phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

use auth for kvant
All checks were successful
Build and Push playground container / build-playground (push) Successful in 1m6s
Details
Build and Push container / build (push) Successful in 4m27s
Details

Browse source
This commit is contained in:
Angel Nunez Mencias 2025-06-02 01:23:33 +02:00
parent 3bde47e562
commit 96003b55de
Signed by: angel.nunez
SSH key fingerprint: SHA256:z1nFAg1v1AfbhEHrgBetByUJUwziv2R2f4VyN75opcg
4 changed files with 2342 additions and 2305 deletions
Download patch file Download diff file Expand all files Collapse all files

7
kvant_start_local.sh
View file

@ -5,14 +5,18 @@ export EMBEDDING_MODEL="inference-bge-m3"
export EMBEDDING_DIMENSION="1024"
export LLAMA_STACK_PORT=8321
export OPENAI_BASE_URL=https://maas.ai-2.kvant.cloud/v1
export OPENAI_API_KEY=sk-ZqAWqBKFXjb6y3tVej2AaA
# OPENAI_API_KEY= env file
export VLLM_MAX_TOKENS=125000
# KEYCLOAK_CLIENT_SECRET= env file
export $(cat .env | xargs)
docker run -it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $(pwd)/data:/root/.llama \
--mount type=bind,source="$(pwd)"/llama_stack/templates/kvant/run.yaml,target=/root/.llama/config.yaml,readonly \
--entrypoint python \
--env-file ./.env \
distribution-kvant:dev \
-m llama_stack.distribution.server.server --config /root/.llama/config.yaml \
--port $LLAMA_STACK_PORT \
@ -23,3 +27,4 @@ docker run -it \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env EMBEDDING_MODEL=$EMBEDDING_MODEL \
--env EMBEDDING_DIMENSION=$EMBEDDING_DIMENSION \
--env KEYCLOAK_CLIENT_SECRET=$KEYCLOAK_CLIENT_SECRET \