cmem-plugin-llm 0.5.0__tar.gz

cmem_plugin_llm-0.5.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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 2021 CMEM
+
+   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.

cmem_plugin_llm-0.5.0/PKG-INFO

@@ -0,0 +1,65 @@
+Metadata-Version: 2.3
+Name: cmem-plugin-llm
+Version: 0.5.0
+Summary: Interact with Large Language Models.
+License: Apache-2.0
+Keywords: eccenca Corporate Memory,plugin
+Author: eccenca GmbH
+Author-email: cmempy-developer@eccenca.com
+Requires-Python: >=3.11,<4.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Plugins
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: cmem-plugin-base (>=4.7.0,<5.0.0)
+Requires-Dist: langchain-community (>=0.3.0,<0.4.0)
+Requires-Dist: langchain-openai (>=0.2.0,<0.3.0)
+Requires-Dist: pydantic (>=2.8.2,<3.0.0)
+Description-Content-Type: text/markdown
+
+# cmem-plugin-llm
+
+Interact with Large Language Models.
+
+[![eccenca Corporate Memory][cmem-shield]][cmem-link]
+
+This is a plugin for [eccenca](https://eccenca.com) [Corporate Memory](https://documentation.eccenca.com). You can install it with the [cmemc](https://eccenca.com/go/cmemc) command line clients like this:
+
+```
+cmemc admin workspace python install cmem-plugin-llm
+```
+  
+[![poetry][poetry-shield]][poetry-link] [![ruff][ruff-shield]][ruff-link] [![mypy][mypy-shield]][mypy-link] [![copier][copier-shield]][copier] 
+
+[cmem-link]: https://documentation.eccenca.com
+[cmem-shield]: https://img.shields.io/endpoint?url=https://dev.documentation.eccenca.com/badge.json
+[poetry-link]: https://python-poetry.org/
+[poetry-shield]: https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json
+[ruff-link]: https://docs.astral.sh/ruff/
+[ruff-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json&label=Code%20Style
+[mypy-link]: https://mypy-lang.org/
+[mypy-shield]: https://www.mypy-lang.org/static/mypy_badge.svg
+[copier]: https://copier.readthedocs.io/
+[copier-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/copier-org/copier/master/img/badge/badge-grayscale-inverted-border-purple.json
+
+This plugin contain the following capabilitities:
+
+- create embeddings: it allows to create embeddings from an arbitrary data point or from specified data point paths (properties/columns).
+After being processed each data point receive two additional paths the ```embedding``` path and the ```text``` path.
+  - The ```text``` path contain the paths utilized for generate the embeddings in text format. 
+    - If the original data contain already a path named ```text```, this path is used for embeddings generation.
+  - The ```embedding``` path contain the generated embedding.
+
+# Parameters
+
+- ```url```: openAI compatible endpoint, default ```https://api.openai.com/v1```
+- ```model```: embedding model, default ```text-embedding-3-small```
+- ```api_key```: api key of the endpoint, default blank
+- ```timout_single_request```: the request timenout in milliseconds, default ```10000```
+- ```entries_processing_buffer```: number of processed entries per request, default ```1000```
+- ```embedding_paths```: specify which paths should be used for embedding generation, default all
+- ```embedding_output_text```: output path that will contain the embedding text, default ```text```
+- ```embedding_output_path```: output path that will contain the generated embedding, default ```embedding```

