Skip to content
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.

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

Full docker compose fails with socket error #4

Open
HorusPi opened this issue Jan 8, 2024 · 0 comments
Open

Full docker compose fails with socket error #4

HorusPi opened this issue Jan 8, 2024 · 0 comments

Comments

@HorusPi
Copy link

HorusPi commented Jan 8, 2024

ollama-agent-1 | Skipping virtualenv creation, as specified in config file.
ollama-agent-1 | [nltk_data] Downloading package punkt to /root/nltk_data...
ollama-agent-1 | [nltk_data] Unzipping tokenizers/punkt.zip.
ollama-agent-1 | Traceback (most recent call last):
ollama-agent-1 | File "/usr/local/lib/python3.11/site-packages/httpcore/_exceptions.py", line 10, in map_exceptions
ollama-agent-1 | yield
ollama-agent-1 | File "/usr/local/lib/python3.11/site-packages/httpcore/_backends/sync.py", line 100, in connect_tcp
ollama-agent-1 | sock = socket.create_connection(
ollama-agent-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^
ollama-agent-1 | File "/usr/local/lib/python3.11/socket.py", line 851, in create_connection
ollama-agent-1 | raise exceptions[0]
ollama-agent-1 | File "/usr/local/lib/python3.11/socket.py", line 836, in create_connection
ollama-agent-1 | sock.connect(sa)
ollama-agent-1 | OSError: [Errno 99] Cannot assign requested address

Used docker-compose
services:
ollama-agent:
build: .
volumes:
- ./data:/data
- ./logs:/logs
- ./vector_db:/vector_db
- ./ollama_rag:/ollama_rag
depends_on:
- qdrant
- ollama
ports:
- "8001:8000"
environment:
- "HOST_MACHINE_ADDRESS=host.docker.internal"

qdrant:
image: qdrant/qdrant
container_name: qdrant
command: ["./qdrant", "--config-path", "config/qdrant.yaml"]
volumes:
- ./vector_db:/qdrant/storage
- ./config/qdrant.yaml:/qdrant/config/qdrant.yaml
ports:
- "6333:6333"
- "6334:6334"
logging:
driver: "json-file"
options:
max-file: "1"
max-size: "10m"
deploy:
resources:
limits:
memory: 10Gb
ollama:
image: ollama/ollama
container_name: ollama
ports:
- "11434:11434"
volumes:
- "ollama:/root/.ollama"
restart: unless-stopped

volumes:
ollama:
driver: local

used main.yml

qdrant:
#url: http://qdrant
url: http://localhost
port: 6333
prefer_grpc: false
collection_name_ollama: ollama

aleph_alpha_embeddings:
normalize: True
size: 5120
compress_to_size: null
model_name: "luminous-base-control"

ollama_embeddings:
#url: "http://localhost:11434" # if not using docker
url: "http://host.docker.internal:11434" # if using docker
model: zephyr

ollama:
model: zephyr
#url: "http://localhost:11434" # if not using docker
url: "http://host.docker.internal:11434" # if using docker

It also does not detect the nvidia card on system.
Run on windows 10 system with docker-desktop 4.26.1

ollama and qdrant are up and running without issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant