Python: Nvidia Embedding Connector #10410

raspawar · 2025-02-05T10:07:36Z

Nvidia Embedding Connector

Description

Contribution Checklist

The code builds clean without any errors or warnings
The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
All unit tests pass, and I have added new tests where possible
I didn't break anyone 😄

mattf · 2025-02-05T12:21:40Z

...ic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

+
+    """Specific settings for the text embedding endpoint."""
+
+    input: str | list[str] | list[int] | list[list[int]] | None = None


the OpenAI Embedding API supports list[int] and list[list[int]] to accept pre-tokenized input. the NeMo Retriever Embedding API does not support this.

microsoft-github-policy-service · 2025-02-05T13:11:55Z

@raspawar please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

(default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
(when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"

Contributor License Agreement

Contribution License Agreement

This Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
and conveys certain license rights to Microsoft Corporation and its affiliates (“Microsoft”) for Your
contributions to Microsoft open source projects. This Agreement is effective as of the latest signature
date below.

Definitions.
“Code” means the computer software code, whether in human-readable or machine-executable form,
that is delivered by You to Microsoft under this Agreement.
“Project” means any of the projects owned or managed by Microsoft and offered under a license
approved by the Open Source Initiative (www.opensource.org).
“Submit” is the act of uploading, submitting, transmitting, or distributing code or other content to any
Project, 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 Project for the purpose of
discussing and improving that Project, but excluding communication that is conspicuously marked or
otherwise designated in writing by You as “Not a Submission.”
“Submission” means the Code and any other copyrightable material Submitted by You, including any
associated comments and documentation.
Your Submission. You must agree to the terms of this Agreement before making a Submission to any
Project. This Agreement covers any and all Submissions that You, now or in the future (except as
described in Section 4 below), Submit to any Project.
Originality of Work. You represent that each of Your Submissions is entirely Your original work.
Should You wish to Submit materials that are not Your original work, You may Submit them separately
to the Project if You (a) retain all copyright and license information that was in the materials as You
received them, (b) in the description accompanying Your Submission, include the phrase “Submission
containing materials of a third party:” followed by the names of the third party and any licenses or other
restrictions of which You are aware, and (c) follow any other instructions in the Project’s written
guidelines concerning Submissions.
Your Employer. References to “employer” in this Agreement include Your employer or anyone else
for whom You are acting in making Your Submission, e.g. as a contractor, vendor, or agent. If Your
Submission is made in the course of Your work for an employer or Your employer has intellectual
property rights in Your Submission by contract or applicable law, You must secure permission from Your
employer to make the Submission before signing this Agreement. In that case, the term “You” in this
Agreement will refer to You and the employer collectively. If You change employers in the future and
desire to Submit additional Submissions for the new employer, then You agree to sign a new Agreement
and secure permission from the new employer before Submitting those Submissions.
Licenses.

Copyright License. You grant Microsoft, and those who receive the Submission directly or
indirectly from Microsoft, a perpetual, worldwide, non-exclusive, royalty-free, irrevocable license in the
Submission to reproduce, prepare derivative works of, publicly display, publicly perform, and distribute
the Submission and such derivative works, and to sublicense any or all of the foregoing rights to third
parties.
Patent License. You grant Microsoft, and those who receive the Submission directly or
indirectly from Microsoft, a perpetual, worldwide, non-exclusive, royalty-free, irrevocable license under
Your patent claims that are necessarily infringed by the Submission or the combination of the
Submission with the Project to which it was Submitted to make, have made, use, offer to sell, sell and
import or otherwise dispose of the Submission alone or with the Project.
Other Rights Reserved. Each party reserves all rights not expressly granted in this Agreement.
No additional licenses or rights whatsoever (including, without limitation, any implied licenses) are
granted by implication, exhaustion, estoppel or otherwise.

Representations and Warranties. You represent that You are legally entitled to grant the above
licenses. You represent that each of Your Submissions is entirely Your original work (except as You may
have disclosed under Section 3). You represent that You have secured permission from Your employer to
make the Submission in cases where Your Submission is made in the course of Your work for Your
employer or Your employer has intellectual property rights in Your Submission by contract or applicable
law. If You are signing this Agreement on behalf of Your employer, You represent and warrant that You
have the necessary authority to bind the listed employer to the obligations contained in this Agreement.
You are not expected to provide support for Your Submission, unless You choose to do so. UNLESS
REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, AND EXCEPT FOR THE WARRANTIES
EXPRESSLY STATED IN SECTIONS 3, 4, AND 6, THE SUBMISSION PROVIDED UNDER THIS AGREEMENT IS
PROVIDED WITHOUT WARRANTY OF ANY KIND, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTY OF
NONINFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
Notice to Microsoft. You agree to notify Microsoft in writing of any facts or circumstances of which
You later become aware that would make Your representations in this Agreement inaccurate in any
respect.
Information about Submissions. You agree that contributions to Projects and information about
contributions may be maintained indefinitely and disclosed publicly, including Your name and other
information that You submit with Your Submission.
Governing Law/Jurisdiction. This Agreement is governed by the laws of the State of Washington, and
the parties consent to exclusive jurisdiction and venue in the federal courts sitting in King County,
Washington, unless no federal subject matter jurisdiction exists, in which case the parties consent to
exclusive jurisdiction and venue in the Superior Court of King County, Washington. The parties waive all
defenses of lack of personal jurisdiction and forum non-conveniens.
Entire Agreement/Assignment. This Agreement is the entire agreement between the parties, and
supersedes any and all prior agreements, understandings or communications, written or oral, between
the parties relating to the subject matter hereof. This Agreement may be assigned by Microsoft.

