mervinpraison / praisonai Goto Github PK

ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/staticfiles.py", line 202, in check_config
stat_result = await anyio.to_thread.run_sync(os.stat, self.directory)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/asyncio/futures.py", line 287, in await
yield self # This tells Task to wait for completion.
^^^^^^^^^^
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/asyncio/tasks.py", line 349, in __wakeup
future.result()
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/asyncio/futures.py", line 203, in result
raise self._exception.with_traceback(self._exception_tb)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: 'public'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 426, in run_asgi
result = await app( # type: ignore[func-returns-value]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in call
return await self.app(scope, receive, send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/engineio/async_drivers/asgi.py", line 74, in call
await self.other_asgi_app(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in call
await super().call(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/applications.py", line 123, in call
await self.middleware_stack(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/middleware/errors.py", line 186, in call
raise exc
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/middleware/errors.py", line 164, in call
await self.app(scope, receive, _send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/middleware/cors.py", line 85, in call
await self.app(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 65, in call
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
raise exc
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/routing.py", line 756, in call
await self.middleware_stack(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/routing.py", line 776, in app
await route.handle(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/routing.py", line 485, in handle
await self.app(scope, receive, send)
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/staticfiles.py", line 99, in call
await self.check_config()
File "/Users/praison/miniconda3/envs/praisonai/lib/python3.11/site-packages/starlette/staticfiles.py", line 204, in check_config
raise RuntimeError(
RuntimeError: StaticFiles directory 'public' does not exist.
Settings updated

