sutro 0.1.36__py3-none-any.whl → 0.1.38__py3-none-any.whl

sutro/templates/classification.py

@@ -0,0 +1,117 @@
+import json
+from typing import Union, List
+import polars as pl
+import pandas as pd
+from pydantic import BaseModel
+
+from ..common import ModelOptions
+from ..interfaces import BaseSutroClient
+
+
+class ClassificationTemplates(BaseSutroClient):
+    def classify(
+        self,
+        data: Union[List, pd.DataFrame, pl.DataFrame, str],
+        classes: Union[dict[str, str], list[str]],
+        model: ModelOptions = "gemma-3-12b-it",
+        job_priority: int = 0,
+        name: Union[str, List[str]] = None,
+        description: Union[str, List[str]] = None,
+        output_column: str = "inference_result",
+        column: Union[str, List[str]] = None,
+        truncate_rows: bool = True,
+        include_scratchpad: bool = False,
+    ):
+        """
+        A simple template style function to perform classification on the provided data with Sutro. The intention is that the implemented code should be very easy to extend further, while showing a basic structure for large-scale classification with Sutro.
+
+        It uses structured outputs with a scratchpad field, enabling the model to reason step-by-step before providing the final classification.
+        The method supports various input formats including lists, DataFrames (Polars or Pandas), file paths, and datasets.
+        The method will wait for the classification job to complete before returning the results.
+
+        Args:
+            data (Union[List, pd.DataFrame, pl.DataFrame, str]): The data to classify. Each row should contain some text to classifiy that fits into one of the passed in labels.
+            classes (Union[dict[str, str], list[str]]): The classification classes. Can be either:
+                - A list of class names, ie ["Positive", "Negative", "Neutral"]
+                - A dict mapping class labels to descriptions, ie {"Positive": "Expresses satisfaction...", ...}
+                Providing descriptions can improve classification accuracy, especially for ambiguous or domain-specific categories.
+            model (ModelOptions, optional): The LLM to use. Defaults to "gemma-3-12b-it"; a model chosen for its balance of performance and efficiency, that also retains competency across a broad number of different domains.
+            job_priority (int, optional): The priority of the job. Defaults to 0.
+            name (Union[str, List[str]], optional): A job name for experiment/metadata tracking purposes. Defaults to None.
+            description (Union[str, List[str]], optional): A job description for experiment/metadata tracking purposes. Defaults to None.
+            output_column (str, optional): The column name to store the classification results in if the input is a DataFrame. Defaults to "inference_result".
+            column (Union[str, List[str]], optional): The column name to use for classification. Required if data is a DataFrame, file path, or dataset. If a list is supplied, it will concatenate the columns of the list into a single column, accepting separator strings.
+            truncate_rows (bool, optional): If True, any rows that have a token count exceeding the context window length of the selected model will be truncated to the max length that will fit within the context window. Defaults to True.
+            include_scratchpad (bool, optional): If True, includes the model's thinking scratchpad in the output. If False, only returns the final classification. Defaults to False.
+
+        Returns:
+            The completed classification results for the provided data. If include_scratchpad is True, returns both scratchpad and classification fields in JSON object. If False, returns only the classification as a string.
+
+        """
+        if isinstance(classes, dict):
+            formatted_classes = "\n".join(
+                [f"- {name}: {desc}" for name, desc in classes.items()]
+            )
+        else:
+            formatted_classes = "\n".join([f"- {c}" for c in classes])
+
+        system_prompt = f"""You are an expert classifier. Your task is to accurately categorize the input into one of the provided classes.
+
+## Classes
+
+{formatted_classes}
+
+## Instructions
+
+1. **Analyze the input carefully**: Read and understand the full context - identify key elements, themes, and characteristics
+
+2. **Consider each class**: For each possible class, evaluate how similar the input is to its typical characteristics
+
+3. **Provide your reasoning in the scratchpad**: Think through which class fits best and why
+
+4. **Provide output**: Give your final classification
+
+If needed, use the scratchpad field to work through steps 1-3, then provide your final answer in the classification field.
+
+## Guidelines
+
+- Select exactly ONE class, even if multiple seem applicable (choose the best match)
+- If the input is ambiguous, choose the closest fit and explain your reasoning
+- Base your decision on the actual content, not assumptions or implications
+- Similar inputs should receive the same classification
+
+Respond using the structured format with scratchpad and classification fields."""
+
+        class ClassificationOutput(BaseModel):
+            # Since we're using structured outputs, we want to give the model some
+            # space to reason and think as needed
+            scratchpad: str
+            classification: str
+
+        job_id = self.infer(
+            data,
+            model,
+            name,
+            description,
+            system_prompt=system_prompt,
+            output_schema=ClassificationOutput,
+            column=column,
+            output_column=output_column,
+            job_priority=job_priority,
+            truncate_rows=truncate_rows,
+            stay_attached=False,
+        )
+
+        results = self.await_job_completion(job_id)
+
+        # Filter out scratchpad if not wanted
+        if not include_scratchpad:
+            results = results.with_columns(
+                pl.col(output_column)
+                .map_elements(
+                    lambda x: json.loads(x)["classification"], return_dtype=pl.Utf8
+                )
+                .alias(output_column)
+            )
+
+        return results

