-
-
Save mberman84/2ad782e90d18650dfdf42d677c18c520 to your computer and use it in GitHub Desktop.
| git clone https://github.com/OpenDevin/OpenDevin.git | |
| cd OpenDevin | |
| conda create -n od python=3.10 | |
| conda activate od | |
| docker ps | |
| (optional) install docker if not already installed | |
| docker pull ghcr.io/opendevin/sandbox | |
| export OPENAI_API_KEY={your key} | |
| (optional I had to install rust) curl --proto '=https' --tlsv1.2 -sSf [https://sh.rustup.rs](https://sh.rustup.rs/) | sh | |
| (optional) restart terminal | |
| python -m pip install -r requirements.txt | |
| (optional) orjson issue (MacOS) | |
| - pip uninstall orjson | |
| - pip install --no-cache-dir --only-binary :all: orjson | |
| uvicorn opendevin.server.listen:app --port 3000 |
@Orizune change 'export' to 'set' on windows
export OPENAI_API_KEY={your key}
'export' is not recongnized as as intern command (i'm in windows)
can somebody give me proper and latest installation steps.
Yes, this gist should definitely be updated. At least for linux, it was pretty far off.
For windows you need to set an environment variable, look up how to do that in Windows.
I had to generate conda with:
conda create -n od python=3.11
so that later, I could:
make build
which was the only way to generate some files that were not there.
requirements.txt needs at least the following:
datasets
pandas
litellm
termcolor
seaborn
docker
fastapi
uvicorn[standard]
ruff
mypy
langchain
langchain-core
langchain-community
llama-index
llama-index-vector-stores-chroma
chromadb
llama-index-embeddings-huggingface
llama-index-embeddings-azure-openai
llama-index-embeddings-ollama
google-generativeai
toml
pexpect
e2b
json_repair
browsergym
html2text
Ok, I finally have OpenDevin built, now what?
I wanted to give it some commands, but the folder is showing OpenDevin. Odd question, but how do I create a new project? I don't see it. I don't want it trashing the OpenDevin directory. I noticed it was immediately looking at the code in there, and I don't want OpenDevin messing with itself.
Pip install litellm
…
On Mon, Apr 8, 2024, 13:38 Anis111111 @.> wrote: @.* commented on this gist. ------------------------------ uvicorn opendevin.server.listen:app --port 3000 Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in run_codeFile "C:\Users\Anis--M\anaconda3\Scripts\uvicorn.exe_main.py", line 7, in File "C:\Users\Anis--M\anaconda3\Lib\site-packages\click\core.py", line 1157, in call return self.main(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\site-packages\click\core.py", line 1078, in main rv = self.invoke(ctx) ^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\site-packages\click\core.py", line 1434, in invoke return ctx.invoke(self.callback, **ctx.params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\site-packages\click\core.py", line 783, in invoke return __callback(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\main.py", line 409, in main run( File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\main.py", line 575, in run server.run() File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\server.py", line 65, in run return asyncio.run(self.serve(sockets=sockets)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\asyncio\runners.py", line 190, in run return runner.run(main) ^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\asyncio\runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\asyncio\base_events.py", line 653, in run_until_complete return future.result() ^^^^^^^^^^^^^^^ File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\server.py", line 69, in serve await self._serve(sockets) File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\server.py", line 76, in serveconfig.load()File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\config.py", line 433, in loadself.loaded_app = import_from_string(self.app http://self.app)^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\importer.py", line 22, in import_from_stringraise exc from NoneFile "C:\Users\Anis--M\anaconda3\Lib\site-packages\uvicorn\importer.py", line 19, in import_from_stringmodule = importlib.import_module(module_str)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "C:\Users\Anis--M\anaconda3\Lib\importlib_init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "", line 1204, in _gcd_import File "", line 1176, in _find_and_load File "", line 1147, in _find_and_load_unlocked File "", line 690, in _load_unlocked File "", line 940, in exec_module File "", line 241, in _call_with_frames_removed File "C:\Users\Anis--M\Desktop\OpenDevin\opendevin\server\listen.py", line 5, in import litellm ModuleNotFoundError: No module named 'litellm' what shoud i do?? — Reply to this email directly, view it on GitHub https://gist.github.com/mberman84/2ad782e90d18650dfdf42d677c18c520#gistcomment-5016655 or unsubscribe https://github.com/notifications/unsubscribe-auth/BHO7XPWRFKIIXPTRWYS52IDY4LW4XBFKMF2HI4TJMJ2XIZLTSKBKK5TBNR2WLJDUOJ2WLJDOMFWWLO3UNBZGKYLEL5YGC4TUNFRWS4DBNZ2F6YLDORUXM2LUPGBKK5TBNR2WLJDHNFZXJJDOMFWWLK3UNBZGKYLEL52HS4DFVRZXKYTKMVRXIX3UPFYGLK2HNFZXIQ3PNVWWK3TUUZ2G64DJMNZZDAVEOR4XAZNEM5UXG5FFOZQWY5LFVEYTEOJTG4YDSMJZU52HE2LHM5SXFJTDOJSWC5DF . You are receiving this email because you commented on the thread. Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub .
i have some issue and i do pip install litellm.. but it still have that issue
File "", line 1050, in _gcd_import
File "", line 1027, in _find_and_load
File "", line 1006, in _find_and_load_unlocked
File "", line 688, in _load_unlocked
File "", line 883, in exec_module
File "", line 241, in _call_with_frames_removed
File "/home/jenkins888/openDevin/OpenDevin-main/opendevin/server/listen.py", line 358, in
app.mount('/', StaticFiles(directory='./frontend/dist'), name='dist')
File "/home/jenkins888/.local/share/virtualenvs/OpenDevin-main-46NLFAxI/lib/python3.10/site-packages/starlette/staticfiles.py", line 59, in init
raise RuntimeError(f"Directory '{directory}' does not exist")
ERROR:root:<class 'RuntimeError'>: Directory './frontend/dist' does not exist
01:44:26 - opendevin:INFO: manager.py:46 - Closing 0 agent(s)...