cmem_plugin_llm-0.5.0/README-public.md

@@ -0,0 +1,43 @@
+# cmem-plugin-llm
+
+Interact with Large Language Models.
+
+[![eccenca Corporate Memory][cmem-shield]][cmem-link]
+
+This is a plugin for [eccenca](https://eccenca.com) [Corporate Memory](https://documentation.eccenca.com). You can install it with the [cmemc](https://eccenca.com/go/cmemc) command line clients like this:
+
+```
+cmemc admin workspace python install cmem-plugin-llm
+```
+  
+[![poetry][poetry-shield]][poetry-link] [![ruff][ruff-shield]][ruff-link] [![mypy][mypy-shield]][mypy-link] [![copier][copier-shield]][copier] 
+
+[cmem-link]: https://documentation.eccenca.com
+[cmem-shield]: https://img.shields.io/endpoint?url=https://dev.documentation.eccenca.com/badge.json
+[poetry-link]: https://python-poetry.org/
+[poetry-shield]: https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json
+[ruff-link]: https://docs.astral.sh/ruff/
+[ruff-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json&label=Code%20Style
+[mypy-link]: https://mypy-lang.org/
+[mypy-shield]: https://www.mypy-lang.org/static/mypy_badge.svg
+[copier]: https://copier.readthedocs.io/
+[copier-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/copier-org/copier/master/img/badge/badge-grayscale-inverted-border-purple.json
+
+This plugin contain the following capabilitities:
+
+- create embeddings: it allows to create embeddings from an arbitrary data point or from specified data point paths (properties/columns).
+After being processed each data point receive two additional paths the ```embedding``` path and the ```text``` path.
+  - The ```text``` path contain the paths utilized for generate the embeddings in text format. 
+    - If the original data contain already a path named ```text```, this path is used for embeddings generation.
+  - The ```embedding``` path contain the generated embedding.
+
+# Parameters
+
+- ```url```: openAI compatible endpoint, default ```https://api.openai.com/v1```
+- ```model```: embedding model, default ```text-embedding-3-small```
+- ```api_key```: api key of the endpoint, default blank
+- ```timout_single_request```: the request timenout in milliseconds, default ```10000```
+- ```entries_processing_buffer```: number of processed entries per request, default ```1000```
+- ```embedding_paths```: specify which paths should be used for embedding generation, default all
+- ```embedding_output_text```: output path that will contain the embedding text, default ```text```
+- ```embedding_output_path```: output path that will contain the generated embedding, default ```embedding```

cmem_plugin_llm-0.5.0/cmem_plugin_llm/__init__.py

@@ -0,0 +1 @@
+"""cmem-plugin-llm"""