sutro/templates/embed.py

@@ -0,0 +1,53 @@
+from typing import Union, List
+import polars as pl
+import pandas as pd
+from ..common import EmbeddingModelOptions
+from ..interfaces import BaseSutroClient
+
+
+class EmbeddingTemplates(BaseSutroClient):
+    def embed(
+        self,
+        data: Union[List, pd.DataFrame, pl.DataFrame, str],
+        model: EmbeddingModelOptions = "qwen-3-embedding-0.6b",
+        job_priority: int = 0,
+        name: Union[str, List[str]] = None,
+        description: Union[str, List[str]] = None,
+        output_column: str = "inference_result",
+        column: Union[str, List[str]] = None,
+        truncate_rows: bool = True,
+    ):
+        """
+        A simple template style function to generate embeddings for the provided data, with Sutro. The intention is that the implemented code should be very easy to extend further, while showing a basic structure for large scale embedding generation with Sutro.
+
+        This method allows you to generate vector embeddings for the provided data using Sutro.
+        It supports various options for inputting data, such as lists, DataFrames (Polars or Pandas), file paths and datasets.
+        The method will wait for the embedding job to complete before returning the results.
+
+        Args:
+            data (Union[List, pd.DataFrame, pl.DataFrame, str]): The data to generate embeddings for.
+            model (ModelOptions, optional): The embedding model to use. Defaults to "qwen-3-embedding-0.6b"; a model we chose as its small & fast, yet performs well on a variety of tasks.
+            job_priority (int, optional): The priority of the job. Defaults to 0.
+            name (Union[str, List[str]], optional): A job name for experiment/metadata tracking purposes. Defaults to None.
+            description (Union[str, List[str]], optional): A job description for experiment/metadata tracking purposes. Defaults to None.
+            output_column (str, optional): The column name to store the embedding results in if the input is a DataFrame. Defaults to "inference_result".
+            column (Union[str, List[str]], optional): The column name to use for embedding generation. Required if data is a DataFrame, file path, or dataset. If a list is supplied, it will concatenate the columns of the list into a single column, accepting separator strings.
+            truncate_rows (bool, optional): If True, any rows that have a token count exceeding the context window length of the selected model will be truncated to the max length that will fit within the context window. Defaults to True.
+
+        Returns:
+            The completed embedding results for the provided data.
+
+        """
+        job_id = self.infer(
+            data,
+            model,
+            name,
+            description,
+            column,
+            output_column,
+            job_priority,
+            truncate_rows=truncate_rows,
+            stay_attached=False,
+        )
+
+        return self.await_job_completion(job_id)

sutro/validation.py

@@ -0,0 +1,60 @@
+import importlib.metadata
+import json
+import os
+
+import requests
+
+from sutro.common import to_colored_text
+
+
+def check_version(package_name: str):
+    try:
+        # Local version
+        local_version = importlib.metadata.version(package_name)
+    except importlib.metadata.PackageNotFoundError:
+        print(f"{package_name} is not installed.")
+        return
+
+    try:
+        # Latest release from PyPI
+        resp = requests.get(f"https://pypi.org/pypi/{package_name}/json", timeout=2)
+        resp.raise_for_status()
+        latest_version = resp.json()["info"]["version"]
+
+        if local_version != latest_version:
+            msg = (
+                f"⚠️  You are using {package_name} {local_version}, "
+                f"but the latest release is {latest_version}. "
+                f"Run `[uv] pip install -U {package_name}` to upgrade."
+            )
+            print(to_colored_text(msg, state="callout"))
+    except Exception:
+        # Fail silently or log, you don’t want this blocking usage
+        pass
+
+
+def check_for_api_key():
+    """
+    Check for an API key in the user's home directory.
+
+    This method looks for a configuration file named 'config.json' in the
+    '.sutro' directory within the user's home directory.
+    If the file exists, it attempts to read the API key from it.
+
+    Returns:
+        str or None: The API key if found in the configuration file, or None if not found.
+
+    Note:
+        The expected structure of the config.json file is:
+        {
+            "api_key": "your_api_key_here"
+        }
+    """
+    CONFIG_DIR = os.path.expanduser("~/.sutro")
+    CONFIG_FILE = os.path.join(CONFIG_DIR, "config.json")
+    if os.path.exists(CONFIG_FILE):
+        with open(CONFIG_FILE, "r") as f:
+            config = json.load(f)
+        return config.get("api_key")
+    else:
+        return None

