donkey-embeddings-watsonx 0.1.0__tar.gz

donkey_embeddings_watsonx-0.1.0/.gitignore

@@ -0,0 +1,85 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+#IDE
+.DS_Store
+.idea
+.vscode
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Mkdocs documentation
+docs/_build/
+docs/api_reference/site/
+
+# Ruff
+.ruff_cache/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/

donkey_embeddings_watsonx-0.1.0/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: donkey-embeddings-watsonx
+Version: 0.1.0
+Summary: donkey embeddings watsonx integration
+Author-email: Leonardo Furnielis <leonardofurnielis@outlook.com>
+License: Apache-2.0
+Requires-Python: <3.14,>=3.11
+Requires-Dist: donkey-core<0.2.0,>=0.1.0
+Requires-Dist: ibm-watsonx-ai<1.6.0,>=1.5.5
+Provides-Extra: dev
+Requires-Dist: pytest-asyncio<2.0.0,>=1.4.0; extra == 'dev'
+Requires-Dist: pytest<10.0.0,>=9.1.1; extra == 'dev'
+Requires-Dist: ruff<0.16.0,>=0.15.20; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Donkey embeddings integration - watsonx
+
+## Installation
+
+```bash
+pip install donkey-embeddings-watsonx
+```

donkey_embeddings_watsonx-0.1.0/README.md

@@ -0,0 +1,7 @@
+# Donkey embeddings integration - watsonx
+
+## Installation
+
+```bash
+pip install donkey-embeddings-watsonx
+```

donkey_embeddings_watsonx-0.1.0/donkey/embeddings/watsonx/__init__.py

@@ -0,0 +1,3 @@
+from donkey.embeddings.watsonx.base import WatsonxEmbedding
+
+__all__ = ["WatsonxEmbedding"]

donkey_embeddings_watsonx-0.1.0/donkey/embeddings/watsonx/base.py

@@ -0,0 +1,85 @@
+from typing import Any
+
+from donkey.core.bridge.pydantic import Field, PrivateAttr, SecretStr
+from donkey.core.embeddings import BaseEmbedding, Embedding
+
+
+class WatsonxEmbedding(BaseEmbedding):
+    """
+    IBM watsonx embedding models.
+
+    Note:
+            One of these parameters is required: `project_id` or `space_id`. Not both.
+
+    See [https://cloud.ibm.com/apidocs/watsonx-ai#endpoint-url](https://cloud.ibm.com/apidocs/watsonx-ai#endpoint-url) for the watsonx.ai API endpoints.
+
+    Attributes:
+        model_name (str): IBM watsonx.ai model to be used. Defaults to `ibm/slate-30m-english-rtrvr`.
+        api_key (str): watsonx API key.
+        url (str): watsonx instance url.
+        truncate_input_tokens (str): Maximum number of input tokens accepted. Defaults to `512`
+        project_id (str, optional): watsonx project_id.
+        space_id (str, optional): watsonx space_id.
+
+    Example:
+        ```python
+        from donkey.embeddings.watsonx import WatsonxEmbedding
+
+        watsonx_embedding = WatsonxEmbedding(
+            api_key="your_api_key",
+            url="your_instance_url",
+            project_id="your_project_id",
+        )
+        ```
+    """
+
+    model_name: str = Field(
+        default="ibm/slate-30m-english-rtrvr",
+        description="Name of the embedding model",
+    )
+    api_key: SecretStr
+    url: str
+    truncate_input_tokens: int = 512
+    project_id: str | None = None
+    space_id: str | None = None
+
+    _client: Any = PrivateAttr()
+
+    def model_post_init(self, __context):  # noqa: PYI063
+        from ibm_watsonx_ai import Credentials
+        from ibm_watsonx_ai.foundation_models import Embeddings as WatsonxEmbeddings
+
+        if (not (self.project_id or self.space_id)) or (
+            self.project_id and self.space_id
+        ):
+            raise ValueError(
+                "Must provide ONE of these parameters [`project_id`, `space_id`], not both.",
+            )
+
+        kwargs_params = {
+            "model_id": self.model_name,
+            "params": {
+                "truncate_input_tokens": self.truncate_input_tokens,
+                "return_options": {"input_text": False},
+            },
+            "credentials": Credentials(
+                api_key=self.api_key.get_secret_value(), url=self.url
+            ),
+        }
+
+        if self.project_id:
+            kwargs_params["project_id"] = self.project_id
+        else:
+            kwargs_params["space_id"] = self.space_id
+
+        self._client = WatsonxEmbeddings(**kwargs_params)
+
+    def _get_text_embeddings(self, input: str | list[str]) -> list[Embedding]:
+        """Embed one or more text strings."""
+        if isinstance(input, str):
+            return [self._client.embed_query(input)]
+
+        elif isinstance(input, list) and all(isinstance(i, str) for i in input):
+            return self._client.embed_documents(input)
+        else:
+            raise TypeError(f"Expected str or list[str], got {type(input).__name__}")

donkey_embeddings_watsonx-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "donkey-embeddings-watsonx"
+version = "0.1.0"
+description = "donkey embeddings watsonx integration"
+authors = [{ name = "Leonardo Furnielis", email = "leonardofurnielis@outlook.com" }]
+license = { text = "Apache-2.0" }
+readme = "README.md"
+requires-python = ">=3.11,<3.14"
+dependencies = [
+    "ibm-watsonx-ai>=1.5.5,<1.6.0",
+    "donkey-core>=0.1.0,<0.2.0",
+]
+
+[tool.hatch.build.targets.sdist]
+include = ["donkey/"]
+
+[tool.hatch.build.targets.wheel]
+include = ["donkey/"]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=9.1.1,<10.0.0",
+    "pytest-asyncio>=1.4.0,<2.0.0",
+    "ruff>=0.15.20,<0.16.0",
+]