Calling `langgraph up` i get the error `langgraph-api-1 | FileNotFoundError: [Errno 2] No such file or directory: '/deps/langgraph-example-pyproject/my_agent\\agent.py`

[Andrei-Tocut]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangGraph/LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [X] I am sure that this is a bug in LangGraph/LangChain rather than my code.
• [X] I am sure this is better as an issue rather than a GitHub discussion, since this is a LangGraph bug and not a design question.

Example Code

langgraph up

Error Message and Stack Trace (if applicable)

langgraph-api-1       | 2024-10-09T06:31:32.686169Z [error    ] Traceback (most recent call last):
langgraph-api-1       |   File "/usr/local/lib/python3.11/site-packages/starlette/routing.py", line 693, in lifespan
langgraph-api-1       |     async with self.lifespan_context(app) as maybe_state:
langgraph-api-1       |   File "/usr/local/lib/python3.11/contextlib.py", line 210, in __aenter__
langgraph-api-1       |     return await anext(self.gen)
langgraph-api-1       |            ^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/api/langgraph_api/lifespan.py", line 23, in lifespan
langgraph-api-1       |   File "/api/langgraph_api/shared/graph.py", line 205, in collect_graphs_from_env
langgraph-api-1       |   File "/usr/local/lib/python3.11/site-packages/langchain_core/runnables/config.py", line 590, in run_in_executor
langgraph-api-1       |     return await asyncio.get_running_loop().run_in_executor(
langgraph-api-1       |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
langgraph-api-1       |     result = self.fn(*self.args, **self.kwargs)
langgraph-api-1       |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/usr/local/lib/python3.11/site-packages/langchain_core/runnables/config.py", line 581, in wrapper
langgraph-api-1       |     return func(*args, **kwargs)
langgraph-api-1       |            ^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/api/langgraph_api/shared/graph.py", line 233, in _graph_from_spec
langgraph-api-1       |   File "<frozen importlib._bootstrap_external>", line 936, in exec_module
langgraph-api-1       |   File "<frozen importlib._bootstrap_external>", line 1073, in get_code
langgraph-api-1       |   File "<frozen importlib._bootstrap_external>", line 1130, in get_data
langgraph-api-1       | FileNotFoundError: [Errno 2] No such file or directory: '/deps/langgraph-example-pyproject/my_agent\\agent.py'
langgraph-api-1       |  [uvicorn.error] api_revision=e09c235 api_variant=licensed
langgraph-api-1       | 2024-10-09T06:31:32.686561Z [error    ] Application startup failed. Exiting. [uvicorn.error] api_revision=e09c235 api_variant=licensed
langgraph-api-1 exited with code 3

Description

I want to test the langgraph locally fist before deploy and when i run langgraph up i get the following error langgraph-api-1 | FileNotFoundError: [Errno 2] No such file or directory: '/deps/langgraph-example-pyproject/my_agent\\agent.py. While i encountered this issue i cloned the example project from this and attepmpted to serve it up but i got the same issue. Might it be because i am using windows? But it shouldnt matter since it runs in a docker container.

System Info

langgraph.json

` { "dependencies": ["."], "graphs": { "agent": "./my_agent/agent.py:graph" }, "env": ".env" }

`

pyproject.toml

` [tool.poetry] name = "my_agent" version = "0.1.0" description = "Example LangGraph project for deployment to LangGraph Cloud" authors = [ "langchain-ai" ] packages = [ { include = "my_agent" }, ]

[tool.poetry.dependencies] python = ">=3.9.0,<3.13" langgraph = "^0.2.0" langchain_anthropic = "^0.1.0" langchain_core = "^0.2.0" langchain_openai = "^0.1.0" tavily-python = "^0.3.0" langchain_community = "^0.2.0"

[build-system] requires = ["poetry-core"] build-backend = "poetry.core.masonry.api" `

