github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9127] How can I connect to Ollama's server? #5937

New Issue
Closed
opened 2026-04-12 17:16:41 -05:00 by GiteaMirror · 18 comments
GiteaMirror commented 2026-04-12 17:16:41 -05:00
Owner
Copy Link

Originally created by @Neabigmo on GitHub (Feb 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9127

when I run the powershell:

Image

really make me confusing./(ㄒoㄒ)/~~

Originally created by @Neabigmo on GitHub (Feb 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9127 when I run the powershell: ![Image](https://github.com/user-attachments/assets/8a04e782-f32d-4baa-bd3b-4c56de36cbc9) really make me confusing./(ㄒoㄒ)/~~
GiteaMirror commented 2026-04-12 17:16:42 -05:00
Author
Owner
Copy Link

@LeisureLinux commented on GitHub (Feb 15, 2025):

  • check your process list.
  • check your service running.
  • use netstat check your opening port.
  • check other terminal is running ollama or not. how do you start your ollam?
  • try setx OLLAMA_HOST=127.0.0.1:11434
<!-- gh-comment-id:2660822331 --> @LeisureLinux commented on GitHub (Feb 15, 2025): - check your process list. - check your service running. - use netstat check your opening port. - check other terminal is running ollama or not. how do you start your ollam? - try setx OLLAMA_HOST=127.0.0.1:11434
GiteaMirror commented 2026-04-12 17:16:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 15, 2025):

The ollama server crashed when you did the run command. Server logs may show why.

<!-- gh-comment-id:2660889387 --> @rick-github commented on GitHub (Feb 15, 2025): The ollama server crashed when you did the `run` command. [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may show why.
GiteaMirror commented 2026-04-12 17:16:43 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 15, 2025):

The ollama server crashed when you did the run command. Server logs may show why.

Why do I have to use a proxy in the code to connect to the model? This will conflict with my actual proxy.
os.environ["http_proxy"] = "http://127.0.0.1:11434"
os.environ["https_proxy"] = "http://127.0.0.1:11434"

<!-- gh-comment-id:2661019906 --> @trash-fish commented on GitHub (Feb 15, 2025): > The ollama server crashed when you did the `run` command. [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may show why. Why do I have to use a proxy in the code to connect to the model? This will conflict with my actual proxy. os.environ["http_proxy"] = "http://127.0.0.1:11434" os.environ["https_proxy"] = "http://127.0.0.1:11434"
GiteaMirror commented 2026-04-12 17:16:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 15, 2025):

You don't have to use a proxy, and in fact you shouldn't for 127.0.0.1.

<!-- gh-comment-id:2661022128 --> @rick-github commented on GitHub (Feb 15, 2025): You don't have to use a proxy, and in fact you shouldn't for 127.0.0.1.
GiteaMirror commented 2026-04-12 17:16:44 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 15, 2025):

You don't have to use a proxy, and in fact you shouldn't for 127.0.0.1.

If I don't add the proxy, my error is as follows:

Traceback (most recent call last):
File "W:\代码\LLM\LangChainDemo01\demo03.py", line 54, in
print(chain.invoke({'content': '你好？'}))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\runnables\base.py", line 3024, in invoke
input = context.run(step.invoke, input, config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 284, in invoke
self.generate_prompt(
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 860, in generate_prompt
return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 690, in generate
self._generate_with_cache(
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 925, in _generate_with_cache
result = self._generate(
^^^^^^^^^^^^^^^
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_ollama\chat_models.py", line 701, in _generate
final_chunk = self._chat_stream_with_aggregation(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_ollama\chat_models.py", line 602, in _chat_stream_with_aggregation
for stream_resp in self._create_chat_stream(messages, stop, **kwargs):
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_ollama\chat_models.py", line 589, in _create_chat_stream
yield from self._client.chat(**chat_params)
File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\ollama_client.py", line 168, in inner
raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: (status code: 502)