mattf

this is looking good. i've added some comments and questions.

python/semantic_kernel/connectors/ai/nvidia/__init__.py

...ic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

mattf · 2025-02-05T14:20:04Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_handler.py

+        """Send a request to the OpenAI embeddings endpoint."""
+        try:
+            # exclude input-type from main body
+            response = await self.client.embeddings.create(**settings.prepare_settings_dict(exclude="input_type"))


why exclude input_type?

because openai client does not allow input_type parameter, so I excluded it from main dict and added in extra body

mattf · 2025-02-05T14:21:38Z

...ic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

+        As well as any fields that are None.
+        """
+        return self.model_dump(
+            exclude={"service_id", "extension_data", "structured_json_response", "input_type"},


does the input_type need to be passed as extra_body

mattf · 2025-02-05T14:32:56Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_text_embedding.py

+        for i in range(0, len(texts), batch_size):
+            batch = texts[i : i + batch_size]
+            settings.input = batch
+            raw_embedding = await self._send_request(settings=settings)


it looks like batch_size is controlling the number of texts that are sent for embedding in a single call to the service.

each of those batches can also be sent in parallel.

indeed, batch size refers to how many characters are included in each call, if this can be parallelized, please do, also moving the actual embedding calls here makes this simpler (vs the handler, see earlier comment)

mattf · 2025-02-05T14:33:50Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_handler.py

+    def to_dict(self) -> dict[str, str]:
+        """Create a dict of the service settings."""
+        client_settings = {
+            "api_key": self.client.api_key,


what are the security implications of including the api_key here?

mattf · 2025-02-05T14:35:09Z

python/semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py

+                (Env var NVIDIA_BASE_URL)
+    - chat_model_id: The NVIDIA chat model ID to use see https://docs.api.nvidia.com/nim/reference/llm-apis.
+        (Env var NVIDIA_CHAT_MODEL_ID)
+    - text_model_id: str | None - The NVIDIA text model ID to use, for example, nvidia/nemotron-4-340b-reward.


there are also vision language models (VLMs), which take text or images as input and produce text

Yes will add when working on vlm support

those models are supported with the ChatCompletionClientBase as well

python/tests/unit/connectors/ai/nvidia/services/test_nvidia_text_embedding.py

mattf · 2025-02-05T14:37:18Z

python/tests/unit/connectors/ai/nvidia/services/test_nvidia_text_embedding.py

+        model=ai_model_id,
+        dimensions=embedding_dimensions,
+        encoding_format="float",
+        extra_body={"input_type": "passage"},


this demonstrates there are two ways to pass input_type. i suggest only providing one.

I think this is right, as I am validating the request bosy and in that input_type goes in extra_body

…nto raspawar/nvidia-chat-compl

eavanvalkenburg

Left a bunch of comments, most important is to simplify this by a lot!

eavanvalkenburg · 2025-02-10T08:59:16Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_model_types.py

+class NvidiaModelTypes(Enum):
+    """Nvidia model types, can be text, chat or embedding."""
+
+    TEXT = "text"


if we don't support these modalities, they shouldn't be in here (yet)

eavanvalkenburg · 2025-02-10T09:25:22Z

...ic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

+    model: str = None
+    encoding_format: Literal["float", "base64"] | None = "float"  # default to float
+    truncate: Literal[None, "NONE", "START", "END"] | None = None
+    input_type: Literal["passage", "query"] | None = "passage"  # default to passage


it is preferred to set defaults to None if the service itself has default values, that way we don't get out of sync with the default documented by services

eavanvalkenburg · 2025-02-10T09:25:53Z

...ic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

+    """Specific settings for the text embedding endpoint."""
+
+    input: str | list[str] | list[int] | list[list[int]] | None = None
+    model: str = None


model is a reserved term for pydantic, please use a alternative with a Alias, for instance for openai we use:
ai_model_id: Annotated[str | None, Field(serialization_alias="model")] = None

eavanvalkenburg · 2025-02-10T09:27:44Z

...ic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

+class NvidiaEmbeddingPromptExecutionSettings(NvidiaPromptExecutionSettings):
+    """Settings for NVIDIA embedding prompt execution."""
+
+    """Specific settings for the text embedding endpoint."""


