github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11495] Unable to pull Ollama model even though I did #33353

New Issue
Open
opened 2026-04-22 15:55:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 15:55:52 -05:00
Owner
Copy Link

Originally created by @shermaine0603 on GitHub (Jul 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11495

Hi all, I am trying to run an Ollama model (llava:7b) inside a docker container.

I first created a start_services.sh file to run ollama serve in the background (since it does hang when it runs).

#!/bin/sh

# Start Ollama in the background
ollama serve &

# Wait for Ollama to start
sleep 5

# Pull the required model(s)
ollama pull llava:7b

# Start your Python application
python read_excel.py

tail -f /dev/null``

Then I build a docker image from this dockerfile:

> FROM ollama/ollama:latest

WORKDIR /app

# Install Python and dependencies
RUN apt-get update && apt-get install -y python3 python3-pip -y curl \
    && ln -s /usr/bin/python3 /usr/bin/python \
    && curl -fsSL https://ollama.com/install.sh | sh

RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y python3-venv python3-sklearn

# Create and activate a virtual environment
RUN python3 -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

# Upgrade pip and install scikit-learn
RUN pip install --upgrade pip
RUN pip install scikit-learn

# RUN pip freeze > requirements.txt
# RUN pip install -r requirements.txt
RUN pip3 install ollama
RUN pip install Openpyxl
RUN pip install Pillow
RUN pip install pandas
RUN pip install numpy

# Make the startup script executable
COPY start_services.sh .
RUN chmod +x start_services.sh

# Expose the Ollama API port
EXPOSE 11434

#Override the ENTRYPOINT from the base image
ENTRYPOINT []

# Run the startup script
CMD ["./start_services.sh"]``

As you can see in my dockerfile, the last line runs the script.

However, when I finally tried to run my python script, which will run llava, inside the docker container, it gave the following error:

Traceback (most recent call last):
  File "/app/read_excel.py", line 15, in <module>
    res = ollama.chat(
          ^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/ollama/_client.py", line 342, in chat
    return self._request(
           ^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/ollama/_client.py", line 180, in _request
    return cls(**self._request_raw(*args, **kwargs).json())
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/ollama/_client.py", line 124, in _request_raw
    raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: model "llava:7b" not found, try pulling it first (status code: 404)

I don't understand how am I encountering this error even though I did pull the model in the start_services.sh. How can I resolve this issue?

Originally created by @shermaine0603 on GitHub (Jul 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11495 Hi all, I am trying to run an Ollama model (llava:7b) inside a docker container. I first created a start_services.sh file to run ollama serve in the background (since it does hang when it runs). ``` #!/bin/sh # Start Ollama in the background ollama serve & # Wait for Ollama to start sleep 5 # Pull the required model(s) ollama pull llava:7b # Start your Python application python read_excel.py tail -f /dev/null`` ``` Then I build a docker image from this dockerfile: ``` > FROM ollama/ollama:latest WORKDIR /app # Install Python and dependencies RUN apt-get update && apt-get install -y python3 python3-pip -y curl \ && ln -s /usr/bin/python3 /usr/bin/python \ && curl -fsSL https://ollama.com/install.sh | sh RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y python3-venv python3-sklearn # Create and activate a virtual environment RUN python3 -m venv /opt/venv ENV PATH="/opt/venv/bin:$PATH" # Upgrade pip and install scikit-learn RUN pip install --upgrade pip RUN pip install scikit-learn # RUN pip freeze > requirements.txt # RUN pip install -r requirements.txt RUN pip3 install ollama RUN pip install Openpyxl RUN pip install Pillow RUN pip install pandas RUN pip install numpy # Make the startup script executable COPY start_services.sh . RUN chmod +x start_services.sh # Expose the Ollama API port EXPOSE 11434 #Override the ENTRYPOINT from the base image ENTRYPOINT [] # Run the startup script CMD ["./start_services.sh"]`` ``` As you can see in my dockerfile, the last line runs the script. However, when I finally tried to run my python script, which will run llava, inside the docker container, it gave the following error: ``` Traceback (most recent call last): File "/app/read_excel.py", line 15, in <module> res = ollama.chat( ^^^^^^^^^^^^ File "/opt/venv/lib/python3.12/site-packages/ollama/_client.py", line 342, in chat return self._request( ^^^^^^^^^^^^^^ File "/opt/venv/lib/python3.12/site-packages/ollama/_client.py", line 180, in _request return cls(**self._request_raw(*args, **kwargs).json()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/venv/lib/python3.12/site-packages/ollama/_client.py", line 124, in _request_raw raise ResponseError(e.response.text, e.response.status_code) from None ollama._types.ResponseError: model "llava:7b" not found, try pulling it first (status code: 404) ``` I don't understand how am I encountering this error even though I did pull the model in the start_services.sh. How can I resolve this issue?
GiteaMirror added the docker label 2026-04-22 15:55:52 -05:00
GiteaMirror commented 2026-04-22 15:55:53 -05:00
Author
Owner
Copy Link

@nehagawhane commented on GitHub (Aug 1, 2025):

Sometimes for me, it takes longer than 5, have you tried:

ollama pull <model>
until ollama list | grep -q <model>; do
sleep 5
done
<!-- gh-comment-id:3141862045 --> @nehagawhane commented on GitHub (Aug 1, 2025): Sometimes for me, it takes longer than 5, have you tried: ``` ollama pull <model> until ollama list | grep -q <model>; do sleep 5 done ```
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 docker
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#33353
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?