Skip to content

support all text model #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
johnnywale merged 1 commit into from
Jan 11, 2026
Merged

support all text model #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
221 changes: 210 additions & 11 deletions .github/workflows/build-on-release.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,21 +69,222 @@ jobs:
strategy:
matrix:
include:
- variant: models--Qdrant--multilingual-e5-large-onnx
model_type: multilingual-e5-large
platform: linux/amd64
- variant: models--Xenova--all-mpnet-base-v2
model_type: all-mpnet-base-v2
model_id: Xenova/all-mpnet-base-v2
dimension: 768
platform: linux/amd64
- variant: models--Xenova--bge-base-en-v1.5
model_type: bge-base-en-v1.5
- variant: models--Alibaba-NLP--gte-large-en-v1.5
model_type: gte-large-en-v1.5
model_id: Alibaba-NLP/gte-large-en-v1.5
dimension: 1024
platform: linux/amd64
- variant: models--jinaai--jina-embeddings-v2-base-code
model_type: jina-embeddings-v2-base-code
model_id: jinaai/jina-embeddings-v2-base-code
dimension: 768
platform: linux/amd64
- variant: models--Xenova--bge-large-en-v1.5
model_type: bge-large-en-v1.5
model_id: Xenova/bge-large-en-v1.5
dimension: 1024
platform: linux/amd64
- variant: models--intfloat--multilingual-e5-small
model_type: multilingual-e5-small
model_id: intfloat/multilingual-e5-small
dimension: 384
platform: linux/amd64
- variant: models--mixedbread-ai--mxbai-embed-large-v1
model_type: mxbai-embed-large-v1
model_id: mixedbread-ai/mxbai-embed-large-v1
dimension: 1024
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-m-long
model_type: snowflake-arctic-embed-m-long
model_id: snowflake/snowflake-arctic-embed-m-long
dimension: 768
platform: linux/amd64
- variant: models--nomic-ai--nomic-embed-text-v1.5
model_type: nomic-embed-text-v1.5
model_id: nomic-ai/nomic-embed-text-v1.5
dimension: 768
platform: linux/amd64
- variant: models--Snowflake--snowflake-arctic-embed-m
model_type: snowflake-arctic-embed-m
model_id: Snowflake/snowflake-arctic-embed-m
dimension: 768
platform: linux/amd64
- variant: models--Xenova--bge-base-en-v1.5
model_type: bge-base-en-v1.5
model_id: Xenova/bge-base-en-v1.5
dimension: 768
platform: linux/amd64
- variant: models--Xenova--bge-small-en-v1.5
model_type: bge-small-en-v1.5
model_id: Xenova/bge-small-en-v1.5
dimension: 384
platform: linux/amd64
- variant: models--mixedbread-ai--mxbai-embed-large-v1
model_type: mxbai-embed-large-v1
model_id: mixedbread-ai/mxbai-embed-large-v1
dimension: 1024
platform: linux/amd64
- variant: models--onnx-community--embeddinggemma-300m-ONNX
model_type: embeddinggemma-300m-ONNX
model_id: onnx-community/embeddinggemma-300m-ONNX
dimension: 768
platform: linux/amd64
- variant: models--Qdrant--multilingual-e5-large-onnx
model_type: multilingual-e5-large-onnx
model_id: Qdrant/multilingual-e5-large-onnx
dimension: 1024
platform: linux/amd64
- variant: models--Qdrant--paraphrase-multilingual-MiniLM-L12-v2-onnx-Q
model_type: paraphrase-multilingual-MiniLM-L12-v2-onnx-Q
model_id: Qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q
dimension: 384
platform: linux/amd64
- variant: models--Xenova--paraphrase-multilingual-mpnet-base-v2
model_type: paraphrase-multilingual-mpnet-base-v2
model_id: Xenova/paraphrase-multilingual-mpnet-base-v2
dimension: 768
platform: linux/amd64
- variant: models--lightonai--modernbert-embed-large
model_type: modernbert-embed-large
model_id: lightonai/modernbert-embed-large
dimension: 1024
platform: linux/amd64
- variant: models--Xenova--all-MiniLM-L12-v2
model_type: all-MiniLM-L12-v2
model_id: Xenova/all-MiniLM-L12-v2
dimension: 384
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-m-long
model_type: snowflake-arctic-embed-m-long
model_id: snowflake/snowflake-arctic-embed-m-long
dimension: 768
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-l
model_type: snowflake-arctic-embed-l
model_id: snowflake/snowflake-arctic-embed-l
dimension: 1024
platform: linux/amd64
- variant: models--Xenova--bge-large-zh-v1.5
model_type: bge-large-zh-v1.5
model_id: Xenova/bge-large-zh-v1.5
dimension: 1024
platform: linux/amd64
- variant: models--Qdrant--all-MiniLM-L6-v2-onnx
model_type: all-MiniLM-L6-v2-onnx
model_id: Qdrant/all-MiniLM-L6-v2-onnx
dimension: 384
platform: linux/amd64
- variant: models--intfloat--multilingual-e5-base
model_type: multilingual-e5-base
model_id: intfloat/multilingual-e5-base
dimension: 768
platform: linux/amd64
- variant: models--Alibaba-NLP--gte-large-en-v1.5
model_type: gte-large-en-v1.5
model_id: Alibaba-NLP/gte-large-en-v1.5
dimension: 1024
platform: linux/amd64
- variant: models--Snowflake--snowflake-arctic-embed-m
model_type: snowflake-arctic-embed-m
model_id: Snowflake/snowflake-arctic-embed-m
dimension: 768
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-xs
model_type: snowflake-arctic-embed-xs
model_id: snowflake/snowflake-arctic-embed-xs
dimension: 384
platform: linux/amd64
- variant: models--BAAI--bge-m3
model_type: bge-m3
model_id: BAAI/bge-m3
dimension: 1024
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-s
model_type: snowflake-arctic-embed-s
model_id: snowflake/snowflake-arctic-embed-s
dimension: 384
platform: linux/amd64
- variant: models--Qdrant--clip-ViT-B-32-text
model_type: clip-ViT-B-32-text
model_id: Qdrant/clip-ViT-B-32-text
dimension: 512
platform: linux/amd64
- variant: models--nomic-ai--nomic-embed-text-v1
model_type: nomic-embed-text-v1
model_id: nomic-ai/nomic-embed-text-v1
dimension: 768
platform: linux/amd64
- variant: models--Xenova--all-MiniLM-L6-v2
model_type: all-MiniLM-L6-v2
model_id: Xenova/all-MiniLM-L6-v2
dimension: 384
platform: linux/amd64
- variant: models--Alibaba-NLP--gte-base-en-v1.5
model_type: gte-base-en-v1.5
model_id: Alibaba-NLP/gte-base-en-v1.5
dimension: 768
platform: linux/amd64
- variant: models--Xenova--all-MiniLM-L12-v2
model_type: all-MiniLM-L12-v2
model_id: Xenova/all-MiniLM-L12-v2
dimension: 384
platform: linux/amd64
- variant: models--Qdrant--bge-base-en-v1.5-onnx-Q
model_type: bge-base-en-v1.5-onnx-Q
model_id: Qdrant/bge-base-en-v1.5-onnx-Q
dimension: 768
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-s
model_type: snowflake-arctic-embed-s
model_id: snowflake/snowflake-arctic-embed-s
dimension: 384
platform: linux/amd64
- variant: models--Qdrant--bge-large-en-v1.5-onnx-Q
model_type: bge-large-en-v1.5-onnx-Q
model_id: Qdrant/bge-large-en-v1.5-onnx-Q
dimension: 1024
platform: linux/amd64
- variant: models--Qdrant--bge-small-en-v1.5-onnx-Q
model_type: bge-small-en-v1.5-onnx-Q
model_id: Qdrant/bge-small-en-v1.5-onnx-Q
dimension: 384
platform: linux/amd64
- variant: models--Alibaba-NLP--gte-base-en-v1.5
model_type: gte-base-en-v1.5
model_id: Alibaba-NLP/gte-base-en-v1.5
dimension: 768
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-xs
model_type: snowflake-arctic-embed-xs
model_id: snowflake/snowflake-arctic-embed-xs
dimension: 384
platform: linux/amd64
- variant: models--snowflake--snowflake-arctic-embed-l
model_type: snowflake-arctic-embed-l
model_id: snowflake/snowflake-arctic-embed-l
dimension: 1024
platform: linux/amd64
- variant: models--Xenova--paraphrase-multilingual-MiniLM-L12-v2
model_type: paraphrase-multilingual-MiniLM-L12-v2
model_id: Xenova/paraphrase-multilingual-MiniLM-L12-v2
dimension: 384
platform: linux/amd64
- variant: models--nomic-ai--nomic-embed-text-v1.5
model_type: nomic-embed-text-v1.5
model_id: nomic-ai/nomic-embed-text-v1.5
dimension: 768
platform: linux/amd64
- variant: models--Xenova--bge-small-zh-v1.5
model_type: bge-small-zh-v1.5
model_id: Xenova/bge-small-zh-v1.5
dimension: 512
platform: linux/amd64

