github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4196] Mocked model for integration testing Ollama into other tools and environments #2610

New Issue
Open
opened 2026-04-12 12:57:43 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 12:57:43 -05:00
Owner
Copy Link

Originally created by @bauersimon on GitHub (May 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4196

We are looking for a model or a functionality of Ollama that allows us to mock requests and responses without changing the Ollama binary. Basically we want to define a map of requests to responses, e.g. when "Foo" comes in as a request, we want to define that "Bar" should be returned by the model.

This allows us to do integration testing of Ollama for the DevQualityEval (an evaluation benchmark to evolve the quality of code generation). We need deterministic mocking definition, to allow for deterministic testing.

Originally created by @bauersimon on GitHub (May 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4196 We are looking for a model or a functionality of Ollama that allows us to mock requests and responses without changing the Ollama binary. Basically we want to define a map of requests to responses, e.g. when "Foo" comes in as a request, we want to define that "Bar" should be returned by the model. This allows us to do integration testing of Ollama for the [DevQualityEval](https://github.com/symflower/eval-dev-quality) (an evaluation benchmark to evolve the quality of code generation). We need deterministic mocking definition, to allow for deterministic testing.
GiteaMirror added the feature request label 2026-04-12 12:57:43 -05:00
GiteaMirror commented 2026-04-12 12:57:44 -05:00
Author
Owner
Copy Link

@alexrecuenco commented on GitHub (Oct 21, 2024):

I was also looking to do some basic integration testing, and I can't figure out what is the best approach.

@bauersimon, did you find any simple integrated way to do it? I don't know if the "simplest way" it is going to be create our own "model" that simply echoes back the tokens it receives

<!-- gh-comment-id:2426510123 --> @alexrecuenco commented on GitHub (Oct 21, 2024): I was also looking to do some basic integration testing, and I can't figure out what is the best approach. @bauersimon, did you find any simple integrated way to do it? I don't know if the "simplest way" it is going to be create our own "model" that simply echoes back the tokens it receives
GiteaMirror commented 2026-04-12 12:57:45 -05:00
Author
Owner
Copy Link

@bauersimon commented on GitHub (Oct 24, 2024):

We still just use qwen:0.5b and assert that some text is returned. Better than nothing but not ideal.

<!-- gh-comment-id:2435028055 --> @bauersimon commented on GitHub (Oct 24, 2024): We still just use `qwen:0.5b` and assert that some text is returned. Better than nothing but not ideal.
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 feature request
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#2610
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?