my code：


# 设置代理
# os.environ["http_proxy"] = "http://127.0.0.1:11434"
# os.environ["https_proxy"] = "http://127.0.0.1:11434"



# 调用大语言模型
model = ChatOllama(
    model="llama3.2:1b",
    base_url="http://localhost:11434",
    temperature=0.8
)


# 定义提示模板
prompt = ChatPromptTemplate.from_messages(
    [('system', '你作为ai注释，为用户解决问题'), ('human', '{content}')]
)


# 定义解析器
parser = StrOutputParser()



# 获取链，模板、模型、消息解析器
chain = prompt | model | parser




print(chain.invoke({'content': '你好？'}))
<!-- gh-comment-id:2661023235 --> @trash-fish commented on GitHub (Feb 15, 2025): > You don't have to use a proxy, and in fact you shouldn't for 127.0.0.1. If I don't add the proxy, my error is as follows: Traceback (most recent call last): File "W:\代码\LLM\LangChainDemo01\demo03.py", line 54, in <module> print(chain.invoke({'content': '你好？'})) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\runnables\base.py", line 3024, in invoke input = context.run(step.invoke, input, config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 284, in invoke self.generate_prompt( File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 860, in generate_prompt return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 690, in generate self._generate_with_cache( File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\language_models\chat_models.py", line 925, in _generate_with_cache result = self._generate( ^^^^^^^^^^^^^^^ File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_ollama\chat_models.py", line 701, in _generate final_chunk = self._chat_stream_with_aggregation( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_ollama\chat_models.py", line 602, in _chat_stream_with_aggregation for stream_resp in self._create_chat_stream(messages, stop, **kwargs): File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_ollama\chat_models.py", line 589, in _create_chat_stream yield from self._client.chat(**chat_params) File "C:\Users\20262\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\ollama\_client.py", line 168, in inner raise ResponseError(e.response.text, e.response.status_code) from None ollama._types.ResponseError: (status code: 502) ``` my code： # 设置代理 # os.environ["http_proxy"] = "http://127.0.0.1:11434" # os.environ["https_proxy"] = "http://127.0.0.1:11434" # 调用大语言模型 model = ChatOllama( model="llama3.2:1b", base_url="http://localhost:11434", temperature=0.8 ) # 定义提示模板 prompt = ChatPromptTemplate.from_messages( [('system', '你作为ai注释，为用户解决问题'), ('human', '{content}')] ) # 定义解析器 parser = StrOutputParser() # 获取链，模板、模型、消息解析器 chain = prompt | model | parser print(chain.invoke({'content': '你好？'})) ```
GiteaMirror commented 2026-04-12 17:16:44 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 15, 2025):

You don't have to use a proxy, and in fact you shouldn't for 127.0.0.1.

Image

I installed the model on my local machine using Ollama.

<!-- gh-comment-id:2661023954 --> @trash-fish commented on GitHub (Feb 15, 2025): > You don't have to use a proxy, and in fact you shouldn't for 127.0.0.1. ![Image](https://github.com/user-attachments/assets/c7a5535f-5f00-4d2b-a6ee-fccfbf0b89ac) I installed the model on my local machine using Ollama.
GiteaMirror commented 2026-04-12 17:16:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 15, 2025):

What does the following return:

curl localhost:11434
<!-- gh-comment-id:2661024595 --> @rick-github commented on GitHub (Feb 15, 2025): What does the following return: ``` curl localhost:11434 ```
GiteaMirror commented 2026-04-12 17:16:45 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 15, 2025):

What does the following return:

curl localhost:11434

Image

<!-- gh-comment-id:2661024971 --> @trash-fish commented on GitHub (Feb 15, 2025): > What does the following return: > > ``` > curl localhost:11434 > ``` ![Image](https://github.com/user-attachments/assets/ed1a4f3a-4542-44ef-8aff-f960348b59bf)
GiteaMirror commented 2026-04-12 17:16:46 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 15, 2025):

What does the following return:

curl localhost:11434

As long as I use it, there won't be any error reported.

# os.environ["http_proxy"] = "http://127.0.0.1:11434"
# os.environ["https_proxy"] = "http://127.0.0.1:11434"
<!-- gh-comment-id:2661025235 --> @trash-fish commented on GitHub (Feb 15, 2025): > What does the following return: > > ``` > curl localhost:11434 > ``` As long as I use it, there won't be any error reported. ``` # os.environ["http_proxy"] = "http://127.0.0.1:11434" # os.environ["https_proxy"] = "http://127.0.0.1:11434" ```
GiteaMirror commented 2026-04-12 17:16:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 15, 2025):

Ollama is running

ollama is working. If your app doesn't, that's a problem with the app or your proxy configuration. Try setting

os.environ["no_proxy"] = "127.0.0.1,localhost"
<!-- gh-comment-id:2661028405 --> @rick-github commented on GitHub (Feb 15, 2025): ``` Ollama is running ``` ollama is working. If your app doesn't, that's a problem with the app or your proxy configuration. Try setting ``` os.environ["no_proxy"] = "127.0.0.1,localhost" ```
GiteaMirror commented 2026-04-12 17:16:47 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 15, 2025):

Ollama is running

ollama is working. If your app doesn't, that's a problem with the app or your proxy configuration. Try setting

os.environ["no_proxy"] = "127.0.0.1,localhost"

If I use os.environ["no_proxy"] = "127.0.0.1,localhost", my proxy becomes invalid, causing me to be unable to access TavilySearchAPI. This might be due to my location in China, but theoretically, I shouldn't need to add os.environ["no_proxy"] = "127.0.0.1,localhost" to call the model.

