Sign inSign up

mongodb/apix_test:voyage-4-nano-20260603-alpha

Integration & delivery
Databases & storage
Manifest digest

sha256:26ed9245c826fec63884e2406609e406ed437c01e881c18aec1f0edf2cc800bc

OS/ARCH

linux/arm64

Compressed size

1.05 GB

Last pushed

19 days by fmenezesmongodb

Type

Image

Manifest digest

sha256:26ed9245c826fec63884e2406609e406ed437c01e881c18aec1f0edf2cc800bc

Image Layers

1ARG RELEASE0 B
2ARG LAUNCHPAD_BUILD_ARCH0 B
3LABEL org.opencontainers.image.version=24.040 B
4ADD file ... in / 28.56 MB
5CMD ["/bin/bash"]0 B
6ENV DEBIAN_FRONTEND=noninteractive0 B
7RUN /bin/sh -c apt-get update84.32 MB
8ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python0 B
9COPY /opt/uv/python /opt/uv/python # buildkit20.96 MB
10ENV VIRTUAL_ENV=/opt/venvs/voyage-ai0 B
11COPY /opt/venvs/voyage-ai /opt/venvs/voyage-ai # buildkit416.61 MB
12ENV PATH=/opt/venvs/voyage-ai/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B
13WORKDIR /app93 B
14ARG SERVER__PORT=80800 B
15ARG SERVER__MAX_REQUESTS=00 B
16ARG SERVER__MAX_REQUESTS_JITTER=00 B
17ARG SERVER__WORKERS=10 B
18ARG SERVER__TIMEOUT=3000 B
19ARG SERVER__GRACEFUL_TIMEOUT=250 B
20ARG SERVER__WRITABLE_PATH_PREFIX=/tmp0 B
21ARG SERVER__OTEL_SERVICE_NAME=0 B
22ARG SERVER__INFO_PATH=/info0 B
23ARG SERVER__STARTUP_PATH=/health/startup0 B
24ARG SERVER__READINESS_PATH=/health/readiness0 B
25ARG SERVER__LIVENESS_PATH=/health/liveness0 B
26ARG SERVER__DOCS_PATH=0 B
27ARG SERVER__OPENAPI_PATH=/openapi.json0 B
28ARG SERVER__EMBEDDINGS_PATH=/embeddings0 B
29ARG SERVER__CONTEXTUALIZED_EMBEDDINGS_PATH=/contextualizedembeddings0 B
30ARG SERVER__MULTIMODAL_EMBEDDINGS_PATH=/multimodalembeddings0 B
31ARG SERVER__RERANK_PATH=/rerank0 B
32ARG SERVER__TLS__ENABLED=false0 B
33ARG SERVER__TLS__CERTFILE=0 B
34ARG SERVER__TLS__KEYFILE=0 B
35ARG SERVER__TLS__CA_CERTS=0 B
36ARG SERVER__ERROR_RESPONSE_THROTTLING__ENABLED=true0 B
37ARG SERVER__ERROR_RESPONSE_THROTTLING__WINDOW_SECONDS=10.00 B
38ARG SERVER__ERROR_RESPONSE_THROTTLING__MAX_ERRORS_PER_WINDOW=500 B
39ARG SERVER__ERROR_RESPONSE_THROTTLING__DELAY_SECONDS=1.00 B
40ARG SERVER__ERROR_RESPONSE_THROTTLING__STATUS_CODES=[429, 500, 503, 504]0 B
41ARG SERVER__METRICS__ENABLED=false0 B
42ARG SERVER__METRICS__PATH=/metrics0 B
43ARG SERVER__METRICS__PORT=0 B
44ARG SERVER__CORRECTNESS__CHECK_ON_STARTUP=true0 B
45ARG SERVER__CORRECTNESS__BASE_DIR=/app/correlation0 B
46ARG SERVER__CORRECTNESS__CONCURRENCY=80 B
47ARG SERVER__CORRECTNESS__RESULT_WAIT_TIMEOUT=600.00 B
48ARG DATA_PARALLEL__ENABLED=false0 B
49ARG DATA_PARALLEL__NUM_WORKERS=auto0 B
50ARG DATA_PARALLEL__LOAD_BALANCING_STRATEGY=token_aware0 B
51ARG DATA_PARALLEL__WORKER_INIT_TIMEOUT=600.00 B
52ARG DATA_PARALLEL__WORKER_EXECUTION_TIMEOUT=30.00 B
53ARG DATA_PARALLEL__WORKER_QUEUE_MAXSIZE=1000 B
54ARG DATA_PARALLEL__BATCHING__STRATEGY=time_window0 B
55ARG DATA_PARALLEL__BATCHING__MAX_WAIT_TIME=0.010 B
56ARG DATA_PARALLEL__BATCHING__MAX_QUEUE_SIZE=20000 B
57ARG DATA_PARALLEL__HEALTH_MONITORING__CHECK_INTERVAL=5.00 B
58ARG DATA_PARALLEL__HEALTH_MONITORING__MAX_CONSECUTIVE_TIMEOUTS=30 B
59ARG DATA_PARALLEL__HEALTH_MONITORING__ENABLE_ACTIVE_CHECKS=false0 B
60ARG DATA_PARALLEL__HEALTH_MONITORING__ACTIVE_CHECK_INTERVAL=600 B
61ARG DATA_PARALLEL__HEALTH_MONITORING__ACTIVE_CHECK_TIMEOUT=50 B
62ARG DATA_PARALLEL__HEALTH_MONITORING__MAX_RESTART_ATTEMPTS=30 B
63ARG DATA_PARALLEL__HEALTH_MONITORING__RESTART_COOLDOWN=30.00 B
