github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2161] Provide Docker images with pre-downloaded models #1235

New Issue
Closed
opened 2026-04-12 11:00:22 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 11:00:22 -05:00
Owner
Copy Link

Originally created by @eddumelendez on GitHub (Jan 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2161

Libraries and frameworks have been built around Ollama such as LangChain4J and pulling models are part of the process to make use of it.

Currently, in order to test the library integration there is a setup done using Testcontainers to start Ollama's Docker image and pull the image to provide the infrastructure needed for the Integration Test. See this code snippet.

I think https://github.com/jmorganca/ollama/issues/2160 could help in this scenario as well but for those who want to run specific models supported by Ollama, it provides a nice getting started experience IMO. There is an effort on the project to maintain those images https://hub.docker.com/u/langchain4j but would be nice to provide images with the model in it.

Originally created by @eddumelendez on GitHub (Jan 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2161 Libraries and frameworks have been built around Ollama such as [LangChain4J](https://github.com/langchain4j/langchain4j) and pulling models are part of the process to make use of it. Currently, in order to test the library integration there is a setup done using [Testcontainers](https://testcontainers.com/) to start Ollama's Docker image and pull the image to provide the infrastructure needed for the Integration Test. See [this code snippet](https://github.com/langchain4j/langchain4j/blob/50f32ba1985826ce7dc81300400c6c5fd2c22576/langchain4j-ollama/src/test/java/dev/langchain4j/model/ollama/AbstractOllamaInfrastructure.java#L65-L75). I think https://github.com/jmorganca/ollama/issues/2160 could help in this scenario as well but for those who want to run specific models supported by Ollama, it provides a nice getting started experience IMO. There is an effort on the project to maintain those images https://hub.docker.com/u/langchain4j but would be nice to provide images with the model in it.
GiteaMirror commented 2026-04-12 11:00:23 -05:00
Author
Owner
Copy Link

@eddumelendez commented on GitHub (Feb 21, 2024):

bakllava, mistral, orca-mini and phi would be a good start for langchain4j and spring-ai projects

<!-- gh-comment-id:1957098567 --> @eddumelendez commented on GitHub (Feb 21, 2024): `bakllava`, `mistral`, `orca-mini` and `phi` would be a good start for [langchain4j](https://github.com/langchain4j/langchain4j/blob/main/langchain4j-ollama/src/test/java/dev/langchain4j/model/ollama/AbstractOllamaInfrastructure.java#L21) and spring-ai projects
GiteaMirror commented 2026-04-12 11:00:23 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Mar 11, 2024):

There's currently no plans to provide official docker images with predownloaded models although you can always augment it to include this functionality

<!-- gh-comment-id:1989238053 --> @mxyng commented on GitHub (Mar 11, 2024): There's currently no plans to provide official docker images with predownloaded models although you can always augment it to include this functionality
GiteaMirror commented 2026-04-12 11:00:23 -05:00
Author
Owner
Copy Link

@CWKSC commented on GitHub (Oct 31, 2024):

According to docker - How to build in Mistral model into Ollama permanently? - Stack Overflow

FROM docker.io/ollama/ollama:0.3.14

# https://stackoverflow.com/questions/78688712/how-to-build-in-mistral-model-into-ollama-permanently
RUN apt-get update && \
    DEBIAN_FRONTEND=noninteractive \
    apt-get install --no-install-recommends --assume-yes \
        curl
RUN ollama serve & \
    curl --retry 10 --retry-connrefused --retry-delay 1 http://localhost:11434/ && \
    curl -X POST -d '{"name": "llama3.2:3b"}' http://localhost:11434/api/pull
<!-- gh-comment-id:2449775166 --> @CWKSC commented on GitHub (Oct 31, 2024): According to [docker - How to build in Mistral model into Ollama permanently? - Stack Overflow](https://stackoverflow.com/questions/78688712/how-to-build-in-mistral-model-into-ollama-permanently) ```containerfile FROM docker.io/ollama/ollama:0.3.14 # https://stackoverflow.com/questions/78688712/how-to-build-in-mistral-model-into-ollama-permanently RUN apt-get update && \ DEBIAN_FRONTEND=noninteractive \ apt-get install --no-install-recommends --assume-yes \ curl RUN ollama serve & \ curl --retry 10 --retry-connrefused --retry-delay 1 http://localhost:11434/ && \ curl -X POST -d '{"name": "llama3.2:3b"}' http://localhost:11434/api/pull ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1235
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?