RuntimeError: StaticFiles directory 'public' does not exist.
2024-06-19 22:43:33,142 - 8622177088 - utils.py-utils:50 - ERROR: str expected, not NoneType
Traceback (most recent call last):
File "/Users/praison/.pyenv/versions/3.11.0/lib/python3.11/site-packages/chainlit/utils.py", line 44, in wrapper
return await user_function(**params_values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/praison/.pyenv/versions/3.11.0/lib/python3.11/site-packages/praisonai/chainlit_ui.py", line 143, in start_chat
await on_settings_update(settings)
File "/Users/praison/.pyenv/versions/3.11.0/lib/python3.11/site-packages/praisonai/chainlit_ui.py", line 152, in on_settings_update
os.environ["OPENAI_API_KEY"] = config_list[0]['api_key']
~~~~~~~~~~^^^^^^^^^^^^^^^^^^
File "", line 683, in setitem
File "", line 757, in encode
TypeError: str expected, not NoneType

@MervinPraison , brilliant! thanks a lot.

I start this issue to collect Ideas for future enhancements.

• to deploy anywhere, skypilot would you let deploy on any cloud or on premise.
  SkyPilot: Run LLMs, AI, and Batch jobs on any cloud. Get maximum savings, highest GPU availability, and managed execution—all with a simple interface.

backends:

• phidata:
  Build AI Assistants with function calling and connect LLMs to external tools.
• DSPy
  it's a class of it's own, and I don't know whether it fits into PraisonAI

Feature request: how to create secondary market research agent , with customisation

Please add example and yaml file , planning to create fastapi for it , user will add which section/ company related, geography related information as input..

Output to be generated like report

im trying to execute on windows with ollama an llama2 model

after some minutes of working i get this error:

python -m praisonai --init give me the latest news about openai
(windows does not recognize praison as a command  )


Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\praisonai\__main__.py", line 10, in <module>
    main()
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\praisonai\__main__.py", line 7, in main
    praison_ai.main()
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\praisonai\cli.py", line 76, in main
    self.agent_file = generator.generate()
                      ^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\praisonai\auto.py", line 45, in generate
    response = self.client.chat.completions.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\instructor\patch.py", line 570, in new_create_sync
    response = retry_sync(
               ^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\instructor\patch.py", line 387, in retry_sync
    for attempt in max_retries:
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\tenacity\__init__.py", line 347, in __iter__
    do = self.iter(retry_state=retry_state)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\tenacity\__init__.py", line 325, in iter
    raise retry_exc.reraise()
          ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\tenacity\__init__.py", line 158, in reraise
    raise self.last_attempt.result()
          ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.1008.0_x64__qbz5n2kfra8p0\Lib\concurrent\futures\_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.1008.0_x64__qbz5n2kfra8p0\Lib\concurrent\futures\_base.py", line 401, in __get_result
    raise self._exception
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\instructor\patch.py", line 441, in retry_sync
    raise e
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\instructor\patch.py", line 402, in retry_sync
    return process_response(
           ^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\instructor\patch.py", line 207, in process_response
    model = response_model.from_response(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\instructor\function_calls.py", line 131, in from_response
    return cls.model_validate_json(
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\oldla\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\pydantic\main.py", line 561, in model_validate_json
    return cls.__pydantic_validator__.validate_json(json_data, strict=strict, context=context)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 1 validation error for TeamStructure
  Invalid JSON: EOF while parsing an object at line 75 column 0 [type=json_invalid, input_value='{\n"roles": {\n"narrativ...n\n\n\n\n\n\n\n\n\n\n\n', input_type=str]
    For further information visit https://errors.pydantic.dev/2.7/v/json_invalid

any clue how to solve?

Can you support azure open ai credentials?

it would be nice if praisonAI always honored the agents.yaml file, even if it generates the agents itself. It could append to that agent configuration if an external agents.yaml file is provided

Pretty awesome project but tools are needed for advanced usage. Since there are alot of tools which langchain supports and crewai also has some tools support which can help in doing some advance task so in my opinion when you start adding tools to this project then start from google serper(serper.dev),brave search,duck duck go search,wikipedia and maybe after these you can add yahoo finance,youtube,stack exchange etc.i will study source code too and will see in what other form can contribute in future.This will be good starting point for tools addition to this awesome project in my opinion :-))

I use no virtual environment... so it is the default python environment.
I install praisonai and run it... regardless which parameter I use - ollama, UI, init, etc... it always asks for openAI API key.

I changed the url and the model in auto.py, cli.py the url_base .. but stil... I tried to set OPENAI_API_KEY=fake . Still doesnt work...

Cant find where is this hardcoded COMPULSORY requirement about this key so I have to use OpenAI

openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

I dont understand the requirement of a key from my side... There are so many solutions how to see if I want to use OpenAI... but that...
Can you make it simple for me and to ask nicely if I want to use openAI or not in the beginning...

Hi,

Great project!

I've added the following to the .env file:
OPENAI_MODEL_NAME="mixtral-8x7b-32768"
OPENAI_API_KEY="gsk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
OPENAI_API_BASE="https://api.groq.com/openai/v1"

but i get the following error:

Traceback (most recent call last):
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/bin/praisonai", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/praisonai/__main__.py", line 7, in main
    praison_ai.main()
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/praisonai/cli.py", line 76, in main
    self.agent_file = generator.generate()
                      ^^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/praisonai/auto.py", line 45, in generate
    response = self.client.chat.completions.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/instructor/patch.py", line 570, in new_create_sync
    response = retry_sync(
               ^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/instructor/patch.py", line 387, in retry_sync
    for attempt in max_retries:
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/tenacity/__init__.py", line 347, in __iter__
    do = self.iter(retry_state=retry_state)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/tenacity/__init__.py", line 325, in iter
    raise retry_exc.reraise()
          ^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/tenacity/__init__.py", line 158, in reraise
    raise self.last_attempt.result()
          ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/concurrent/futures/_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/instructor/patch.py", line 390, in retry_sync
    response = func(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/openai/_utils/_utils.py", line 275, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/openai/resources/chat/completions.py", line 667, in create
    return self._post(
           ^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/openai/_base_client.py", line 1233, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/openai/_base_client.py", line 922, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/home/andrea/repos/scripts/AI/praisonAI/venv/lib/python3.11/site-packages/openai/_base_client.py", line 1013, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.AuthenticationError: Error code: 401 - {'error': {'message': 'Invalid API Key', 'type': 'invalid_request_error', 'code': 'invalid_api_key'}}```


