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 #6791] Occasionally getting a 500 response and 'ollama._types.ResponseError: health resp' seemingly out of nowhere #4281

New Issue
Open
opened 2026-04-12 15:12:34 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 15:12:34 -05:00
Owner
Copy Link

Originally created by @danielj0nes on GitHub (Sep 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6791

What is the issue?

Hello, I am running a Python server that receives and sends requests to an instance of Ollama (with the Llama 3.1 model).

When lots of requests are sent at once, I occasionally receive a 500 response from the Ollama server which causes the process to crash. The error I get from the Python Ollama module is as follows:

  File "ollama\_client.py", line 407, in generate
  File "ollama\_client.py", line 378, in _request_stream
  File "ollama\_client.py", line 348, in _request
ollama._types.ResponseError: health resp: Get "http://127.0.0.1:61519/health": dial tcp 127.0.0.1:61519: connectex: Only one usage of each socket address (protocol/network address/port) is normally permitted.

I am not trying to do anything else with Ollama whilst requests to generate are being sent.

Is there something in Ollama that is automatically attempting to bind this port? Can I somehow just disable this '/health' endpoint?

Thanks in advance.

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.3.10

Originally created by @danielj0nes on GitHub (Sep 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6791 ### What is the issue? Hello, I am running a Python server that receives and sends requests to an instance of Ollama (with the Llama 3.1 model). When lots of requests are sent at once, I occasionally receive a 500 response from the Ollama server which causes the process to crash. The error I get from the Python Ollama module is as follows: ```Traceback (most recent call last): File "ollama\_client.py", line 407, in generate File "ollama\_client.py", line 378, in _request_stream File "ollama\_client.py", line 348, in _request ollama._types.ResponseError: health resp: Get "http://127.0.0.1:61519/health": dial tcp 127.0.0.1:61519: connectex: Only one usage of each socket address (protocol/network address/port) is normally permitted. ``` I am not trying to do anything else with Ollama whilst requests to generate are being sent. Is there something in Ollama that is automatically attempting to bind this port? Can I somehow just disable this '/health' endpoint? Thanks in advance. ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.3.10
GiteaMirror added the bug label 2026-04-12 15:12:34 -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 bug
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#4281
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?