OS Name Microsoft Windows 10 Enterprise Version 10.0.19045 Build 19045

❯ langchain --version langchain-cli 0.0.31

[Andrei-Tocut]

this is the config for the other project

` [tool.poetry] name = "quinn_agent" version = "0.1.0" description = "" readme = "README.md"

packages = [ { include = "quinn_agent" }, ]

[tool.poetry.dependencies] python = ">=3.12,<3.13" langchain = "^0.3.2" langchain-openai = "^0.2.2" langchainhub = "^0.1.21" langchain-pinecone = "^0.2.0" python-dotenv = "^1.0.1" langgraph = "^0.2.34" neo4j = "^5.25.0" lark = "^1.2.2" pydantic = "^2.9.2"

[build-system] requires = ["poetry-core"] build-backend = "poetry.core.masonry.api" `

{ "python_version": "3.12", "dependencies": [ "." ], "graphs": { "agent": "./quinn_agent/agent.py:graph" }, "env": ".env" } File structure

[vbarda]

@Andrei-Tocut yes, Windows is not currently supported but we're working on adding support

[p4norman]

+1

[githubramu]

+1 I see the error like below...tryies to use npm to install for python instead of pip

[langgraph-api 3/5] RUN cd /deps/langgraph_001 && npm i:

[vbarda]

This should be fixed now, but feel free to reopen if you're still running into it. We also now recommend using langgraph dev for local testing: https://langchain-ai.github.io/langgraph/tutorials/langgraph-platform/local-server/

[droideronline]

I am Still facing the same relative path error on windows, any help would be appreciated

[droideronline]

As a Temporary Fix, we could create a main.py in same directory as langgraph.json with

from agents.graph import create_workflow

# useful for LangGraph Server
graph = create_workflow()

And tweak the config to match the path with

    "python_version": "3.12",
    "dockerfile_lines": [],
    "dependencies": [
      "."
    ],
    "graphs": {
      "agent": "./main.py:graph"
    },
    "env": ".env"
  }

PS: This works perfectly fine for me

[mdanish-kh]

This should be fixed now, but feel free to reopen if you're still running into it. We also now recommend using langgraph dev for local testing

@vbarda Looks like the fix (I'm presuming it's https://github.com/langchain-ai/langgraph/pull/2480) was merged in a separate branch, not main, and hasn't been shipped to a release. Can we re-open this issue until the fix has made its way in a release?

Edit: Looks like it was fixed for langgraph dev, but if you run langgraph build -t <image_name> and then use docker-compose file to run the graph, it would fail

In the output of langgraph build -t <img_name>:

---

For Windows users, the workaround is to run the same langgraph build command from WSL (Windows Subsystem for Linux)

[lokinnnnnn]

It has been several months so far, hasn't it been fixed yet? I still encounter this problem now.

[saminkhan1]

bumping this, facing a similar issue

[eyurtsev]

Will resolve next week. If you're blocked by this you can use WSL in the meantime (https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux).

[dqbd]

Should be fixed in https://github.com/langchain-ai/langgraph/pull/3318

[willy20040711]

I have the similar problem as below, when I deploy my graph to langGraph platform studio.

my pyproject.toml `[tool.poetry] name = "sample_agent" version = "0.1.0" description = "Starter" authors = ["Markus Ecker [email protected]"] license = "MIT" [project] name = "sample_agent" version = "0.0.1" requires-python = ">=3.10,<4.0" dependencies = [ "langchain-openai>=0.2.1", "langchain-anthropic>=0.2.1", "langchain>=0.3.1", "openai>=1.51.0", "langchain-community>=0.3.1", "copilotkit==0.1.39", "uvicorn>=0.31.0", "python-dotenv>=1.0.1", "langchain-core>=0.3.25", "langgraph-cli[inmem]>=0.1.64", "langchain-mcp-adapters (==0.0.5)", "fastmcp>=0.4.1", "langgraph (>=0.3.11,<0.4.0)" ]