cmem_plugin_llm-0.5.0/cmem_plugin_llm/create_embedding.py

@@ -0,0 +1,313 @@
+"""Create Embeddings via OpenAI embeddings API endpoint"""
+
+from collections.abc import Generator, Sequence
+from typing import Any, ClassVar
+
+from cmem_plugin_base.dataintegration.context import (
+    ExecutionContext,
+    ExecutionReport,
+    PluginContext,
+)
+from cmem_plugin_base.dataintegration.description import Plugin, PluginParameter
+from cmem_plugin_base.dataintegration.entity import (
+    Entities,
+    Entity,
+    EntityPath,
+    EntitySchema,
+)
+from cmem_plugin_base.dataintegration.parameter.password import Password, PasswordParameterType
+from cmem_plugin_base.dataintegration.plugins import WorkflowPlugin
+from cmem_plugin_base.dataintegration.ports import (
+    FixedNumberOfInputs,
+    FixedSchemaPort,
+    FlexibleSchemaPort,
+    UnknownSchemaPort,
+)
+from cmem_plugin_base.dataintegration.types import Autocompletion, StringParameterType
+from langchain_core.utils.utils import convert_to_secret_str
+from langchain_openai import OpenAIEmbeddings
+from openai import AuthenticationError, OpenAI
+
+DEFAULT_EMBEDDING_PATH = "_embedding"
+DEFAULT_EMBEDDING_SOURCE_PATH = "_embedding_source"
+MODEL_EXAMPLE = "text-embedding-3-small"
+
+
+class SamePathError(ValueError):
+    """Same Path Exception"""
+
+    def __init__(self, path: str):
+        super().__init__(f"Path '{path}' can not be input AND output path.")
+
+
+class OpenAPIModel(StringParameterType):
+    """OpenAPI Model Type"""
+
+    autocompletion_depends_on_parameters: ClassVar[list[str]] = ["url", "api_key"]
+
+    # auto complete for values
+    allow_only_autocompleted_values: bool = True
+    # auto complete for labels
+    autocomplete_value_with_labels: bool = True
+
+    def autocomplete(
+        self,
+        query_terms: list[str],
+        depend_on_parameter_values: list[Any],
+        context: PluginContext,
+    ) -> list[Autocompletion]:
+        """Return all results that match ALL provided query terms."""
+        _ = context
+        url = depend_on_parameter_values[0]
+        api_key = depend_on_parameter_values[1]
+        api_key = api_key if isinstance(api_key, str) else api_key.decrypt()
+        result = []
+        try:
+            api = OpenAI(api_key=api_key, base_url=url)
+            models = api.models.list()
+            filtered_models = set()
+            if query_terms:
+                for term in query_terms:
+                    for model in models:
+                        if term in model.id:
+                            filtered_models.add(model.id)
+            else:
+                filtered_models = {_.id for _ in models}
+            result = [Autocompletion(value=f"{_}", label=f"{_}") for _ in filtered_models]
+        except AuthenticationError as error:
+            raise ValueError(
+                "Failed to authenticate with OpenAI API, Please check URL and API key."
+            ) from error
+
+        result.sort(key=lambda x: x.label)
+        return result
+
+
+@Plugin(
+    label="Create Embeddings",
+    description="Fetch embeddings from OpenAI embeddings API endpoint.",
+    parameters=[
+        PluginParameter(
+            name="url",
+            label="URL",
+            description="URL of the OpenAI API (without endpoint path and without trailing slash)",
+            default_value="https://api.openai.com/v1",
+        ),
+        PluginParameter(
+            name="api_key",
+            label="The OpenAI API key",
+            param_type=PasswordParameterType(),
+            description="Fill the OpenAI API key if needed "
+            "(or give a dummy value in case you access an unsecured endpoint).",
+        ),
+        PluginParameter(
+            name="model",
+            label=f"The embeddings model, e.g. {MODEL_EXAMPLE}",
+            param_type=OpenAPIModel(),
+        ),
+        PluginParameter(
+            name="timout_single_request",
+            label="Timeout (Single Request, in Milliseconds)",
+            advanced=True,
+            default_value=10000,
+        ),
+        PluginParameter(
+            name="entries_processing_buffer",
+            label="Entries Processing Buffer",
+            description="How many input values do you want to send per request?",
+            advanced=True,
+            default_value=100,
+        ),
+        PluginParameter(
+            name="embedding_output_path",
+            label="Entity Embedding path (output)",
+            description=f"Changing this value will change the output schema accordingly. "
+            f"Default: {DEFAULT_EMBEDDING_PATH}",
+            advanced=True,
+            default_value=DEFAULT_EMBEDDING_PATH,
+        ),
+        PluginParameter(
+            name="embedding_output_text",
+            label="Entity Embedding text (output)",
+            description=f"Changing this value will change the output schema accordingly. "
+            f"Default: {DEFAULT_EMBEDDING_SOURCE_PATH}",
+            advanced=True,
+            default_value=DEFAULT_EMBEDDING_SOURCE_PATH,
+        ),
+        PluginParameter(
+            name="embedding_paths",
+            label="Used entity paths (comma-separated list)",
+            description="Changing this value will change, which input paths are used by the "
+            "workflow task. A blank value means, all paths are used.",
+            advanced=True,
+            default_value="text",
+        ),
+    ],
+)
+class CreateEmbeddings(WorkflowPlugin):
+    """Fetch embeddings from OpenAI embeddings API endpoint"""
+
+    execution_context: ExecutionContext
+    embeddings: OpenAIEmbeddings
+    entries_processing_buffer: int
+    embedding_output_text: str
+    embedding_output_path: str
+    embedding_paths: list[str]
+    embedding_report: ExecutionReport
+
+    def __init__(  # noqa: PLR0913
+        self,
+        url: str,
+        api_key: Password | str = "",
+        model: str = MODEL_EXAMPLE,
+        timout_single_request: int = 10000,
+        entries_processing_buffer: int = 100,
+        embedding_paths: str = "",
+        embedding_output_text: str = DEFAULT_EMBEDDING_SOURCE_PATH,
+        embedding_output_path: str = DEFAULT_EMBEDDING_PATH,
+    ) -> None:
+        self.base_url = url
+        self.timout_single_request = timout_single_request
+        self.api_key = api_key if isinstance(api_key, str) else api_key.decrypt()
+        if self.api_key == "":
+            self.api_key = "dummy-key"