steps:
- name: Checkout code
uses: actions/checkout@v4
Expand Down Expand Up @@ -119,22 +320,20 @@ jobs:
with:
images: ${{ secrets.DOCKER_USERNAME }}/serverless-vectorizer
tags: |
type=raw,value=${{ steps.get_tag.outputs.tag_name }}-${{ matrix.model_type }}
type=raw,value=latest-${{ matrix.model_type }}
type=raw,value=${{ matrix.model_type }}
type=raw,value=${{ steps.get_tag.outputs.tag_name }}-${{ matrix.model_id }}
type=raw,value=latest-${{ matrix.model_id }}
type=raw,value=${{ matrix.model_id }}

- name: Build and push variant image
uses: docker/build-push-action@v6
with:

file: Dockerfile.variant
platforms: ${{ matrix.platform }}
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
build-args: |
BASE_IMAGE=${{ secrets.DOCKER_USERNAME }}/serverless-vectorizer:base-${{ steps.get_tag.outputs.tag_name }}
VARIANT=${{ matrix.variant }}
MODEL_TYPE=${{ matrix.model_type }}
MODEL_ID=${{ matrix.model_id }}
cache-from: type=gha
cache-to: type=gha,mode=max
4 changes: 4 additions & 0 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,10 @@ path = "src/bin/preload.rs"
name = "embed-cli"
path = "src/bin/cli.rs"

[[bin]]
name = "list-models"
path = "src/bin/list-models.rs"

[profile.release]
opt-level = "z"
lto = true
Expand Down
8 changes: 3 additions & 5 deletions Dockerfile.variant
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,12 +2,10 @@
ARG BASE_IMAGE
FROM ${BASE_IMAGE}

ARG VARIANT
ARG MODEL_TYPE
ARG MODEL_ID

ENV MODEL_VARIANT=${VARIANT}
ENV MODEL_TYPE=${MODEL_TYPE}
ENV MODEL_ID=${MODEL_ID}

RUN cd ${LAMBDA_TASK_ROOT}/ && ${LAMBDA_RUNTIME_DIR}/preload ${MODEL_TYPE}
RUN cd ${LAMBDA_TASK_ROOT}/ && ${LAMBDA_RUNTIME_DIR}/preload ${MODEL_ID}

CMD [ "bootstrap" ]
Loading