
+        raise ValueError(
+            "Query input cannot be empty. Provide a SQL query string or "
+            "JSON query configuration."
+        )
+
+    # Try to parse as JSON first.
+    try:
+        parsed = json.loads(query_input)
+
+        # If it's already a QueryRequest (has 'query' field), use as-is.
+        if isinstance(parsed, dict) and "query" in parsed:
+            return json.dumps(parsed)
+
+        # Handle legacy {"sql": "..."} format.
+        if isinstance(parsed, dict) and "sql" in parsed:
+            sql_string = parsed["sql"]
+            if not isinstance(sql_string, str) or not sql_string.strip():
+                raise ValueError(
+                    "Invalid 'sql' field in query. Expected a non-empty SQL string."
+                )
+            # Merge any other fields (like return_metadata) if present.
+            request = {"query": sql_string, "return_metadata": True}
+            if "return_metadata" in parsed:
+                request["return_metadata"] = parsed["return_metadata"]
+            if "parameters" in parsed:
+                request["parameters"] = parsed["parameters"]
+            return json.dumps(request)
+
+        # If it's a dict but not a QueryRequest, wrap it as the query field.
+        if isinstance(parsed, dict):
+            return json.dumps({"query": parsed, "return_metadata": True})
+
+        # If it's a string in JSON (unlikely but possible), treat as SQL.
+        if isinstance(parsed, str):
+            return json.dumps({"query": parsed, "return_metadata": True})
+
+        # Other types, wrap as query.
+        return json.dumps({"query": parsed, "return_metadata": True})
+    except json.JSONDecodeError:
+        # Not valid JSON, treat as SQL string.
+        # This is expected for plain SQL queries, so we don't raise an error.
+        return json.dumps({"query": query_input, "return_metadata": True})
+    except ValueError as e:
+        # Re-raise ValueError with context.
+        raise ValueError(f"Invalid query input: {e}") from e
+
+
 @app.command()
 def init(
-    api_key: str = typer.Option(..., help="Your Shaped API key."),
-    env: str = typer.Option("prod", help="Environment to use (e.g., prod, dev, staging)."),
+    api_key: str = typer.Option(..., "--api-key", help="Your Shaped API key."),
+    env: str = typer.Option(
+        "prod", "--env", help="Environment to use (e.g., prod, dev, staging)."
+    ),
 ):
     """
     Initialize the Shaped CLI with your API key and environment.
-    
+
     This command saves your configuration locally so you don't need to
     provide your API key for every command.
     """
     config = Config(api_key=api_key, env=env)
     _write_config(config)
-    typer.echo(f"Initializing with config: {config.dict()}")
+    typer.echo(f"Initializing with config: {config.model_dump()}")
 
 
 ##############
 # ENGINE API #
 ##############
 
+
 @app.command()
 def create_engine(
     file: typer.FileText = typer.Option(
@@ -89,7 +155,7 @@ def create_engine(
 ):
     """
     Create a new engine.
-    
+
     The engine configuration can be provided via:
     - --file: Path to a JSON/YAML file
     - stdin: Pipe JSON/YAML content
@@ -125,7 +191,7 @@ def update_engine(
 ):
     """
     Update an existing engine.
-    
+
     The engine configuration can be provided via:
     - --file: Path to a JSON/YAML file
     - stdin: Pipe JSON/YAML content
@@ -218,7 +284,7 @@ def create_table_from_uri(
 ):
     """
     Create a table from a data file and automatically insert the data.
-    
+
     The table schema is inferred from the first chunk of data.
     """
     chunks = _read_chunks(path, type, chunk_size=1)
@@ -249,7 +315,7 @@ def create_table(
 ):
     """
     Create a new table.
-    
+
     The table configuration can be provided via:
     - --file: Path to a JSON/YAML file
     - stdin: Pipe JSON/YAML content
@@ -321,7 +387,7 @@ def update_table(
 ):
     """
     Update an existing table.
-    
+
     The table configuration can be provided via:
     - --file: Path to a JSON/YAML file
     - stdin: Pipe JSON/YAML content
@@ -359,7 +425,7 @@ def table_insert(
 ):
     """
     Insert data into a table from a file.
-    
+
     Data is read in chunks and uploaded progressively with a progress bar.
     """
     config = _read_config()
@@ -383,7 +449,7 @@ def table_insert(
     # Chunk read and upload.
     for chunk in _read_chunks(file, type, chunk_size=1000):
         _write_chunk(chunk)
-    
+
     bar.close()
 
 
@@ -440,7 +506,7 @@ def create_view(
 ):
     """
     Create a new view.
-    
+
     The view configuration can be provided via:
     - --file: Path to a JSON/YAML file
     - stdin: Pipe JSON/YAML content
@@ -513,7 +579,7 @@ def update_view(
 ):
     """
     Update an existing view.
-    
+
     The view configuration can be provided via:
     - --file: Path to a JSON/YAML file
     - stdin: Pipe JSON/YAML content
@@ -566,20 +632,22 @@ def delete_view(
 