+        self.embeddings = OpenAIEmbeddings(
+            base_url=url,
+            api_key=convert_to_secret_str(self.api_key),
+            model=model,
+            timeout=timout_single_request,
+        )
+        self.entries_processing_buffer = entries_processing_buffer
+        self.embedding_output_text = embedding_output_text
+        self.embedding_output_path = embedding_output_path
+        self.embedding_paths = self.input_paths_to_list(embedding_paths)
+        self.embedding_report = ExecutionReport()
+        self.embedding_report.operation = "create"
+        self.embedding_report.operation_desc = "embeddings created"
+        self._setup_ports()
+        if self.embedding_output_text in self.embedding_paths:
+            raise SamePathError(self.embedding_output_text)
+        if self.embedding_output_path in self.embedding_paths:
+            raise SamePathError(self.embedding_output_path)
+
+    @staticmethod
+    def input_paths_to_list(paths: str) -> list[str]:
+        """Convert a comma-separated list of strings to a python list of strings."""
+        return [] if paths == "" else [_.strip() for _ in paths.split(",")]
+
+    def _setup_ports(self) -> None:
+        """Configure input and output ports depending on the configuration"""
+        if len(self.embedding_paths) == 0:
+            self.input_ports = FixedNumberOfInputs([FlexibleSchemaPort()])
+            self.output_port = UnknownSchemaPort()
+            return
+
+        input_paths = [EntityPath(path=_) for _ in self.embedding_paths]
+        input_schema = EntitySchema(type_uri="entity", paths=input_paths)
+        self.input_ports = FixedNumberOfInputs(ports=[FixedSchemaPort(schema=input_schema)])
+
+        output_paths = [
+            EntityPath(path=_)
+            for _ in [*self.embedding_paths, self.embedding_output_path, self.embedding_output_text]
+        ]
+        output_schema = EntitySchema(type_uri="entity", paths=output_paths)
+        self.output_port = FixedSchemaPort(schema=output_schema)
+
+    def _generate_output_schema(self, input_schema: EntitySchema) -> EntitySchema:
+        """Get output schema"""
+        paths = list(input_schema.paths).copy()
+        paths.append(EntityPath(self.embedding_output_path))
+        paths.append(EntityPath(self.embedding_output_text))
+        return EntitySchema(type_uri=input_schema.type_uri, paths=paths)
+
+    def workflow_canceling(self) -> bool:
+        """Check if the workflow is canceling / cancelled"""
+        try:
+            if self.execution_context.workflow.status() == "Canceling":
+                self.log.info("End task (Cancelled Workflow).")
+                return True
+        except AttributeError:
+            pass
+        return False
+
+    def _embedding_report_update(self, n: int) -> None:
+        if hasattr(self.execution_context, "report"):
+            self.embedding_report.entity_count += n
+            self.execution_context.report.update(self.embedding_report)
+
+    @staticmethod
+    def chunker(seq: Sequence, size: int) -> Generator[Sequence]:
+        """Split a sequence into chunks"""
+        chunk = []
+        for entry in seq:
+            chunk.append(entry)
+            if len(chunk) == size:
+                yield chunk.copy()
+                chunk.clear()
+        if len(chunk) > 0:
+            yield chunk.copy()
+
+    @staticmethod
+    def _entity_to_dict(paths: Sequence[EntityPath], entity: Entity) -> dict[str, list[str]]:
+        """Create a dict representation of an entity"""
+        entity_dic = {}
+        for key, value in zip(paths, entity.values, strict=False):
+            entity_dic[key.path] = list(value)
+        return entity_dic
+
+    def _process_entities(self, entities: Entities) -> Generator[Entity]:
+        """Process an entity list (chunked), yielding new entity objects"""
+        self._embedding_report_update(0)
+        for entity_chunk in self.chunker(entities.entities, self.entries_processing_buffer):
+            embeddings_sources: list[str] = []  # a list of embedding source texts
+            entity_dicts: list[dict[str, list[str]]] = []  # a list of entity dictionaries
+            entity: Entity
+            if self.workflow_canceling():
+                break
+            for entity in entity_chunk:
+                entity_dic = self._entity_to_dict(entities.schema.paths, entity)
+                entity_dicts.append(entity_dic)
+                if len(entity.values) == 1 and len(entity.values[0]) == 1:
+                    embedding_source = entity.values[0][0]
+                else:
+                    embedding_source = str(entity_dic)
+                embeddings_sources.append(embedding_source)
+            embeddings: list[list[float]] = self.embeddings.embed_documents(embeddings_sources)
+            self._embedding_report_update(len(embeddings_sources))
+
+            # looping over list of embeddings, entity dicts, sources and entities
+            for (
+                entity_embedding,
+                entity_dict,
+                embedding_source,
+                original_entity,
+            ) in zip(
+                embeddings,
+                entity_dicts,
+                embeddings_sources,
+                entity_chunk,
+                strict=False,
+            ):
+                # add string repr of the embedding as a single value list
+                entity_dict[self.embedding_output_path] = [str(entity_embedding)]
+                # add string repr of the embedding source as a single value list
+                entity_dict[self.embedding_output_text] = [embedding_source]
+                values = list(entity_dict.values())
+                yield Entity(uri=original_entity.uri, values=values)
+
+    def execute(
+        self,
+        inputs: Sequence[Entities],
+        context: ExecutionContext,
+    ) -> Entities:
+        """Run the workflow operator."""
+        self.log.info("Start")
+        self.execution_context = context
+        first_input: Entities = inputs[0]
+        for input_path in [_.path for _ in first_input.schema.paths]:
+            if input_path in [self.embedding_output_path, self.embedding_output_text]:
+                raise SamePathError(input_path)
+        entities = self._process_entities(first_input)
+        schema = self._generate_output_schema(first_input.schema)
+        self.log.info("End")
+        return Entities(entities=entities, schema=schema)