On the other hand, if I export the variables like so:
export OPENAI_MODEL_NAME="mixtral-8x7b-32768"
export OPENAI_API_KEY="gsk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
export OPENAI_API_BASE="https://api.groq.com/openai/v1"

Groq works perfectly fine.

tried many times in different configurations, but always reached this error: Building wheels for collected packages: chroma-hnswlib
Building wheel for chroma-hnswlib (pyproject.toml) ... error
error: subprocess-exited-with-error

× Building wheel for chroma-hnswlib (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [5 lines of output]
running bdist_wheel
running build
running build_ext
building 'hnswlib' extension
error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for chroma-hnswlib
Failed to build chroma-hnswlib
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (chroma-hnswlib)

experiencing an error with a Python script. The error message indicates that a subprocess call to conda run failed with a non-zero exit status of 1. why command that failed is trying to run a Python script (train.py) within a conda environment named praison_env
virtual environment, it's activated

this is the error ERROR conda.cli.main_run:execute(125): conda run python -u /usr/local/lib/python3.10/dist-packages/praisonai/train.py train failed. (See above for error)

subprocess.CalledProcessError: Command '['conda', 'run', '--no-capture-output', '--name', 'praison_env', 'python', '-u', '/usr/local/lib/python3.10/dist-packages/praisonai/train.py', 'train']' returned non-zero exit status 1.

I just experimented with praisonai. It is promising project. To start the project it seems that parisonai rely on Openai exclusively to build the project. When I exported other model to os.environemnt i get error. If this is the case, it would help to tell the user about this. Specially that the target user is not advanced programmer. I also think that using export and such will deter many users who don't know anything about programming. I think a wrapper around this which ask clearly what model you want to use to build agents.yaml? then enter your api key for that model. Or one config file that has all the info about apis keys in one place.
I asked :
praisonai --init create a crew to scan houses and apartments for sale user input the country, price, square meters, number of rooms, and other preferences. The output should include list of houses, the urls, and other information about the house or apratment like price, location, number of rooms etc
I got cool result :
framework: crewai
topic: create a crew to scan houses and apartments for sale user input the country,
price, square meters, number of rooms, and other preferences. The output should
include list of houses, the urls, and other information about the house or apratment
like price, location, number of rooms etc
roles:
data_collector:
backstory: Experienced in web scraping and data collection, with a focus on real
estate.
goal: Gather house listing data based on user preferences.
role: Data Collector
tasks:
collect_listings_task:
description: Scrape websites for house and apartment listings based on user
preferences (country, price, square meters, number of rooms, etc.)
expected_output: Raw data containing house and apartment listings, including
URLs, price, location, and number of rooms.
tools:
- ''
data_processor:
backstory: Skilled in data processing and organization, particularly in cleaning
and formatting scraped data.
goal: Process and organize the collected data.
role: Data Processor
tasks:
process_listings_task:
description: Filter, clean, and format the raw listing data to remove duplicates
and errors. Organize the data in a structured format.
expected_output: Clean and organized dataset of house and apartment listings,
ready for analysis.
tools:
- ''
data_analyzer:
backstory: Expert in data analysis and presentation, with a focus on delivering
actionable insights to users.
goal: Analyze and compile the processed data into a final user-friendly output.
role: Data Analyzer
tasks:
analyze_listings_task:
description: Analyze the cleaned data to generate a final list of houses and
apartments for sale. Ensure the output includes URLs, price, location, square
meters, and number of rooms.
expected_output: Comprehensive list of houses and apartments for sale, including
detailed information such as URLs, price, location, square meters, and number
of rooms.
tools:
- ''
dependencies: []

looking more at this results, it still require polishing. It is not ready to give meaningful outcome. Not clear what kind of input the crews require and not clear if this crew are ready to do their work. The tool section is empty which is confusing.
My point is that a demo of a fully functional crew that can professionally perform as experts would attract way more interest than a demo of a tool that make creating agents easier.

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
anaconda-cloud-auth 0.1.4 requires pydantic<2.0, but you have pydantic 2.6.4 which is incompatible.

When I change to pydantic<2.0, the dependency issue continues to trickle down.

I'm having this same issue when I tried to install and run CrewAI last weekend. (Already raised an issue there but have yet to hear back.)

Thanks.

Fabric (https://github.com/danielmiessler/fabric/tree/main) uses praisonAI as a library. However, praison parses the command line arguments in the main routine, which means that it takes takes fabrics's, which are incompatible with praison's. As a result, agent_file may get overwritten with other content.

https://github.com/danielmiessler/fabric/blob/45fcc547d53ecac2edf52f59f81a5e272cb28878/installer/client/cli/utils.py#L488-L490

praisonAI should only parse command line arguments when called from the command line. It would be nice if it provided an entry point so that it can be used as a library.

WARNING: Translation file for de-DE not found. Using default translation en-US. As soon as I write something via praison ai chat in the chat window, praison ai crashes or goes to login window!?!

`ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/Users/test/praisonai-package/praisonai/ui/sql_alchemy.py", line 81, in execute_sql
await session.begin()
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/ext/asyncio/session.py", line 1865, in start
await greenlet_spawn(
^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/util/concurrency.py", line 99, in greenlet_spawn
_not_implemented()
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/util/concurrency.py", line 79, in _not_implemented
raise ValueError(
ValueError: the greenlet library is required to use this function. No module named 'greenlet'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/test/praisonai-package/praisonai/ui/sql_alchemy.py", line 95, in execute_sql
await session.rollback()
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/ext/asyncio/session.py", line 999, in rollback
await greenlet_spawn(self.sync_session.rollback)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/util/concurrency.py", line 99, in greenlet_spawn
_not_implemented()
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/util/concurrency.py", line 79, in _not_implemented
raise ValueError(
ValueError: the greenlet library is required to use this function. No module named 'greenlet'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 426, in run_asgi
result = await app( # type: ignore[func-returns-value]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in call
return await self.app(scope, receive, send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/engineio/async_drivers/asgi.py", line 74, in call
await self.other_asgi_app(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in call
await super().call(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/applications.py", line 123, in call
await self.middleware_stack(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/middleware/errors.py", line 186, in call
raise exc
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/middleware/errors.py", line 164, in call
