Skip to content

Added Gemini Image Captioning to Docker Compose files #267

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

Open
adsarver wants to merge 11 commits into
base: develop
Choose a base branch
from
Open

Added Gemini Image Captioning to Docker Compose files #267

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
22811bd
Added the gemini component
Jun 6, 2025
0355e27
Merge branch develop into kburkewv/feat/gemini-detection
Jun 17, 2025
35df143
Merge remote-tracking branch 'origin/develop' into kburkewv/feat/gemi…
sashearing Jan 9, 2026
1d5e111
remove detection from components base in gemini detection definition
sashearing Jan 9, 2026
101c5b4
Merge remote-tracking branch 'origin/develop' into adsarver/feat/gemi…
adsarver Jul 8, 2026
9dfeafd
Added vllm and params to the summarization compose
adsarver Jul 9, 2026
0691ddd
Added gemini video sum to tests compose
adsarver Jul 9, 2026
0611e3a
Added gpu and healthcheck to vllm server, added vllm test server
adsarver Jul 10, 2026
ca9cff9
Jenkins fix
adsarver Jul 13, 2026
75a936a
Updated summarization server to not force a specific gpu, like speech…
adsarver Jul 21, 2026
dc746ad
Added image captioning to compose file
adsarver Aug 10, 2026
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
20 changes: 20 additions & 0 deletions docker-compose.components.test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,26 @@ services:
east-text-detection:
<<: *test-args

gemini-video-summarization:
<<: *test-args

gemini-video-summarization-vllm-tests:
image: ${REGISTRY}openmpf_gemini_video_summarization_tests:${TAG}
build:
context: ${OPENMPF_PROJECTS_PATH}/openmpf-components/python/GeminiVideoSummarization
target: vllm-tests
args:
BUILD_REGISTRY: ${REGISTRY}
BUILD_TAG: ${TAG}
RUN_TESTS: 'true'
environment:
RUN_VLLM_TESTS: 'true'
GEMINI_TEST_OPENAI_BASE_URL: http://gemini-video-summarization-server:8000/v1
GEMINI_TEST_MODEL_NAME: ${GEMINI_MODEL_NAME:-google/gemma-4-12B-it}
depends_on:
gemini-video-summarization-server:
condition: service_healthy

mog-motion-detection:
<<: *test-args

Expand Down
96 changes: 96 additions & 0 deletions docker-compose.components.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,6 +131,102 @@ services:
resources:
limits:
cpus: "2.0"

gemini-image-captioning:
<<: *component-base
image: ${REGISTRY}openmpf_gemini_image_captioning:${TAG}
build:
context: ${OPENMPF_PROJECTS_PATH}/openmpf-components/python/GeminiImageCaptioning
args:
BUILD_REGISTRY: ${REGISTRY}
BUILD_TAG: ${TAG}
environment:
<<: *common-env-vars
MPF_PROP_API: ${GEMINI_IMAGE_CAPTIONING_API:-OpenAI}
MPF_PROP_OPENAI_BASE_URL: ${GEMINI_IMAGE_CAPTIONING_OPENAI_BASE_URL:-http://gemini-image-captioning-server:8000/v1}
MPF_PROP_MODEL_NAME: ${GEMINI_IMAGE_CAPTIONING_MODEL_NAME:-google/gemma-4-12B-it}
MPF_PROP_APPLICATION_CREDENTIALS: ${GEMINI_IMAGE_CAPTIONING_APPLICATION_CREDENTIALS:-}
MPF_PROP_OPENAI_REQUEST_TIMEOUT_SECONDS: ${GEMINI_IMAGE_CAPTIONING_OPENAI_REQUEST_TIMEOUT_SECONDS:-600}
depends_on:
workflow-manager:
condition: service_started
gemini-image-captioning-server:
condition: service_healthy

gemini-image-captioning-server:
image: ${REGISTRY}openmpf_gemini_image_captioning_server:${TAG}
build:
context: ${OPENMPF_PROJECTS_PATH}/openmpf-components/python/GeminiImageCaptioning
dockerfile: Dockerfile.vllm
ipc: host
volumes:
- type: bind
source: ${GEMINI_IMAGE_CAPTIONING_HF_CACHE:-${HOME}/.cache/huggingface}
target: /root/.cache/huggingface
healthcheck:
test: ["CMD", "curl", "--fail", "--silent", "--show-error", "--max-time", "5", "http://localhost:8000/health"]
interval: 10s
timeout: 6s
retries: 120
start_period: 30s
deploy:
mode: global
# resources:
# reservations:
# devices:
# - driver: nvidia
# device_ids: ['0']
# capabilities: [gpu]


gemini-video-summarization:
<<: *component-base
image: ${REGISTRY}openmpf_gemini_video_summarization:${TAG}
build:
context: ${OPENMPF_PROJECTS_PATH}/openmpf-components/python/GeminiVideoSummarization
args:
BUILD_REGISTRY: ${REGISTRY}
BUILD_TAG: ${TAG}
environment:
<<: *common-env-vars
MPF_PROP_API: ${GEMINI_API:-OpenAI}
MPF_PROP_OPENAI_BASE_URL: ${GEMINI_OPENAI_BASE_URL:-http://gemini-video-summarization-server:8000/v1}
MPF_PROP_MODEL_NAME: ${GEMINI_MODEL_NAME:-google/gemma-4-12B-it}
MPF_PROP_APPLICATION_CREDENTIALS: ${GEMINI_APPLICATION_CREDENTIALS:-}
MPF_PROP_ENABLE_TIMELINE: ${GEMINI_ENABLE_TIMELINE:-0}
MPF_PROP_ENABLE_AUDIO: ${GEMINI_ENABLE_AUDIO:-1}
MPF_PROP_PROCESS_FPS: ${GEMINI_PROCESS_FPS:-1.0}
MPF_PROP_OPENAI_REQUEST_TIMEOUT_SECONDS: ${GEMINI_OPENAI_REQUEST_TIMEOUT_SECONDS:-600}
depends_on:
workflow-manager:
condition: service_started
gemini-video-summarization-server:
condition: service_healthy

gemini-video-summarization-server:
image: ${REGISTRY}openmpf_gemini_video_summarization_server:${TAG}
build:
context: ${OPENMPF_PROJECTS_PATH}/openmpf-components/python/GeminiVideoSummarization
dockerfile: Dockerfile.vllm
ipc: host
volumes:
- type: bind
source: ${GEMINI_HF_CACHE:-${HOME}/.cache/huggingface}
target: /root/.cache/huggingface
healthcheck:
test: ["CMD", "curl", "--fail", "--silent", "--show-error", "--max-time", "5", "http://localhost:8000/health"]
interval: 10s
timeout: 6s
retries: 120
start_period: 30s
deploy:
mode: global
# resources:
# reservations:
# devices:
# - driver: nvidia
# device_ids: ['0']
# capabilities: [gpu]

fasttext-language-detection:
<<: *component-base
Expand Down