 @app.command()
 def query(
-    engine_name: str = typer.Option(..., help="Name of the engine to execute the query against."),
+    engine_name: str = typer.Option(
+        ..., help="Name of the engine to execute the query against."
+    ),
     query_file: typer.FileText = typer.Option(
         None, help="Path to a JSON or YAML file containing the query."
     ),
     query: str = typer.Option(
-        None, help="JSON string containing the query. Can be used instead of --query-file."
+        None, help="Query string (SQL or JSON). Can be used instead of --query-file."
     ),
 ):
     """
     Execute an ad-hoc query against an engine.
-    
+
     The query can be provided via:
     - --query-file: Path to a JSON/YAML file
-    - --query: JSON string directly
+    - --query: SQL query string or JSON string containing the query
     - stdin: Pipe JSON/YAML content
     """
     config = _read_config()
@@ -590,28 +658,79 @@ def query(
         "x-api-key": config.api_key,
     }
 
-    if not sys.stdin.isatty():
-        payload = sys.stdin.read()
-    elif query_file is not None:
-        payload = _parse_file_as_json(query_file)
-    elif query is not None:
-        payload = query
-    else:
-        raise ValueError(
-            "Must provide either a '--query-file', '--query' JSON string, or stdin input."
-        )
+    try:
+        # Check stdin only if no other input options are provided.
+        # If stdin is not a TTY, peek to see if there's content.
+        stdin_has_content = False
+        stdin_content = ""
+        if not sys.stdin.isatty() and query_file is None and query is None:
+            # Only read from stdin if no other options provided.
+            stdin_content = sys.stdin.read()
+            stdin_has_content = bool(stdin_content.strip())
+            if not stdin_has_content:
+                raise ValueError(
+                    "No input provided via stdin. Provide a SQL query string or "
+                    "JSON query configuration."
+                )
+
+        if stdin_has_content:
+            # Read from stdin and normalize to QueryRequest.
+            payload = _normalize_query_to_request(stdin_content)
+        elif query_file is not None:
+            # Read file content and normalize to QueryRequest.
+            # Files can contain SQL strings or JSON/YAML.
+            try:
+                # Try to parse as JSON/YAML first.
+                query_file.seek(0)
+                file_content = _parse_file_as_json(query_file)
+            except (ValueError, json.JSONDecodeError, yaml.YAMLError) as e:
+                # If parsing fails, read as raw content (e.g., SQL string).
+                query_file.seek(0)
+                file_content = query_file.read()
+                if not file_content.strip():
+                    raise ValueError(
+                        f"File '{query_file.name}' is empty or could not be parsed. "
+                        "Provide a SQL query string or valid JSON/YAML configuration."
+                    ) from e
+            payload = _normalize_query_to_request(file_content)
+        elif query is not None:
+            # Normalize CLI string input to QueryRequest.
+            payload = _normalize_query_to_request(query)
+        else:
+            raise ValueError(
+                "Must provide query input via one of:\n"
+                "  - --query-file: Path to a file containing SQL or JSON/YAML\n"
+                "  - --query: SQL query string or JSON string\n"
+                "  - stdin: Pipe SQL or JSON/YAML content"
+            )
+    except ValueError as e:
+        typer.echo(f"Error: {e}", err=True)
+        raise typer.Exit(1)
+    except Exception as e:
+        typer.echo(f"Error: Unexpected error processing query input: {e}", err=True)
+        raise typer.Exit(1)
 
     typer.echo(payload)
     response = requests.post(url, headers=headers, data=payload)
     if response.status_code != 200:
-        typer.echo(f"Error: {response.status_code}\n{response.text}")
+        # Try to parse error response for better error message.
+        try:
+            error_data = response.json()
+            error_msg = error_data.get(
+                "message", error_data.get("detail", response.text)
+            )
+            typer.echo(f"Error {response.status_code}: {error_msg}", err=True)
+        except (json.JSONDecodeError, ValueError):
+            typer.echo(f"Error {response.status_code}: {response.text}", err=True)
         raise typer.Exit(1)
     typer.echo(_parse_response_as_yaml(response.text))
 
 
 @app.command()
 def execute_saved_query(
-    engine_name: str = typer.Option(..., help="Name of the engine containing the saved query."),
+    engine_name: str = typer.Option(
+        ..., help="Name of the engine containing the saved query."
+    ),
     query_name: str = typer.Option(..., help="Name of the saved query to execute."),
 ):
     """
@@ -633,7 +752,9 @@ def execute_saved_query(
 
 @app.command()
 def view_saved_query(
-    engine_name: str = typer.Option(..., help="Name of the engine containing the saved query."),
+    engine_name: str = typer.Option(
+        ..., help="Name of the engine containing the saved query."
+    ),
     query_name: str = typer.Option(..., help="Name of the saved query to view."),
 ):
     """
@@ -651,7 +772,9 @@ def view_saved_query(
 
 @app.command()
 def list_saved_queries(
-    engine_name: str = typer.Option(..., help="Name of the engine to list saved queries for."),
+    engine_name: str = typer.Option(
+        ..., help="Name of the engine to list saved queries for."
+    ),
 ):
     """
     List all saved queries for an engine.
@@ -666,5 +789,10 @@ def list_saved_queries(
     typer.echo(_parse_response_as_yaml(response.text))
 
 
-if __name__ == "__main__":
+def main():
+    """Entry point for the shaped CLI command."""
     app(prog_name="shaped")
+
+
+if __name__ == "__main__":
+    main()