github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 05:31:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9316] How to fix this failed to fix semaphore error? is it related to CONCURRENCY_TASK_LIMIt #6079

New Issue
Closed
opened 2026-04-12 17:24:32 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 17:24:32 -05:00
Owner
Copy Link

Originally created by @Jaykumaran on GitHub (Feb 24, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9316

What is the issue?

Hi,
I'm trying to fastgraphrag with ollama models. It uses instructor.from_openai service. Seems there is some problem with using ollama models.

I'm referring to : f2d90a3e23/fast_graphrag/_llm/_llm_openai.py (L60)

or="context canceled"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
time=2025-02-24T18:08:16.792+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:08:16 | 500 |          3m0s |       127.0.0.1 | POST     "/v1/chat/completions"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"
time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m54s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/24 - 18:10:48 | 500 |         2m30s |       127.0.0.1 | POST     "/v1/chat/completions"

I'm trying to run:

working_dir = "./WORKING_DIR/carol/ollama"

grag = GraphRAG(
    working_dir=working_dir,
    # n_checkpoints=2,
    domain = DOMAIN,
    example_queries="\n".join(EXAMPLE_QUERIES),
    entity_types=ENTITY_TYPES,
    config=GraphRAG.Config(
        llm_service=OpenAILLMService(
            model = "llama3.1:8b",
            base_url="http://localhost:11434/v1",
            api_key="ollama",
            mode = instructor.Mode.JSON,
            client="openai",
            
        ),
        embedding_service=OpenAIEmbeddingService(
            model = "mxbai-embed-large" , # mxbai-embed-large
            base_url="http://localhost:11434/v1",
            api_key="ollama",
            embedding_dim=768,  # for mxbai-embed-large - 1024
            # client="openai"
            
        )
        
    )
)


with open("./book.txt") as f:
    grag.insert(f.read())
    
    
print(grag.query("Who is Scrooge?").response)

When i set max_concurrent=int(os.getenv("CONCURRENT_TASK_LIMIT", 1024) as 1 things works as expected.

But then there is no point in using it as async operation.

Looking out for some insights on this.

Image

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @Jaykumaran on GitHub (Feb 24, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9316 ### What is the issue? Hi, I'm trying to fastgraphrag with ollama models. It uses `instructor.from_openai` service. Seems there is some problem with using ollama models. I'm referring to : https://github.com/circlemind-ai/fast-graphrag/blob/f2d90a3e232b80c50efb22667dd16cc2ac6e97de/fast_graphrag/_llm/_llm_openai.py#L60 ``` or="context canceled" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" time=2025-02-24T18:08:16.792+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:08:16 | 500 | 3m0s | 127.0.0.1 | POST "/v1/chat/completions" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" time=2025-02-24T18:10:48.036+05:30 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m54s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/24 - 18:10:48 | 500 | 2m30s | 127.0.0.1 | POST "/v1/chat/completions" ``` I'm trying to run: ``` working_dir = "./WORKING_DIR/carol/ollama" grag = GraphRAG( working_dir=working_dir, # n_checkpoints=2, domain = DOMAIN, example_queries="\n".join(EXAMPLE_QUERIES), entity_types=ENTITY_TYPES, config=GraphRAG.Config( llm_service=OpenAILLMService( model = "llama3.1:8b", base_url="http://localhost:11434/v1", api_key="ollama", mode = instructor.Mode.JSON, client="openai", ), embedding_service=OpenAIEmbeddingService( model = "mxbai-embed-large" , # mxbai-embed-large base_url="http://localhost:11434/v1", api_key="ollama", embedding_dim=768, # for mxbai-embed-large - 1024 # client="openai" ) ) ) with open("./book.txt") as f: grag.insert(f.read()) print(grag.query("Who is Scrooge?").response) ``` When i set `max_concurrent=int(os.getenv("CONCURRENT_TASK_LIMIT", 1024) as 1` things works as expected. But then there is no point in using it as `async` operation. Looking out for some insights on this. ![Image](https://github.com/user-attachments/assets/b8c5bf5e-5620-43ec-bc8a-2db07e82e5f5) ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 17:24:32 -05:00
GiteaMirror commented 2026-04-12 17:24:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 24, 2025):

Increase OLLAMA_NUM_PARALLEL to allow more concurrent completions. However, the embedding interface doesn't support parallel completions, so you would need to run multiple servers to achieve that. I suspect that the reason for the semaphore failures is that there are many pending requests and the client has a 3 minute timeout, and by the time ollama gets around to processing the queued requests, the client has closed the connection.

<!-- gh-comment-id:2678495232 --> @rick-github commented on GitHub (Feb 24, 2025): Increase `OLLAMA_NUM_PARALLEL` to allow more concurrent completions. However, the embedding interface doesn't support parallel completions, so you would need to run multiple servers to achieve that. I suspect that the reason for the semaphore failures is that there are many pending requests and the client has a 3 minute timeout, and by the time ollama gets around to processing the queued requests, the client has closed the connection.
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#6079
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?