please combine into one docstring

eavanvalkenburg · 2025-02-10T09:29:23Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_handler.py

+RESPONSE_TYPE = Union[list[Any],]
+
+
+class NvidiaHandler(KernelBaseModel, ABC):


is the goal to also add chat and or text completions or other modalities? If not, or if only one other, then we don't need all this extra stuff that we have for OpenAI since that support a lot of things and has 2 configs (azure and openai), we could simplify this PR by a lot and only extend the pieces that are shared later on.

eavanvalkenburg · 2025-02-10T09:30:20Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_text_embedding.py

+        # move input_type to extra-body
+        if not settings.extra_body:
+            settings.extra_body = {}
+        settings.extra_body.setdefault("input_type", settings.input_type)


can't we move this logic into the prepare_settings_dict?

eavanvalkenburg · 2025-02-10T09:31:51Z

python/semantic_kernel/connectors/ai/nvidia/services/nvidia_text_embedding.py

+        for i in range(0, len(texts), batch_size):
+            batch = texts[i : i + batch_size]
+            settings.input = batch
+            raw_embedding = await self._send_request(settings=settings)


indeed, batch size refers to how many characters are included in each call, if this can be parallelized, please do, also moving the actual embedding calls here makes this simpler (vs the handler, see earlier comment)

eavanvalkenburg · 2025-02-10T09:33:34Z

python/semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py

+                and more information refer https://docs.api.nvidia.com/nim/reference/
+                use endpoint if you only want to supply the endpoint.
+                (Env var NVIDIA_BASE_URL)
+    - chat_model_id: The NVIDIA chat model ID to use see https://docs.api.nvidia.com/nim/reference/llm-apis.


since chat and text are not supported yet, please remove.

eavanvalkenburg · 2025-02-10T09:34:36Z

python/semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py

+                (Env var NVIDIA_BASE_URL)
+    - chat_model_id: The NVIDIA chat model ID to use see https://docs.api.nvidia.com/nim/reference/llm-apis.
+        (Env var NVIDIA_CHAT_MODEL_ID)
+    - text_model_id: str | None - The NVIDIA text model ID to use, for example, nvidia/nemotron-4-340b-reward.


those models are supported with the ChatCompletionClientBase as well

nvidia embedding connector code

5b82ab1

markwallace-microsoft added the python Pull requests for the Python Semantic Kernel label Feb 5, 2025

github-actions bot changed the title ~~Nvidia Embedding Connector~~ Python: Nvidia Embedding Connector Feb 5, 2025

mattf reviewed Feb 5, 2025

View reviewed changes

add embedding to all-settings

b14665f

markwallace-microsoft added the documentation label Feb 5, 2025

mattf reviewed Feb 5, 2025

View reviewed changes

raspawar added 2 commits February 6, 2025 16:28

Merge branch 'main' of https://github.com/microsoft/semantic-kernel i…

1b3d26c

…nto raspawar/nvidia-chat-compl

review changes

4e9e423

raspawar marked this pull request as ready for review February 6, 2025 11:12

raspawar requested a review from a team as a code owner February 6, 2025 11:12

raspawar mentioned this pull request Feb 6, 2025

Python: NVDIA NIM connector #10325

Open

10 tasks

raspawar marked this pull request as draft February 6, 2025 16:26

eavanvalkenburg reviewed Feb 10, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Python: Nvidia Embedding Connector #10410

Python: Nvidia Embedding Connector #10410

raspawar commented Feb 5, 2025

mattf Feb 5, 2025

microsoft-github-policy-service bot commented Feb 5, 2025

Contribution License Agreement

mattf left a comment

mattf Feb 5, 2025

raspawar Feb 6, 2025

mattf Feb 5, 2025

mattf Feb 5, 2025

eavanvalkenburg Feb 10, 2025

mattf Feb 5, 2025

mattf Feb 5, 2025

raspawar Feb 6, 2025 •

edited

Loading

eavanvalkenburg Feb 10, 2025

mattf Feb 5, 2025

raspawar Feb 6, 2025

eavanvalkenburg left a comment

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025

eavanvalkenburg Feb 10, 2025


		"""Specific settings for the text embedding endpoint."""

		input: str \| list[str] \| list[int] \| list[list[int]] \| None = None

		RESPONSE_TYPE = Union[list[Any],]


		class NvidiaHandler(KernelBaseModel, ABC):

Python: Nvidia Embedding Connector #10410

Are you sure you want to change the base?

Python: Nvidia Embedding Connector #10410

Conversation

raspawar commented Feb 5, 2025

Nvidia Embedding Connector

Description

Contribution Checklist

Choose a reason for hiding this comment

microsoft-github-policy-service bot commented Feb 5, 2025

Contribution License Agreement

mattf left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

raspawar Feb 6, 2025 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

eavanvalkenburg left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

raspawar Feb 6, 2025 •

edited

Loading