[build-system] requires = ["setuptools >= 61.0"] build-backend = "setuptools.build_meta"

[tool.poetry.dependencies] python = ">=3.10,<4.0" langchain-openai = "^0.2.1" langchain-anthropic = "^0.2.1" langchain = "^0.3.1" openai = "^1.51.0" langchain-community = "^0.3.1" copilotkit = "0.1.39" uvicorn = "^0.31.0" python-dotenv = "^1.0.1" langchain-core = "^0.3.25" langgraph-cli = {extras = ["inmem"], version = "^0.1.64"} langchain-mcp-adapters = "^0.0.3" fastmcp = "^0.4.1" langgraph = "^0.3.5"

[tool.poetry.scripts] demo = "sample_agent.demo:main"

[tool.ruff] lint.select = [ "E", # pycodestyle "F", # pyflakes "I", # isort "D", # pydocstyle "D401", # First line should be in imperative mood "T201", "UP", ] lint.ignore = [ "UP006", "UP007", # We actually do want to import from typing_extensions "UP035", # Relax the convention by not requiring documentation for every function parameter. "D417", "E501", ] [tool.ruff.lint.per-file-ignores] "tests/*" = ["D", "UP"] [tool.ruff.lint.pydocstyle] convention = "google"

[tool.mypy] ignore_missing_imports = true ` Below is error message. But langgraph work normally when is running in local.

[ERROR] Background run failed Traceback (most recent call last): File "/api/langgraph_api/worker.py", line 128, in worker File "/usr/local/lib/python3.12/asyncio/tasks.py", line 520, in wait_for return await fut ^^^^^^^^^ File "/api/langgraph_api/stream.py", line 293, in consume File "/api/langgraph_api/stream.py", line 283, in consume File "/api/langgraph_api/stream.py", line 234, in astream_state File "/api/langgraph_api/asyncio.py", line 72, in wait_if_not_done File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/__init__.py", line 2313, in astream async for _ in runner.atick( File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 527, in atick _panic_or_proceed( File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 619, in _panic_or_proceed raise exc File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/retry.py", line 128, in arun_with_retry return await task.proc.ainvoke(task.input, config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 583, in ainvoke input = await step.ainvoke(input, config, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 371, in ainvoke ret = await asyncio.create_task(coro, context=context) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/deps/mcp_langgraph2025/src/custom_agent/graph.py", line 47, in chat_node async with MultiServerMCPClient(mcp_config) as mcp_client: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/langchain_mcp_adapters/client.py", line 256, in __aenter__ await self.connect_to_server_via_stdio(server_name, **connection_dict) File "/usr/local/lib/python3.12/site-packages/langchain_mcp_adapters/client.py", line 196, in connect_to_server_via_stdio stdio_transport = await self.exit_stack.enter_async_context(stdio_client(server_params)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/contextlib.py", line 659, in enter_async_context result = await _enter(cm) ^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/mcp/client/stdio.py", line 100, in stdio_client process = await anyio.open_process( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/anyio/_core/_subprocesses.py", line 190, in open_process return await get_async_backend().open_process( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 2561, in open_process process = await asyncio.create_subprocess_exec( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/asyncio/subprocess.py", line 224, in create_subprocess_exec transport, protocol = await loop.subprocess_exec( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "uvloop/loop.pyx", line 2841, in subprocess_exec File "uvloop/loop.pyx", line 2799, in __subprocess_run File "uvloop/handles/process.pyx", line 611, in uvloop.loop.UVProcessTransport.new File "uvloop/handles/process.pyx", line 112, in uvloop.loop.UVProcess._init FileNotFoundError: [Errno 2] No such file or directory During task with name 'chat_node' and id '11b2b974-3362-762e-375d-e5a1df378a6e'

[sethi-ishmeet]

@willy20040711 Did you find a solution for this yet? I am running in the same error when running the docker image. It works fine on LangGraph dev.