01:44:26 - opendevin:INFO: manager.py:43 - Saving sessions...
01:44:26 - opendevin:INFO: msg_stack.py:41 - Saving messages...
over 12hours+ stuck over there
ERROR:root: File "C:\Users\Gamer\anaconda3\envs\od\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\Gamer\anaconda3\envs\od\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "C:\Users\Gamer\anaconda3\envs\od\Scripts\uvicorn.exe_main.py", line 7, in
sys.exit(main())
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\click\core.py", line 1157, in call
return self.main(*args, **kwargs)
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\click\core.py", line 1078, in main
rv = self.invoke(ctx)
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\click\core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\click\core.py", line 783, in invoke
return __callback(*args, **kwargs)
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\main.py", line 410, in main
run(
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\main.py", line 577, in run
server.run()
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\server.py", line 65, in run
return asyncio.run(self.serve(sockets=sockets))
File "C:\Users\Gamer\anaconda3\envs\od\lib\asyncio\runners.py", line 44, in run
return loop.run_until_complete(main)
File "C:\Users\Gamer\anaconda3\envs\od\lib\asyncio\base_events.py", line 649, in run_until_complete
return future.result()
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\server.py", line 69, in serve
await self._serve(sockets)
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\server.py", line 76, in serve
config.load()
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\config.py", line 434, in load
self.loaded_app = import_from_string(self.app)
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\importer.py", line 22, in import_from_string
raise exc from None
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\uvicorn\importer.py", line 19, in import_from_string
module = importlib.import_module(module_str)
File "C:\Users\Gamer\anaconda3\envs\od\lib\importlib_init.py", line 126, in import_module
return _bootstrap.gcd_import(name[level:], package, level)
File "", line 1050, in gcd_import
File "", line 1027, in find_and_load
File "", line 1006, in find_and_load_unlocked
File "", line 688, in load_unlocked
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\server\listen.py", line 15, in
import agenthub # noqa F401 (we import this to get the agents registered)
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\agenthub_init.py", line 3, in
from opendevin.controller.agent import Agent
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\controller_init.py", line 1, in
from .agent_controller import AgentController
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\controller\agent_controller.py", line 5, in
from opendevin.controller.agent import Agent
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\controller\agent.py", line 12, in
from opendevin.runtime.plugins import PluginRequirement
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\runtime_init.py", line 1, in
from .docker.exec_box import DockerExecBox
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\runtime\docker\exec_box.py", line 19, in
from opendevin.runtime.sandbox import Sandbox
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\runtime\sandbox.py", line 8, in
from opendevin.runtime.plugins.mixin import PluginMixin
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\runtime\plugins_init.py", line 2, in
from .agent_skills import AgentSkillsRequirement
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\runtime\plugins\agent_skills_init.py", line 4, in
from opendevin.runtime.plugins.agent_skills.agentskills import DOCUMENTATION
File "C:\Users\Gamer\Desktop\deviantdevin\opendevin\opendevin\runtime\plugins\agent_skills\agentskills.py", line 25, in
import docx
File "C:\Users\Gamer\anaconda3\envs\od\lib\site-packages\docx_init.py", line 9, in
from core import Docx
ERROR:root:<class 'ModuleNotFoundError'>: No module named 'core'
i need help i dunno what to do
@AgatheBauer @Bahrain-AI mind if I ask, does this work with Ollama and WSL for the CodeAct agent?
https://gist.github.com/mberman84/2ad782e90d18650dfdf42d677c18c520?permalink_comment_id=5008046#gistcomment-5008046 https://gist.github.com/mberman84/2ad782e90d18650dfdf42d677c18c520?permalink_comment_id=5012613#gistcomment-5012613
afdhali You will have to build the dist folder, by using npm commands. First you have to build declaration file in i18ln by building i18ln and then you will have to build dist.
npm run make-i18n
npm run build
running into
19:10:57 - opendevin:ERROR: [llm.py:114](http://llm.py:114/) - litellm.RateLimitError: RateLimitError: OpenAIException - Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}. Attempt #3 | You can customize these settings in the configuration.
I hope this helps someone else I had to remove miniconda and install anaconda3 and then create a requirements.txt and add the following:
datasets
pandas
litellm
termcolor
seaborn
docker
fastapi
uvicorn[standard]
ruff
mypy
langchain
langchain-core
langchain-community
llama-index
llama-index-vector-stores-chroma
chromadb
llama-index-embeddings-huggingface
llama-index-embeddings-azure-openai
llama-index-embeddings-ollama
google-generativeai
toml
termios
I then had an issue with llama-index-vector-stores-chroma with ERROR: Cannot install llama-index-vector-stores-chroma==0.1.2, llama-index-vector-stores-chroma==0.1.3, llama-index-vector-stores-chroma==0.1.4 and llama-index-vector-stores-chroma==0.1.5 because these package versions have conflicting dependencies.
I resolved that by running conda install onnxruntime -c conda-forge
I ran the server and got a further error
I have posted a question on backend issue here
All-Hands-AI/OpenHands#1472