cmem_plugin_llm-0.5.0/pyproject.toml

@@ -0,0 +1,99 @@
+[tool.poetry]
+name = "cmem-plugin-llm"
+version = "0.5.0"
+license = "Apache-2.0"
+description = "Interact with Large Language Models."
+authors = ["eccenca GmbH <cmempy-developer@eccenca.com>"]
+classifiers = [
+    "Development Status :: 4 - Beta","Environment :: Plugins",
+]
+readme = "README-public.md"
+keywords = [
+    "eccenca Corporate Memory", "plugin"
+]
+
+
+[tool.poetry.dependencies]# if you need to change python version here, change it also in .python-version
+python = "^3.11"
+langchain-openai = "^0.2.0"
+langchain-community = "^0.3.0"
+pydantic = "^2.8.2"
+
+[tool.poetry.dependencies.cmem-plugin-base]
+version = "^4.7.0"
+allow-prereleases = false
+
+[tool.poetry.group.dev.dependencies.cmem-cmemc]
+version = "^24.2.0"
+
+[tool.poetry.group.dev.dependencies]
+genbadge = {extras = ["coverage"], version = "^1.1.1"}
+mypy = "^1.11.1"
+pip = "^24"
+pytest = "^8.3.2"
+pytest-cov = "^5.0.0"
+pytest-dotenv = "^0.5.2"
+pytest-html = "^4.1.1"
+pytest-memray = { version = "^1.7.0",  markers = "platform_system != 'Windows'" }
+ruff = "^0.6.1"
+safety = "^1.10.3"
+types-requests = "^2.32.0.20240712"
+
+[build-system]
+requires = ["poetry-core>=1.0.0", "poetry-dynamic-versioning"]
+build-backend = "poetry_dynamic_versioning.backend"
+
+[tool.poetry-dynamic-versioning]
+enable = false
+vcs = "git"
+dirty = true
+bump = true
+
+[tool.mypy]
+warn_return_any = true
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+addopts = ""
+
+[tool.coverage.report]
+exclude_also = [
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if TYPE_CHECKING:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+    ]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.format]
+line-ending = "lf" # Use `\n` line endings for all files
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [
+    "ANN101",  # Missing type annotation for self in method
+    "ANN204",  # Missing return type annotation for special method `__init__`
+    "COM812",  # missing-trailing-comma
+    "D107",    # Missing docstring in __init__
+    "D203",    # [*] 1 blank line required before class docstring
+    "D211",    # No blank lines allowed before class docstring
+    "D213",    # Multi-line docstring summary should start at the second line
+    "D400",    # First line should end with a period
+    "D415",    # First line should end with a period, question mark, or exclamation point
+    "EM",      # Exception texts - https://docs.astral.sh/ruff/rules/#flake8-errmsg-em
+    "FBT",     # The Boolean Trap - https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
+    "FIX002",  # Allow to add TODO notes in the code
+    "G004",    # Logging statement uses f-string
+    "ISC001",  # single-line-implicit-string-concatenation
+    "PD",      # opinionated linting for pandas code
+    "S101",    # use of assert detected
+    "TRY003",  # Avoid specifying long messages outside the exception class
+]
+