{sutro-0.1.36.dist-info → sutro-0.1.38.dist-info}/METADATA

@@ -1,24 +1,23 @@
 Metadata-Version: 2.4
 Name: sutro
-Version: 0.1.36
+Version: 0.1.38
 Summary: Sutro Python SDK
-Project-URL: Homepage, https://sutro.sh
-Project-URL: Documentation, https://docs.sutro.sh
 License-Expression: Apache-2.0
-License-File: LICENSE
+Requires-Dist: numpy>=2.1.1,<3.0.0
+Requires-Dist: requests>=2.32.3,<3.0.0
+Requires-Dist: pandas>=2.2.3,<3.0.0
+Requires-Dist: polars>=1.33.0,<=1.34.0
+Requires-Dist: click>=8.1.7,<9.0.0
+Requires-Dist: colorama>=0.4.4,<1.0.0
+Requires-Dist: yaspin>=3.2.0,<4.0.0
+Requires-Dist: tqdm>=4.67.1,<5.0.0
+Requires-Dist: pydantic>=2.11.4,<3.0.0
+Requires-Dist: pyarrow>=21.0.0,<22.0.0
+Requires-Dist: ruff==0.13.1 ; extra == 'dev'
 Requires-Python: >=3.10
-Requires-Dist: click<9.0.0,>=8.1.7
-Requires-Dist: colorama<1.0.0,>=0.4.4
-Requires-Dist: numpy<3.0.0,>=2.1.1
-Requires-Dist: pandas<3.0.0,>=2.2.3
-Requires-Dist: polars<=1.8.2
-Requires-Dist: pyarrow<22.0.0,>=21.0.0
-Requires-Dist: pydantic<3.0.0,>=2.11.4
-Requires-Dist: requests<3.0.0,>=2.32.3
-Requires-Dist: tqdm<5.0.0,>=4.67.1
-Requires-Dist: yaspin<4.0.0,>=3.2.0
+Project-URL: Documentation, https://docs.sutro.sh
+Project-URL: Homepage, https://sutro.sh
 Provides-Extra: dev
-Requires-Dist: ruff==0.13.1; extra == 'dev'
 Description-Content-Type: text/markdown
 
 ![Sutro Logo](./assets/sutro-logo-dark.png)

sutro-0.1.38.dist-info/RECORD

@@ -0,0 +1,12 @@
+sutro/__init__.py,sha256=yUiVwcZ8QamSqDdRHgzoANyTZ-x3cPzlt2Fs5OllR_w,402
+sutro/cli.py,sha256=0NuqRInXA-_7TRw-T0OxP8otmUHUarMtY7kuLbWDous,13751
+sutro/common.py,sha256=FuTYTzy82Ul56r9SVH0XMOqcBBspDAFvrtHM93ZbT_8,6945
+sutro/interfaces.py,sha256=j8k4iEHjHu6HDEb9XqiuJrIRbXhLZi9WsiVmxC97R8s,2972
+sutro/sdk.py,sha256=qhpmQNHZDaeGffPyCopmlc6YQuA1_hLFmuHeQXlNbSM,56107
+sutro/templates/classification.py,sha256=iNFiyuR8bZc9Xe-NdimklpQUveqg3p_eJOlEAHaj7Is,6080
+sutro/templates/embed.py,sha256=csvLA0hw5Qaro_yZvALRRp9_SbfWABFN0iQXrf8E8_I,2941
+sutro/validation.py,sha256=FlFH5e5PAPIPpCrzU7mwfZKDDvrmkHt2yYsFm0Ahfmg,1849
+sutro-0.1.38.dist-info/WHEEL,sha256=X16MKk8bp2DRsAuyteHJ-9qOjzmnY0x1aj0P1ftqqWA,78
+sutro-0.1.38.dist-info/entry_points.txt,sha256=s-dtPZ0AScjvR8S_ykhzXxtVcUjrRlxVxyJymI81A3E,41
+sutro-0.1.38.dist-info/METADATA,sha256=VeFTzSqKUiPkx8Ey-g1DkZ-_EkrLt6BwVVQa7-XC-sw,6259
+sutro-0.1.38.dist-info/RECORD,,

sutro-0.1.38.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: uv 0.9.2
+Root-Is-Purelib: true
+Tag: py3-none-any

{sutro-0.1.36.dist-info → sutro-0.1.38.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 sutro = sutro.cli:cli
+

sutro-0.1.36.dist-info/RECORD

@@ -1,8 +0,0 @@
-sutro/__init__.py,sha256=yUiVwcZ8QamSqDdRHgzoANyTZ-x3cPzlt2Fs5OllR_w,402
-sutro/cli.py,sha256=_FU8PwP4dMzXXg5ldxCXP3kaZvQtOKdA8Kzjc34xmQ0,13727
-sutro/sdk.py,sha256=vFx0hQczAxefmi-ijlkCgOc8P_TxHgswwGbmMOJpY04,61440
-sutro-0.1.36.dist-info/METADATA,sha256=QlwM7oHJWpLGvyWdV1KxAfg4l8tuc41H29pnUdxu618,6270
-sutro-0.1.36.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-sutro-0.1.36.dist-info/entry_points.txt,sha256=eXvr4dvMV4UmZgR0zmrY8KOmNpo64cJkhNDywiadRFM,40
-sutro-0.1.36.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sutro-0.1.36.dist-info/RECORD,,

sutro-0.1.36.dist-info/WHEEL

@@ -1,4 +0,0 @@
-Wheel-Version: 1.0
-Generator: hatchling 1.27.0
-Root-Is-Purelib: true
-Tag: py3-none-any

sutro-0.1.36.dist-info/licenses/LICENSE

@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.