Spaces:
No application file
No application file
File size: 3,162 Bytes
6d27d90 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
services:
#-----------------------------------
#---- Private-GPT services ---------
#-----------------------------------
# Private-GPT service for the Ollama CPU and GPU modes
# This service builds from an external Dockerfile and runs the Ollama mode.
private-gpt-ollama:
image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-ollama # x-release-please-version
build:
context: .
dockerfile: Dockerfile.ollama
volumes:
- ./local_data/:/home/worker/app/local_data
ports:
- "8001:8001"
environment:
PORT: 8001
PGPT_PROFILES: docker
PGPT_MODE: ollama
PGPT_EMBED_MODE: ollama
PGPT_OLLAMA_API_BASE: http://ollama:11434
HF_TOKEN: ${HF_TOKEN:-}
profiles:
- ""
- ollama-cpu
- ollama-cuda
- ollama-api
# Private-GPT service for the local mode
# This service builds from a local Dockerfile and runs the application in local mode.
private-gpt-llamacpp-cpu:
image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-llamacpp-cpu # x-release-please-version
build:
context: .
dockerfile: Dockerfile.llamacpp-cpu
volumes:
- ./local_data/:/home/worker/app/local_data
- ./models/:/home/worker/app/models
entrypoint: sh -c ".venv/bin/python scripts/setup && .venv/bin/python -m private_gpt"
ports:
- "8001:8001"
environment:
PORT: 8001
PGPT_PROFILES: local
HF_TOKEN: ${HF_TOKEN}
profiles:
- llamacpp-cpu
#-----------------------------------
#---- Ollama services --------------
#-----------------------------------
# Traefik reverse proxy for the Ollama service
# This will route requests to the Ollama service based on the profile.
ollama:
image: traefik:v2.10
ports:
- "8081:8080"
command:
- "--providers.file.filename=/etc/router.yml"
- "--log.level=ERROR"
- "--api.insecure=true"
- "--providers.docker=true"
- "--providers.docker.exposedbydefault=false"
- "--entrypoints.web.address=:11434"
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
- ./.docker/router.yml:/etc/router.yml:ro
extra_hosts:
- "host.docker.internal:host-gateway"
profiles:
- ""
- ollama-cpu
- ollama-cuda
- ollama-api
# Ollama service for the CPU mode
ollama-cpu:
image: ollama/ollama:latest
volumes:
- ./models:/root/.ollama
profiles:
- ""
- ollama-cpu
# Ollama service for the CUDA mode
ollama-cuda:
image: ollama/ollama:latest
volumes:
- ./models:/root/.ollama
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
profiles:
- ollama-cuda
openai:
image: 3x3cut0r/privategpt:latest
build:
context: .
dockerfile: Dockerfile.openai
container_name: privategpt
ports:
- 8080:8080/tcp
environment:
OPENAI_API_KEY: ${OPENAI_API_KEY}
OPENAI_API_BASE: https://api.openai.com/v1
OPENAI_MODEL: gpt-4o-mini
OPENAI_TEMPERATURE: 0.5
|