[GH-ISSUE #3387] Multiline Input Buffer to small #27842

Open
opened 2026-04-22 05:28:30 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @FairyTail2000 on GitHub (Mar 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3387

Originally assigned to: @joshyan1 on GitHub.

What is the issue?

When testing out model capabilities I copy pasted the whole rendered version of the ollama readme into the terminal to be consumed the llm.

While ollama crashed due to insufficient VRAM, this is not the issue in this issue. It took everything up to:

.. Remove a model
... ollama rm llama2
... Copy a model
... ollama cp llama2 my-llama2
... Multiline input
... For multiline input, you can wrap text with """:
...
... >>> """Hello,
... ... world!
... ... """
Error: Post "http://0.0.0.0:11434/api/chat": EOF
~ $ d '{
quote> "model": "mistral",
quote> "messages": [
quote> { "role": "user", "content": "why is the sky blue?" }
quote> ]
quote> }'
zsh: command not found: d

After that the remaining input overflowed into the standard input:
image

What did you expect to see?

Ollama taking the whole input

Steps to reproduce

Copy the rendred version of the readme linked above, paste it and see it overflowing

Are there any recent changes that introduced the issue?

No response

OS

Linux

Architecture

x86

Platform

No response

Ollama version

0.1.29

GPU

Nvidia

GPU info

No response

CPU

Intel

Other software

No response

Originally created by @FairyTail2000 on GitHub (Mar 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3387 Originally assigned to: @joshyan1 on GitHub. ### What is the issue? When testing out model capabilities I copy pasted the whole rendered version of the [ollama readme](https://github.com/ollama/ollama/blob/756c2575535641f1b96d94b4214941b90f4c30c7/README.md) into the terminal to be consumed the llm. While ollama crashed due to insufficient VRAM, this is not the issue in this issue. It took everything up to: > .. Remove a model ... ollama rm llama2 ... Copy a model ... ollama cp llama2 my-llama2 ... Multiline input ... For multiline input, you can wrap text with """: ... ... >>> """Hello, ... ... world! ... ... """ Error: Post "http://0.0.0.0:11434/api/chat": EOF ~ $ d '{ quote> "model": "mistral", quote> "messages": [ quote> { "role": "user", "content": "why is the sky blue?" } quote> ] quote> }' zsh: command not found: d After that the remaining input overflowed into the standard input: ![image](https://github.com/ollama/ollama/assets/22645621/fdcc7c70-5054-4684-8329-1726ee0ed7a9) ### What did you expect to see? Ollama taking the whole input ### Steps to reproduce Copy the rendred version of the readme linked above, paste it and see it overflowing ### Are there any recent changes that introduced the issue? _No response_ ### OS Linux ### Architecture x86 ### Platform _No response_ ### Ollama version 0.1.29 ### GPU Nvidia ### GPU info _No response_ ### CPU Intel ### Other software _No response_
GiteaMirror added the clibug labels 2026-04-22 05:28:30 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#27842