await self.app(scope, receive, _send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/middleware/cors.py", line 93, in call
await self.simple_response(scope, receive, send, request_headers=headers)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/middleware/cors.py", line 148, in simple_response
await self.app(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 65, in call
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
raise exc
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/routing.py", line 756, in call
await self.middleware_stack(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/routing.py", line 776, in app
await route.handle(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/routing.py", line 297, in handle
await self.app(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/routing.py", line 77, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
raise exc
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/starlette/routing.py", line 72, in app
response = await func(request)
^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/fastapi/routing.py", line 278, in app
raw_response = await run_endpoint_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/fastapi/routing.py", line 191, in run_endpoint_function
return await dependant.call(**values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/chainlit/server.py", line 738, in get_user_threads
res = await data_layer.list_threads(payload.pagination, payload.filter)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/praisonai-package/praisonai/ui/sql_alchemy.py", line 256, in list_threads
await self.get_all_user_threads(user_id=filters.userId) or []
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/praisonai-package/praisonai/ui/sql_alchemy.py", line 484, in get_all_user_threads
user_threads = await self.execute_sql(
^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/praisonai-package/praisonai/ui/sql_alchemy.py", line 79, in execute_sql
async with self.async_session() as session:
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/asyncio/tasks.py", line 349, in __wakeup
future.result()
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/asyncio/futures.py", line 203, in result
raise self._exception.with_traceback(self._exception_tb)
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/asyncio/tasks.py", line 277, in __step
result = coro.send(None)
^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/ext/asyncio/session.py", line 1025, in close
await greenlet_spawn(self.sync_session.close)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/util/concurrency.py", line 99, in greenlet_spawn
_not_implemented()
File "/Users/test/miniconda3/envs/langgraph/lib/python3.11/site-packages/sqlalchemy/util/concurrency.py", line 79, in _not_implemented
raise ValueError(
ValueError: the greenlet library is required to use this function. No module named 'greenlet'`

Error as below. Not sure it's from crewai or praisonai. Need help, thanks!!

2024-06-21 12:16:31 - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:31 - Context impl SQLiteImpl.
2024-06-21 12:16:31 - Will assume non-transactional DDL.
2024-06-21 12:16:32 - Context impl SQLiteImpl.
2024-06-21 12:16:32 - Will assume non-transactional DDL.
2024-06-21 12:16:32 - Context impl SQLiteImpl.
2024-06-21 12:16:32 - Will assume non-transactional DDL.
2024-06-21 12:16:32 - Context impl SQLiteImpl.
2024-06-21 12:16:32 - Will assume non-transactional DDL.
 [2024-06-21 12:16:32][DEBUG]: == Working Agent: Concept Researcher
 [2024-06-21 12:16:32][INFO]: == Starting Task: Research existing literature, articles, and real-world scenarios of AI and human interactions to uncover potential conflicts and resolutions.
2024-06-21 12:16:33 - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-06-21 12:16:33 - 'generator' object does not support the context manager protocol
Traceback (most recent call last):
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/chainlit/utils.py", line 44, in wrapper
    return await user_function(**params_values)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/free/chainlit-gongan/app.py", line 194, in main
    result = agents_generator.generate_crew_and_kickoff()
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/praisonai/agents_generator.py", line 269, in generate_crew_and_kickoff
    response = crew.kickoff()
               ^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/crew.py", line 271, in kickoff
    result = self._run_sequential_process()
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/crew.py", line 357, in _run_sequential_process
    output = task.execute(context=task_output)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/task.py", line 187, in execute
    result = self._execute(
             ^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/task.py", line 196, in _execute
    result = agent.execute_task(
             ^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/agent.py", line 243, in execute_task
    result = self.agent_executor.invoke(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain/chains/base.py", line 163, in invoke
    raise e
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain/chains/base.py", line 153, in invoke
    self._call(inputs, run_manager=run_manager)
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/agents/executor.py", line 128, in _call
    next_step_output = self._take_next_step(
                       ^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain/agents/agent.py", line 1138, in _take_next_step
    [
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain/agents/agent.py", line 1138, in <listcomp>
    [
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/crewai/agents/executor.py", line 192, in _iter_next_step
    output = self.agent.plan(  # type: ignore #  Incompatible types in assignment (expression has type "AgentAction | AgentFinish | list[AgentAction]", variable has type "AgentAction")
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain/agents/agent.py", line 397, in plan
    for chunk in self.runnable.stream(inputs, config={"callbacks": callbacks}):
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 2875, in stream
    yield from self.transform(iter([input]), config, **kwargs)
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 2862, in transform
    yield from self._transform_stream_with_config(
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 1881, in _transform_stream_with_config
    chunk: Output = context.run(next, iterator)  # type: ignore
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 2826, in _transform
    for output in final_pipeline:
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 1282, in transform
    for ichunk in input:
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 4736, in transform
    yield from self.bound.transform(
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 1300, in transform
    yield from self.stream(final, config, **kwargs)
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 249, in stream
    raise e
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 229, in stream
    for chunk in self._stream(messages, stop=stop, **kwargs):
  File "/home/songz/miniconda3/envs/free-cl-gongan/lib/python3.11/site-packages/langchain_openai/chat_models/base.py", line 480, in _stream
    with self.client.create(messages=message_dicts, **params) as response:
TypeError: 'generator' object does not support the context manager protocol
2024-06-21 12:16:34 - Connection pool is full, discarding connection: us-api.i.posthog.com. Connection pool size: 10
2024-06-21 12:16:34 - Connection pool is full, discarding connection: us-api.i.posthog.com. Connection pool size: 10
2024-06-21 12:16:34 - Connection pool is full, discarding connection: us-api.i.posthog.com. Connection pool size: 10

Dear maintainers, greetings from CommandDash!

We are a tool to turn docs and examples of your library into a code generation AI agent which helps devs directly generate code for your library as per their requirements.

Our team came across Praison AI for managing LLM systems and figured it could be helpful for new developers building on it to have one such agent. It's ready and is accessible on: Web (Try here!) | VSCode Extension

You can link this in your readme as a badge:

<a href="https://app.commanddash.io/agent?github=https://github.com/MervinPraison/PraisonAI"><img src="https://img.shields.io/badge/AI-Code%20Assist-EB9FDA"></a>

Please feel free to mention it if you believe this could be helpful for new users. Or, close the issue if not. 🙏🏻

The agent is free to use, fully safe (no data retained) and auto-refreshes to stay upto date.

Best wishes!

Hello and thanks for this tool,

I've just watched your video and I think that this repo deserves a free software license, such as GPL, MIT or Apache.

Best,
Orkut

Is it possible to pass in a CSV list of, for me URLs, but for others maybe something else, and then the agents work through the list each in turn? In which case, how do I code that?

pip install praisonai

Environment:
MacOS Sonoma
Python 3.11
Ollama server running
OPENAI_API_KEY=fake
OPENAI_API_BASE=http://localhost:11434/api/generate
OPENAI_MODEL_NAME=mistral

Run Output:

Traceback (most recent call last):
File "/Users/joliva/.pyenv/versions/3.11.6/bin/praisonai", line 8, in
sys.exit(main())
^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/praisonai/main.py", line 7, in main
praison_ai.main()
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/praisonai/cli.py", line 154, in main
self.agent_file = generator.generate()
^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/praisonai/auto.py", line 44, in generate
response = self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/instructor/patch.py", line 570, in new_create_sync
response = retry_sync(
^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/instructor/patch.py", line 387, in retry_sync
for attempt in max_retries:
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/tenacity/init.py", line 347, in iter
do = self.iter(retry_state=retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/tenacity/init.py", line 325, in iter
raise retry_exc.reraise()
^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/tenacity/init.py", line 158, in reraise
raise self.last_attempt.result()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/concurrent/futures/_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/instructor/patch.py", line 390, in retry_sync
response = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_utils/_utils.py", line 275, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/resources/chat/completions.py", line 667, in create
return self._post(
^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_base_client.py", line 1208, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_base_client.py", line 897, in request
return self._request(
^^^^^^^^^^^^^^
File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_base_client.py", line 988, in _request
raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: 404 page not found

Hi
I am trying to run praisonai on linuxmint. I installed a conda environment and ran the code.

1. firstly the database is created by root, or so it seemed, since it was read only and I had to change it.
2. I only use Ollama and tried as in the video. It works till you try to chat. It prints the words and then bombs out back. to the logging page. LiteLLM says nothing special or gives a hint. it did so when I fiddeld around before, but not in the latests instances. On restart it remembers the models, etc so the database is working now.
3. The consol/terminal shows no errors to guide me
4. I tried to create a docker image but could not get it to work, neither on praisonai nor on praisonai code. After a lot of changes pot the dockerfile it ran but the webpage never opened and the program gets stuck. BTW it requests the installation of "duckduckgo_search". So it is missing in the requirements.txt

I am facing issues while using Praisonai code. I getting this error when I execute the command. I am using Ubuntu in WSL. No other error. I have already exported the OpenAI key and it works well without 'code' tool

Allow Input variable values

I am on Linux and it keeps telling me my API key is invalid. I have tried several keys I know work. I have exported it, and verified that it is .bashrc

Any ideas?

i tried setting

OPENAI_API_BASE = https://api.anthropic.com/v1/messages
or
OPENAI_API_BASE = https://api.anthropic.com/v1
and
OPENAI_MODEL_NAME = claude-3-opus-20240229

along with proper OPENAI_API_KEY.

but it gives error :

File "C:\Users\Ameer\AppData\Local\Programs\Python\Python312\Lib\site-packages\openai_base_client.py", line 988, in _request
raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: Error code: 404 - {'type': 'error', 'error': {'type': 'not_found_error', 'message': 'Not Found'}}

what am i doing wrong ? i can use grok and openAi without error

Is there any way to control how often do my automations run?

when I run the praisonai --init command I get the following error even I have set the environment variables:

Traceback (most recent call last): File "<frozen runpy>", line 198, in _run_module_as_main File "<frozen runpy>", line 88, in _run_code File "C:\Users\Ziach\anaconda3\envs\praisonaiagents\Scripts\praisonai.exe\__main__.py", line 7, in <module> File "C:\Users\Ziach\anaconda3\envs\praisonaiagents\Lib\site-packages\praisonai\__main__.py", line 7, in main praison_ai.main() File "C:\Users\Ziach\anaconda3\envs\praisonaiagents\Lib\site-packages\praisonai\cli.py", line 68, in main generator = AutoGenerator(topic=self.topic , framework=self.framework, agent_file=self.agent_file) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Ziach\anaconda3\envs\praisonaiagents\Lib\site-packages\praisonai\auto.py", line 37, in __init__ OpenAI( File "C:\Users\Ziach\anaconda3\envs\praisonaiagents\Lib\site-packages\openai\_client.py", line 104, in __init__ raise OpenAIError( openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

I hope this message finds you well. I'm currently using the Autogen framework in my project and I encountered an issue with the Scrape Website Tool. When attempting to scrape websites in different languages, the tool returns the error 'str' object has no attribute 'decode'.

After some investigation, I found that modifying the tool's function as follows resolves the issue:

def autogen_scrape_website_tool(assistant, user_proxy):
def register_scrape_website_tool(tool_class, tool_name, tool_description, assistant, user_proxy):
def tool_func(website_url: str) -> Any:
tool_instance = tool_class(website_url=website_url)
content = tool_instance.run()
if isinstance(content, str):
content = content.encode('utf-8').decode('utf-8') # Ensure content is properly decoded as UTF-8
return content
register_function(tool_func, caller=assistant, executor=user_proxy, name=tool_name, description=tool_description)
register_scrape_website_tool(ScrapeWebsiteTool, "scrape_website_tool", "Read website content(website_url: 'string') - A tool that can be used to read content from a specified website.", assistant, user_proxy)

I believe this modification could improve the tool's compatibility with websites in various languages. Could you please review this change and consider incorporating it into the official release of the Autogen framework?

Thank you for your attention to this matter. I look forward to your feedback.

Hi, I am running Ollama on my machine and it's working properly. I have multiple tools including CrewAI, PrivateGPT and others that can utilize it. Although, somehow I am not even able to initiate PraisonAI to use Ollama. It keeps giving me error about the OpenAI key. I have updated the .env file as below but the error keeps coming "
Did not find openai_api_key, please add an environment variable OPENAI_API_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)"

How to fix this?! Also, where should the env file be stored.

OPENAI_API_BASE=http://localhost:11434/v1
OPENAI_MODEL_NAME=Majinbu

Allow file input

I found useful to use this with praisonAI to pipe inputs the same way as the fabric project even been compatibles

I call this file pAI

#/bin/zsh
export OPENAI_MODEL_NAME="mixtral-8x7b-32768"
export OPENAI_API_KEY="gsk_****"
export OPENAI_API_BASE="https://api.groq.com/openai/v1" #OR the endpoint you want to use



concatenated_lines=$(cat)
praisonAI_exec=$(which praisonai)

# Check if concatenated_lines is not empty
if [[ -n "$concatenated_lines" ]]; then
    $praisonAI_exec "$@" "$concatenated_lines"