<!-- gh-comment-id:2661032361 --> @trash-fish commented on GitHub (Feb 15, 2025): > ``` > Ollama is running > ``` > > ollama is working. If your app doesn't, that's a problem with the app or your proxy configuration. Try setting > > ``` > os.environ["no_proxy"] = "127.0.0.1,localhost" > ``` If I use os.environ["no_proxy"] = "127.0.0.1,localhost", my proxy becomes invalid, causing me to be unable to access TavilySearchAPI. This might be due to my location in China, but theoretically, I shouldn't need to add os.environ["no_proxy"] = "127.0.0.1,localhost" to call the model.
GiteaMirror commented 2026-04-12 17:16:48 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 15, 2025):

Then you need to figure out why your proxy is not routing traffic to 127.0.0.1:11434 to 127.0.0.1:11434. ollama doesn't need a proxy, if your app does then it's not an ollama problem.

<!-- gh-comment-id:2661033721 --> @rick-github commented on GitHub (Feb 15, 2025): Then you need to figure out why your proxy is not routing traffic to 127.0.0.1:11434 to 127.0.0.1:11434. ollama doesn't need a proxy, if your app does then it's not an ollama problem.
GiteaMirror commented 2026-04-12 17:16:49 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 16, 2025):

Then you need to figure out why your proxy is not routing traffic to 127.0.0.1:11434 to 127.0.0.1:11434. ollama doesn't need a proxy, if your app does then it's not an ollama problem.

os.environ["no_proxy"] = "127.0.0.1,localhost"
os.environ["http_proxy"] = "http://127.0.0.1:7890"
os.environ["https_proxy"] = "http://127.0.0.1:7890"

This can be solved

<!-- gh-comment-id:2661221531 --> @trash-fish commented on GitHub (Feb 16, 2025): > Then you need to figure out why your proxy is not routing traffic to 127.0.0.1:11434 to 127.0.0.1:11434. ollama doesn't need a proxy, if your app does then it's not an ollama problem. os.environ["no_proxy"] = "127.0.0.1,localhost" os.environ["http_proxy"] = "http://127.0.0.1:7890" os.environ["https_proxy"] = "http://127.0.0.1:7890" This can be solved
GiteaMirror commented 2026-04-12 17:16:50 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 16, 2025):

Then you need to figure out why your proxy is not routing traffic to 127.0.0.1:11434 to 127.0.0.1:11434. ollama doesn't need a proxy, if your app does then it's not an ollama problem.

Image
It can also be like this

<!-- gh-comment-id:2661222606 --> @trash-fish commented on GitHub (Feb 16, 2025): > Then you need to figure out why your proxy is not routing traffic to 127.0.0.1:11434 to 127.0.0.1:11434. ollama doesn't need a proxy, if your app does then it's not an ollama problem. ![Image](https://github.com/user-attachments/assets/5e426219-8e1c-46f6-84e7-05baad731ca5) It can also be like this
GiteaMirror commented 2026-04-12 17:16:50 -05:00
Author
Owner
Copy Link

@Neabigmo commented on GitHub (Feb 16, 2025):

以下内容返回什么：

curl localhost:11434

Image
what's meaning?

<!-- gh-comment-id:2661305350 --> @Neabigmo commented on GitHub (Feb 16, 2025): > 以下内容返回什么： > > ``` > curl localhost:11434 > ``` ![Image](https://github.com/user-attachments/assets/fdca1d25-dd6b-40c1-8939-ce21dd9cca50) what's meaning?
GiteaMirror commented 2026-04-12 17:16:51 -05:00
Author
Owner
Copy Link

@Neabigmo commented on GitHub (Feb 16, 2025):

I'm really troubled. Does Ollama require users to configure a proxy? And how should I configure the local port? If I don't configure the proxy, why does the Ollama server reject my access?

<!-- gh-comment-id:2661306366 --> @Neabigmo commented on GitHub (Feb 16, 2025): I'm really troubled. Does Ollama require users to configure a proxy? And how should I configure the local port? If I don't configure the proxy, why does the Ollama server reject my access?
GiteaMirror commented 2026-04-12 17:16:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 16, 2025):

Does Ollama require users to configure a proxy?

No. If you do have a proxy, you need to configure it to allow clients to connect to the ollama port.

<!-- gh-comment-id:2661441054 --> @rick-github commented on GitHub (Feb 16, 2025): > Does Ollama require users to configure a proxy? No. If you do have a proxy, you need to configure it to allow clients to connect to the ollama port.
GiteaMirror commented 2026-04-12 17:16:54 -05:00
Author
Owner
Copy Link

@trash-fish commented on GitHub (Feb 16, 2025):

真的很纠结，Ollama需要用户配置代理吗？本地端口怎么配置？如果不配置代理，Ollama服务器为什么会拒绝我的访问？

支配置https_proxy就行，别配置http_proxy否则会出错

<!-- gh-comment-id:2661442127 --> @trash-fish commented on GitHub (Feb 16, 2025): > 真的很纠结，Ollama需要用户配置代理吗？本地端口怎么配置？如果不配置代理，Ollama服务器为什么会拒绝我的访问？ 支配置https_proxy就行，别配置http_proxy否则会出错
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
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#5937
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?