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 #8090] Add an ollama example that enables users to chat with a code generation model and then tests the code generated by the model #51682

New Issue
Open
opened 2026-04-28 20:44:54 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 20:44:54 -05:00
Owner
Copy Link

Originally created by @jagane on GitHub (Dec 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8090

Often times, code generated by code generation models such as qwen2.5-coder:7b is not perfect. It may not even be syntactically correct. I am proposing to add an example program, possibly derived from the the python-simplechat example, that extracts the code generated by the model and runs/tests it. The first iteration would only know to run python programs.

The name python-code-iterate sounds like a reasonable name for this example program

  1. User enters a prompt e.g. write a python program to quantize a model stored in my local dir /home/userabc/model1
  2. The model generates code for this task and provides it as part of its response, i.e. the 'assistant' message
  3. Our new program python-code-iterate then asks the user whether to run the program and check output
  4. If the user says yes, then python-code-iterate will use a subprocess to run the program and check return code, stdout and stderr
  5. If the return code is non zero, then the stderr contents will be added as a user message and the chat will continue
  6. repeat steps 2 to 5 till satisfactory results are obtained
Originally created by @jagane on GitHub (Dec 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8090 Often times, code generated by code generation models such as qwen2.5-coder:7b is not perfect. It may not even be syntactically correct. I am proposing to add an example program, possibly derived from the the python-simplechat example, that extracts the code generated by the model and runs/tests it. The first iteration would only know to run python programs. The name python-code-iterate sounds like a reasonable name for this example program 1. User enters a prompt e.g. write a python program to quantize a model stored in my local dir /home/userabc/model1 2. The model generates code for this task and provides it as part of its response, i.e. the 'assistant' message 3. Our new program python-code-iterate then asks the user whether to run the program and check output 4. If the user says yes, then python-code-iterate will use a subprocess to run the program and check return code, stdout and stderr 5. If the return code is non zero, then the stderr contents will be added as a user message and the chat will continue 6. repeat steps 2 to 5 till satisfactory results are obtained
GiteaMirror added the feature request label 2026-04-28 20:44:54 -05:00
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#51682
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?