else
    $praisonAI_exec "$@"
fi

Examples:

cat file_with_messy_notes.txt | pAI -auto 'Write a well-crafted essay with the input notes and review the essay to ensure coherence and fact-checking. INPUT: '

https://gist.github.com/johnfelipe/53a5f9f29a68a73ee3976e23fe602880

can u tell me if is good?

The program itself works without any attempt to use the chat or GUI however, when I attempt to use either the chat or the GUI I receive messages similar to:

• 140163889807360 - init.py-init:632 - WARNING: SDK is disabled.
• 140163889807360 - init.py-init:1218 - WARNING: SDK is disabled.

On System Version: macOS 13.6.7 (22G720)
Running pip install prasionai gives this

Cannot install praisonai-tools because these package versions have conflicting dependencies.

The conflict is caused by:
    chromadb 0.4.24 depends on onnxruntime>=1.14.1
    chromadb 0.4.23 depends on onnxruntime>=1.14.1
    chromadb 0.4.22 depends on onnxruntime>=1.14.1

To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict

ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts

Complete new conda env, pip 24.0 from /Users/myusername/anaconda3/envs/prasion/lib/python3.12/site-packages/pip (python 3.12)

Related Google search finds:

• crewAIInc/crewAI#679
• microsoft/onnxruntime#17166

I am able to run this locally with Ollama and Deepseek-coder-v2
But somehow its only picking up python and .py file content but shows all file tree
is there a way we can use javascript/typescript files and its content?

what's the error?

    └── win32_window.h
2024-07-17 16:25:44,348 - 9536 - sql_alchemy.py-sql_alchemy:92 - WARNING: An error occurred: (sqlite3.OperationalError) database is locked
[SQL:
      INSERT INTO steps ("id", "threadId", "createdAt", "start", "end", "output", "name", "type", "streaming", "disableFeedback", "isError", "waitForAnswer", "metadata", "generation") 
      VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
      ON CONFLICT (id) DO UPDATE
      SET "threadId" = ?, "createdAt" = ?, "start" = ?, "end" = ?, "output" = ?, "name" = ?, "type" = ?, "streaming" = ?, "disableFeedback" = ?, "isError" = ?, "waitForAnswer" = ?, "metadata" = ?, "generation" = ?;
    ]
[parameters: ('09f7ea71-2a09-485d-b055-d32207472915', '2b7ed568-ce10-419c-bc78-5aee978362dc', '2024-07-17T14:23:53.075692Z', '2024-07-17T14:23:53.075692Z', '2024-07-17T14:23:53.075692Z', 'What are my project requirements?', 'admin', 'user_message', False, False, False, False, '{}', '{}', '2b7ed568-ce10-419c-bc78-5aee978362dc', '2024-07-17T14:23:53.075692Z', '2024-07-17T14:23:53.075692Z', '2024-07-17T14:23:53.075692Z', 'What are my project requirements?', 'admin', 'user_message', False, False, False, False, '{}', '{}')]
(Background on this error at: https://sqlalche.me/e/20/e3q8)
2024-07-17 16:25:46,248 - 9536 - utils.py-utils:50 - ERROR: litellm.BadRequestError: GetLLMProvider Exception - list index out of range

original model: gemini
Traceback (most recent call last):
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 4353, in get_llm_provider
  model = model.split("/", 1)[1]
      ~~~~~~~~~~~~~~~~~~~^^^
IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\chainlit\utils.py", line 44, in wrapper 
  return await user_function(**params_values)
      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\praisonai\ui\code.py", line 245, in main
  response = await acompletion(
        ^^^^^^^^^^^^^^^^^^
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 1505, in wrapper_async
  raise e
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 1317, in wrapper_async
  result = await original_function(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\main.py", line 338, in acompletion
  _, custom_llm_provider, _, _ = get_llm_provider(
                  ^^^^^^^^^^^^^^^^^
 File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 4531, in get_llm_provider
  raise litellm.exceptions.BadRequestError( # type: ignore
litellm.exceptions.BadRequestError: litellm.BadRequestError: GetLLMProvider Exception - list index out of range

original model: gemini

LLM SUGGESTIONS FOR THE FIX :

There are actually two errors present in the logs you provided:

1. Database Error (WARNING):

Error Message: (sqlite3.OperationalError) database is locked
Explanation: This is a warning message indicating that the database you're trying to insert data into is currently locked. This means another process might be using the database and preventing your code from writing to it.
2. List Index Out of Range (ERROR):

Error Message: litellm.BadRequestError: GetLLMProvider Exception - list index out of range
Explanation: This is the critical error causing the program to crash. It occurs in the get_llm_provider function within the litellm library. The function attempts to split a string containing the model name using the "/" character (line 4353). However, the error message "list index out of range" suggests that the string being split might be empty or doesn't contain a "/" separator.
Possible Causes for the List Index Out of Range Error:

Empty Model Name: The variable model might be empty before being passed to the get_llm_provider function. This could happen if the model selection process fails or isn't set properly.
Invalid Model Name Format: The model name might not be formatted as expected. If the expected format is "/" and you provide just "", the split operation will result in an empty list and the error.
Troubleshooting Steps:

Check Database Lock: Investigate why the database might be locked. There might be another process using it, or a connection issue that needs to be resolved.
Examine Model Name Logic: Look at the code that sets the model variable before calling get_llm_provider. Ensure it's getting a valid and formatted model name.
Review litellm Documentation: Check the documentation for the litellm library to see if there are specific requirements for the model name format.
By addressing both the database lock issue and fixing the cause of the list index out of range error, your program should be able to function correctly.

2024-04-06 20:45:52,842 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.

Starting a new chat....

2024-04-06 20:45:52,843 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:52,843 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:52,843 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
User (to Data Analyst):

Collect and analyze data from top tech news websites to find the latest news on Devika AI

2024-04-06 20:45:52,844 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:52,898 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:53,829 - 140493430167232 - connectionpool.py-connectionpool:330 - WARNING: Connection pool is full, discarding connection: us-api.i.posthog.com. Connection pool size: 10
2024-04-06 20:45:53,906 - 140492943652544 - connectionpool.py-connectionpool:330 - WARNING: Connection pool is full, discarding connection: us-api.i.posthog.com. Connection pool size: 10
2024-04-06 20:45:53,970 - 140492935259840 - connectionpool.py-connectionpool:330 - WARNING: Connection pool is full, discarding connection: us-api.i.posthog.com. Connection pool size: 10
2024-04-06 20:45:54,341 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
Data Analyst (to User):

Sure, I will start by collecting data from top tech news websites regarding Devika AI and then analyze the latest news related to it. I will provide you with a summary of my findings once the analysis is complete. Let me begin the data collection process.

2024-04-06 20:45:54,341 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:54,342 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
User (to Data Analyst):

2024-04-06 20:45:54,343 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:54,362 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:55,752 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
Data Analyst (to User):

I have gathered and analyzed the data from top tech news websites on Devika AI. It appears that there is limited recent news specifically about Devika AI at this moment. If you are looking for more specific information or have any other questions, feel free to let me know!

TERMINATE

2024-04-06 20:45:55,753 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:55,753 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.