64ARG CUSTOM_VLLM_PLUGINS=Qwen3ForVoyageEmbedding0 B
65ENV SERVER__PORT=80800 B
66ENV SERVER__MAX_REQUESTS=00 B
67ENV SERVER__MAX_REQUESTS_JITTER=00 B
68ENV SERVER__WORKERS=10 B
69ENV SERVER__TIMEOUT=3000 B
70ENV SERVER__GRACEFUL_TIMEOUT=250 B
71ENV SERVER__WRITABLE_PATH_PREFIX=/tmp0 B
72ENV SERVER__OTEL_SERVICE_NAME=0 B
73ENV SERVER__INFO_PATH=/info0 B
74ENV SERVER__STARTUP_PATH=/health/startup0 B
75ENV SERVER__READINESS_PATH=/health/readiness0 B
76ENV SERVER__LIVENESS_PATH=/health/liveness0 B
77ENV SERVER__DOCS_PATH=0 B
78ENV SERVER__OPENAPI_PATH=/openapi.json0 B
79ENV SERVER__EMBEDDINGS_PATH=/embeddings0 B
80ENV SERVER__CONTEXTUALIZED_EMBEDDINGS_PATH=/contextualizedembeddings0 B
81ENV SERVER__MULTIMODAL_EMBEDDINGS_PATH=/multimodalembeddings0 B
82ENV SERVER__RERANK_PATH=/rerank0 B
83ENV SERVER__TLS__ENABLED=false0 B
84ENV SERVER__TLS__CERTFILE=0 B
85ENV SERVER__TLS__KEYFILE=0 B
86ENV SERVER__TLS__CA_CERTS=0 B
87ENV SERVER__ERROR_RESPONSE_THROTTLING__ENABLED=true0 B
88ENV SERVER__ERROR_RESPONSE_THROTTLING__WINDOW_SECONDS=10.00 B
89ENV SERVER__ERROR_RESPONSE_THROTTLING__MAX_ERRORS_PER_WINDOW=500 B
90ENV SERVER__ERROR_RESPONSE_THROTTLING__DELAY_SECONDS=1.00 B
91ENV SERVER__ERROR_RESPONSE_THROTTLING__STATUS_CODES=[429, 500, 503, 504]0 B
92ENV SERVER__METRICS__ENABLED=false0 B
93ENV SERVER__METRICS__PATH=/metrics0 B
94ENV SERVER__METRICS__PORT=0 B
95ENV SERVER__CORRECTNESS__CHECK_ON_STARTUP=true0 B
96ENV SERVER__CORRECTNESS__BASE_DIR=/app/correlation0 B
97ENV SERVER__CORRECTNESS__CONCURRENCY=80 B
98ENV SERVER__CORRECTNESS__RESULT_WAIT_TIMEOUT=600.00 B
99ENV DATA_PARALLEL__ENABLED=false0 B
100ENV DATA_PARALLEL__NUM_WORKERS=auto0 B
101ENV DATA_PARALLEL__LOAD_BALANCING_STRATEGY=token_aware0 B
102ENV DATA_PARALLEL__WORKER_INIT_TIMEOUT=600.00 B
103ENV DATA_PARALLEL__WORKER_EXECUTION_TIMEOUT=30.00 B
104ENV DATA_PARALLEL__WORKER_QUEUE_MAXSIZE=1000 B
105ENV DATA_PARALLEL__BATCHING__STRATEGY=time_window0 B
106ENV DATA_PARALLEL__BATCHING__MAX_WAIT_TIME=0.010 B
107ENV DATA_PARALLEL__BATCHING__MAX_QUEUE_SIZE=20000 B
108ENV DATA_PARALLEL__HEALTH_MONITORING__CHECK_INTERVAL=5.00 B
109ENV DATA_PARALLEL__HEALTH_MONITORING__MAX_CONSECUTIVE_TIMEOUTS=30 B
110ENV DATA_PARALLEL__HEALTH_MONITORING__ENABLE_ACTIVE_CHECKS=false0 B
111ENV DATA_PARALLEL__HEALTH_MONITORING__ACTIVE_CHECK_INTERVAL=600 B
112ENV DATA_PARALLEL__HEALTH_MONITORING__ACTIVE_CHECK_TIMEOUT=50 B
113ENV DATA_PARALLEL__HEALTH_MONITORING__MAX_RESTART_ATTEMPTS=30 B
114ENV DATA_PARALLEL__HEALTH_MONITORING__RESTART_COOLDOWN=30.00 B
115ENV CUSTOM_VLLM_PLUGINS=Qwen3ForVoyageEmbedding0 B
116ENV VLLM_DO_NOT_TRACK=10 B
117ENV VLLM_CONFIGURE_LOGGING=00 B
118ENV VLLM_TARGET_DEVICE=cpu0 B
119ENV VLLM_CPU_KVCACHE_SPACE=00 B
120RUN |51 SERVER__PORT=8080 SERVER__MAX_REQUESTS=0 SERVER__MAX_REQUESTS_JITTER=0198 B
121ENV LD_PRELOAD=/usr/local/lib/libtcmalloc_minimal.so.40 B
122COPY . /app/model_weights/ # buildkit521.02 MB
123COPY core /app/core/ # buildkit432.64 KB
124COPY . /app/ # buildkit596 B
125COPY . /app/correlation/ # buildkit178.68 KB
126COPY targets/on_prem/community/embedding/app.py /app/ # buildkit519 B
127COPY targets/on_prem/community/embedding/launcher.py /app/ # buildkit2.96 KB
128COPY targets/on_prem/community/embedding/gunicorn.conf.py /app/ # buildkit1.38 KB
129EXPOSE &{[{{214 0} {214 0}}]0 B
130ENTRYPOINT ["python" "/app/launcher.py"]0 B

Command

 ARG RELEASE