jeff3071 opened a new pull request, #72002:
URL: https://github.com/apache/airflow/pull/72002
<!-- SPDX-License-Identifier: Apache-2.0
https://www.apache.org/licenses/LICENSE-2.0 -->
<!--
Thank you for contributing!
Please provide above a brief description of the changes made in this pull
request.
Write a good git commit message following this guide:
https://chris.beams.io/posts/git-commit/
Please make sure that your code changes are covered with tests.
And in case of new features or big changes remember to adjust the
documentation.
For user-facing UI changes, please attach before/after screenshots (or a
short
screen recording) so reviewers can assess the visual impact.
Feel free to ping (in general) for the review if you do not see reaction for
a few days
(72 Hours is the minimum reaction time you can expect from volunteers) - we
sometimes miss notifications.
In case of an existing issue, reference it using one of the following:
* closes: #ISSUE
* related: #ISSUE
-->
## Why
Embedding model options such as custom dimensions cannot currently be
configured in common AI hooks and operators.
Following the OpenAI provider design, these options are passed explicitly
instead of through connection `extra`.
## What
- Add `embedding_kwargs` to LangChain and LlamaIndex hooks.
- Forward it through LlamaIndex embedding and retrieval operators.
## Test
Use testing dag below and self-host embedding model.
```python
import math
from airflow.providers.common.ai.operators.llamaindex_embedding import
LlamaIndexEmbeddingOperator
from airflow.providers.common.compat.sdk import dag, task
@task
def verify_embeddings(result: dict) -> None:
"""Verify that vLLM produced one finite 128-dimensional vector per
document."""
if result["document_count"] != 2 or result["chunk_count"] != 2:
raise ValueError(
f"Expected two documents and two chunks, got
{result['document_count']} documents "
f"and {result['chunk_count']} chunks"
)
vectors = [chunk["vector"] for chunk in result["chunks"]]
dimensions = {len(vector) for vector in vectors}
if dimensions != {128}:
raise ValueError(f"Expected 128-dimensional vectors, got
{sorted(dimensions)}")
if not all(math.isfinite(value) for vector in vectors for value in
vector):
raise ValueError("Embedding response contains non-finite values")
@dag(schedule=None, tags=["example", "llamaindex", "vllm"])
def example_llamaindex_vllm_embedding():
embed = LlamaIndexEmbeddingOperator(
task_id="generate_embeddings",
documents=[
{
"text": "Apache Airflow orchestrates data workflows.",
"metadata": {"source": "airflow"},
},
{
"text": "Qwen3-Embedding produces vector representations of
text.",
"metadata": {"source": "qwen"},
},
],
embed_model="text-embedding-3-small",
embed_conn_id="llamaindex_vllm",
embedding_kwargs={"dimensions": 128},
chunk_size=128,
chunk_overlap=16,
)
verify_embeddings(embed.output)
example_llamaindex_vllm_embedding()
```
vllm command
```
vllm serve Qwen/Qwen3-Embedding-0.6B --runner pooling --host 0.0.0.0
--port 8000 --api-key EMPTY --max-model-len 1024
--gpu-memory-utilization 0.5 --hf-overrides '{"is_matryoshka":true}'
--served-model-name text-embedding-3-small
```
> Use text-embedding-3-small as the served model name because
`LlamaIndexHook` validates the model name.
---
##### Was generative AI tooling used to co-author this PR?
<!--
If generative AI tooling has been used in the process of authoring this PR,
please
change below checkbox to `[X]` followed by the name of the tool, uncomment
the "Generated-by".
-->
- [x] Yes (Codex:GPT-5.6-sol)
Generated-by: (Codex:GPT-5.6-sol) following [the
guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions)
<!--
Generated-by: [Tool Name] following [the
guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions)
-->
---
* Read the **[Pull Request
Guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#pull-request-guidelines)**
for more information. Note: commit author/co-author name and email in commits
become permanently public when merged.
* For fundamental code changes, an Airflow Improvement Proposal
([AIP](https://cwiki.apache.org/confluence/display/AIRFLOW/Airflow+Improvement+Proposals))
is needed.
* When adding dependency, check compliance with the [ASF 3rd Party License
Policy](https://www.apache.org/legal/resolved.html#category-x).
* For significant user-facing changes create newsfragment:
`{pr_number}.significant.rst`, in
[airflow-core/newsfragments](https://github.com/apache/airflow/tree/main/airflow-core/newsfragments).
You can add this file in a follow-up commit after the PR is created so you
know the PR number.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