Starting a new chat....

2024-04-06 20:45:55,753 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:55,753 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:55,754 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
User (to Content Writer):

Write engaging news articles based on the data analysis of Devika AI news
Context:
I have gathered and analyzed the data from top tech news websites on Devika AI. It appears that there is limited recent news specifically about Devika AI at this moment. If you are looking for more specific information or have any other questions, feel free to let me know!

2024-04-06 20:45:55,754 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:55,775 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:59,063 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
Content Writer (to User):

Title: "Devika AI Continues to Make Waves in the Tech Industry"

In the fast-paced realm of technology, leading companies are constantly innovating to stay ahead of the game. Devika AI, a rising star in the field of artificial intelligence, has been catching the attention of industry experts and investors alike.

A recent data analysis of top tech news websites reveals that Devika AI's impact is being felt across various sectors, with its cutting-edge solutions revolutionizing the way businesses operate. Despite the limited recent news specifically about Devika AI, industry insiders are buzzing with anticipation about what the future holds for this promising company.

From its groundbreaking machine learning algorithms to its unparalleled data analytics capabilities, Devika AI is poised to disrupt the status quo and set new standards in the tech industry. With a team of top-notch engineers and data scientists at the helm, the company shows no signs of slowing down in its quest for innovation and excellence.

As the tech community eagerly awaits the next breakthrough from Devika AI, industry analysts predict that the company's unique approach to AI-driven solutions will continue to draw widespread acclaim and accolades. With its commitment to pushing boundaries and challenging norms, Devika AI is well on its way to solidifying its position as a trailblazer in the world of artificial intelligence.

As we witness the unfolding story of Devika AI, one thing is certain - this is a company that is destined for greatness. Stay tuned for more updates on Devika AI and the remarkable journey that lies ahead.

TERMINATE

2024-04-06 20:45:59,063 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:59,063 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.

Starting a new chat....

2024-04-06 20:45:59,064 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:59,064 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:59,064 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
User (to Editor):

Edit and refine the content created by the Content Writer to ensure quality and accuracy
Context:
I have gathered and analyzed the data from top tech news websites on Devika AI. It appears that there is limited recent news specifically about Devika AI at this moment. If you are looking for more specific information or have any other questions, feel free to let me know!

Title: "Devika AI Continues to Make Waves in the Tech Industry"

In the fast-paced realm of technology, leading companies are constantly innovating to stay ahead of the game. Devika AI, a rising star in the field of artificial intelligence, has been catching the attention of industry experts and investors alike.

A recent data analysis of top tech news websites reveals that Devika AI's impact is being felt across various sectors, with its cutting-edge solutions revolutionizing the way businesses operate. Despite the limited recent news specifically about Devika AI, industry insiders are buzzing with anticipation about what the future holds for this promising company.

From its groundbreaking machine learning algorithms to its unparalleled data analytics capabilities, Devika AI is poised to disrupt the status quo and set new standards in the tech industry. With a team of top-notch engineers and data scientists at the helm, the company shows no signs of slowing down in its quest for innovation and excellence.

As the tech community eagerly awaits the next breakthrough from Devika AI, industry analysts predict that the company's unique approach to AI-driven solutions will continue to draw widespread acclaim and accolades. With its commitment to pushing boundaries and challenging norms, Devika AI is well on its way to solidifying its position as a trailblazer in the world of artificial intelligence.

As we witness the unfolding story of Devika AI, one thing is certain - this is a company that is destined for greatness. Stay tuned for more updates on Devika AI and the remarkable journey that lies ahead.

2024-04-06 20:45:59,064 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:45:59,084 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
2024-04-06 20:46:03,314 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.
Editor (to User):

Title: "Devika AI's Ongoing Impact on the Tech Industry"

In the rapidly evolving tech landscape, companies are continuously striving to innovate and maintain their competitive edge. Devika AI, an emerging player in artificial intelligence, has been garnering attention from industry experts and investors for its groundbreaking advancements.

An analysis of leading tech news platforms indicates that Devika AI is making significant strides across various sectors, reshaping business operations with its state-of-the-art solutions. While there may be limited recent coverage specifically on Devika AI, industry insiders are abuzz with anticipation regarding the company's future trajectory.

From pioneering machine learning algorithms to unmatched data analytics capabilities, Devika AI stands at the forefront of disrupting conventional practices and establishing new benchmarks in the tech sector. Fueled by a talented team of engineers and data scientists, the company remains steadfast in its pursuit of innovation and excellence.

Anticipation within the tech sphere is palpable as Devika AI gears up for its next breakthrough, with industry analysts projecting continued acclaim and recognition for its unique AI-driven strategies. By upholding a commitment to pushing boundaries and defying norms, Devika AI is on track to cement its position as a trailblazer in artificial intelligence.

The narrative of Devika AI unfolds as a tale of inevitability towards success. Stay tuned for forthcoming updates on the journey of Devika AI and its remarkable contributions to the tech realm. If you seek additional information or have specific inquiries, please feel free to reach out!

TERMINATE

2024-04-06 20:46:03,315 - 140494737413376 - base.py-base:79 - WARNING: No default IOStream has been set, defaulting to IOConsole.

    ├── utils.h
    ├── win32_window.cpp
    └── win32_window.h

2024-07-17 17:21:21,675 - 9536 - utils.py-utils:50 - ERROR: litellm.BadRequestError: GetLLMProvider Exception - list index out of range

original model: gemini
Traceback (most recent call last):
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 4353, in get_llm_provider
model = model.split("/", 1)[1]
~~~~~~~~~~~~~~~~~~~^^^
IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\chainlit\utils.py", line 44, in wrapper
return await user_function(**params_values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\praisonai\ui\code.py", line 245, in main
response = await acompletion(
^^^^^^^^^^^^^^^^^^
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 1505, in wrapper_async
raise e
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 1317, in wrapper_async
result = await original_function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\main.py", line 338, in acompletion
_, custom_llm_provider, _, _ = get_llm_provider(
^^^^^^^^^^^^^^^^^
File "D:\MY FLUTTER DEV PROJECTS\shopping_list_app\HERB_APP\HERB_GROWING_COMMUNITY_SHARING\herb_community_sharing_scheme\budgrowX\Lib\site-packages\litellm\utils.py", line 4531, in get_llm_provider
raise litellm.exceptions.BadRequestError( # type: ignore
litellm.exceptions.BadRequestError: litellm.BadRequestError: GetLLMProvider Exception - list index out of range

original model: gemini

Hi Mervin,

I’ve been working with the praisonai code tool and found it immensely helpful for coding with a large context base. Great work on developing such a robust tool! I have a couple of enhancements to propose that could streamline the user experience and repo organization:

• Directory Management:

  • Currently, files like chainlit.md and the .chainlit directory are placed in the root of the repository upon startup. The public directory also adds to the clutter.
  • It would be more efficient to relocate these to ~/.praison/, alongside database.sqlite. This would help keep the root directory clean and organized.

• Docker Integration:

  • Adding Docker support could significantly simplify setting up and running the tool across different environments.
  • Dockerization would ensure a more isolated and consistent operational environment, facilitating easier deployment and scalability.
  • Increased Adoption: Dockerizing the application can lower the barrier to entry for new users, enabling more developers to test the tool. This increased user base can provide more feedback, potentially increase your follower base, and further enhance the toolset through community contributions.

These changes could help maintain the tool’s efficiency while improving its usability and setup process.

Thanks for considering these suggestions. Looking forward to your thoughts!

Environment :
Windows 11
(Conda) with Python 3.11.8
praisonAI 0.0.17

After installation ( :
pip install praisonai

I ran the Initialise :
praisonai --init create a movie script about dog in moon

it return error code as below , I think it's UTF-8 issue :

Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Scripts\praisonai.exe\__main__.py", line 4, in <module>
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\praisonai\__init__.py", line 1, in <module>
    from .cli import PraisonAI
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\praisonai\cli.py", line 11, in <module>
    import gradio as gr
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\__init__.py", line 3, in <module>
    import gradio._simple_templates
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\_simple_templates\__init__.py", line 1, in <module>
    from .simpledropdown import SimpleDropdown
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\_simple_templates\simpledropdown.py", line 6, in <module>
    from gradio.components.base import FormComponent
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\components\__init__.py", line 40, in <module>
    from gradio.components.multimodal_textbox import MultimodalTextbox
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\components\multimodal_textbox.py", line 34, in <module>
    class MultimodalTextbox(FormComponent):
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\component_meta.py", line 198, in __new__
    create_or_modify_pyi(component_class, name, events)
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\site-packages\gradio\component_meta.py", line 92, in create_or_modify_pyi
    source_code = source_file.read_text()
                  ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\adam\anaconda3\envs\adamlab2_env\Lib\pathlib.py", line 1059, in read_text
    return f.read()
           ^^^^^^^^
UnicodeDecodeError: 'cp950' codec can't decode byte 0xe2 in position 2072: illegal multibyte sequence

It's already in the langchain community, but I was wondering how hard it would be to add it to the tools.

Reference:
langchain_community/utilities/searx_search.py - already in the venv from the requirements
https://github.com/searxng/searxng
https://python.langchain.com/docs/integrations/tools/searx_search/
https://docs.searxng.org/dev/search_api

Telemetry is “disabled” for CrewAI in PraisonAI, however when the CrewAI_Tools are loaded the telemetry is sent to posthog. My adblocker is blocking the communication to posthog, therefore an error is generated, see below. A similar message is generated for each tool and the retries cause a significant delay in the PraisonAI process.

_common.py-_common:105 - INFO: Backing off send_request(...) for 0.4s (requests.exceptions.ConnectionError: HTTPSConnectionPool(host='us-api.i.posthog.com', port=443): Max retries exceeded with url: /batch/ (Caused by NameResolutionError("<urllib3.connection.HTTPSConnection object at 0x000002AAF9D125D0>: Failed to resolve 'us-api.i.posthog.com' ([Errno 11001] getaddrinfo failed)")))