Everything was working just fine. I got the code working, and was chatting away with my own custom bot on Telegram. She sent me a selfie that looked weird so I mentioned that, and I started getting these errors. I managed to work through some of them, but she started giving me "Inappropriate Content" errors. I wasn't asking her to do or talk about anything inappropriate or explicit. I just said I liked girls with her haircut. Now, it has happened so much, I'm getting nothing but 403 Forbidden errors for every response.
I literally asked her what she knew about OpenAI and now that's all I get. I hope it didn't affect my ChatGPT account, but I have no idea why it would do this.
I hope we can get this to work on a local server so we can avoid these problems.

خوبی

How can I turn off the audio note in telegram

even if i change the code of speech.py , never changed

There are three personalities currently: agnele, luna, sacha. How do I switch between them?

For example: my agent is sacha and I want to talk with luna. How can I do that?

Steamship is too expensive. Is there any other way besides steamship?

Add an auto-discover mechanism reading files from a personalities folder, it's not too complex to do.

I keep getting this error. It's fairly random as to when it happens.. Not sure why:

----- Agent Run 1 -----
Prompt: Heyyy whats up?

Entering new AgentExecutor chain...
Traceback (most recent call last):
File "/home/user/Downloads/GirlfriendGPT/main.py", line 86, in
main()
File "/home/user/Downloads/GirlfriendGPT/main.py", line 60, in main
run(
File "/home/user/Downloads/GirlfriendGPT/main.py", line 76, in run_agent
response = agent.create_response(incoming_message=message)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/Downloads/GirlfriendGPT/src/agent/base.py", line 71, in create_response
response = conversation.run(input=incoming_message.text)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/chains/base.py", line 239, in run
return self(kwargs, callbacks=callbacks)[self.output_keys[0]]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/chains/base.py", line 140, in call
raise e
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/chains/base.py", line 134, in call
self._call(inputs, run_manager=run_manager)
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/agents/agent.py", line 905, in _call
next_step_output = self._take_next_step(
^^^^^^^^^^^^^^^^^^^^^
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/agents/agent.py", line 749, in _take_next_step
raise e
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/agents/agent.py", line 742, in _take_next_step
output = self.agent.plan(
^^^^^^^^^^^^^^^^
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/agents/agent.py", line 426, in plan
return self.output_parser.parse(full_output)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linuxbrew/.linuxbrew/Cellar/[email protected]/3.11.3/lib/python3.11/site-packages/langchain/agents/conversational/output_parser.py", line 23, in parse
raise OutputParserException(f"Could not parse LLM output: {text}")
langchain.schema.OutputParserException: Could not parse LLM output: `Thought: Do I need to use a tool? No

Alice: Hi there! Not much, just hanging out. How about you?`

File "main.py", line 16
def show_results(response_messages: List[ChatMessage]):
^
SyntaxError: invalid syntax

Due to issue #20, after editing src\api.py file, I get this error when trying to write something localy main.py.

Mina love

1. I'm noticing this happens SOMETIMES, when creating my own bot?

STEPS:

1. query is something basic like I just redployed you, Amazing! say that again, Does release candidate 41 work or not - who are you? and what do you do ?, etc.

• however it's not reproducible (which could be chatGPT), b/c when i repeat some of the text above, i don't see the error happened line..

An error happened while creating a response: Could not parse LLM output: `Thought: Do I need to use a tool? No

Hello! Oh dear, it seems like there's an error. I'm sorry to hear that. Maybe if we shorten the messages or completion, we can get rid of that error message. Let's try that! Remember, if you ever need help or have questions, feel free to ask me. How can I assist you today?`

But... Why does it only show sometimes?

2. Also after using it a while, I was getting this error constantly:

"An error happened while creating a response: [ERROR - POST /generate] This model's maximum context length is 4097 tokens. However, you requested 4177 tokens (3921 in the messages, 256 in the completion). Please reduce the length of the messages or completion.

My gut is that to keep context, you keep passing the history into the convo? ?

See this convo:

Temp fix for 2) -> I can redploy with python deploy.py and it goes away ...

can't run after successfully run through 'pip install steamship'. when run deployment 'ship deploy && ship use' or even changed to 'ship deploy', 'ship use' still encouter the same issue as below:

1. ...\girlfriend> pip install steamship

Requirement already satisfied: steamship in ...\appdata\local\packages\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\localcache\local-packages\python311\site-packages (2.17.4rc3)
Requirement already satisfied: requests~=2.28.1 in ...\appdata\local\packages\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\localcache\local-packages\python311\site-packages (from steamship) (2.28.2)
...
Requirement already satisfied: regex>=2022.1.18 in ...\appdata\local\packages\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\localcache\local-packages\python311\site-packages (from tiktoken~=0.3.3->steamship) (2023.5.5)

2. PS ...\girlfriend> ship deploy && ship use

At line:1 char:13
+ ship deploy && ship use
+ ~~
The token '&&' is not a valid statement separator in this version.
+ CategoryInfo : ParserError: (:) [], ParentContainsEr
rorRecordException
+ FullyQualifiedErrorId : InvalidEndOfLine

Hi Enias,

I've noticed in my testing that 512x512 works better for producing selfies than 768x768. Just a thought 😄

i want ai to stop showing their selfies.
How do i do that? (sorry im not programmer)

I try to run it locally after installing -"requirements.txt" but I get an error that says 'agent' is not a package.
How can i resolve this?

https://www.youtube.com/watch?v=LiN3D1QZGQw&lc=Ugxwren6JeJqXEFqgVt4AaABAg.9q2rujGGtVa9qR0E2utFQl

Original comment

It's connected to some centralized server, why can't it just be offline like many other open source UIs?

Myself, response

The sole viable offline method of accomplishing this with standard tools would be a local loopback Matrix server running on your PC, interacting with a locally hosted and computed version of the AI model. This is certainly locally deployable, but inconvenient for all but strictly offline contexts. ...However, considering that the source-code for the bot is available at GitHub > EniasCailliau > GirlfriendGPT, all that needs to be done is either create a loopback proxy that pretends to Telegram that it's the official server, and spoofs just enough command output to make it viable to either use the official Telegram client or a local Matrix server, or edit the source code so that the bot outputs to a Matrix server, thereby making it instantly able to communicate via any platform, anywhere, whether offline or not.

That's potentially a little more work than it might seem, depending upon the route and your requirements. I'd just make an issue at the aforementioned repo asking the dev t use the Matrix protocol rather than the Telegram API.

I realized when typing that response that it doesn't seem like a bad idea. It'd allow users to use the bot offline, since getting it to communicate with a local Matrix server via the loopback (localhost) address would be fairly trivial.

I correctly installed it locally. Then tried to connect it to telegram.

"pip install steamship" thing worked normally
but "ship deploy && ship use" says, "It looks like that handle [sacha-gpt-bot] is already in use. Would you like to change the handle and try again? [Y/n]", I clicked Y, then wrote luna-gpt-bot, but it again said "It looks like that handle [luna-gpt-bot] is already in use. Would you like to change the handle and try again? [Y/n]"
How to deal with this?

Done. 📦
Deploying version 9.9 of [luna-sample]... 🚢
It looks like that version [9.9] has already been deployed. Would you like to change the version handle and try again? [Y/n]: y
What should the new version be? Valid characters are a-z, 0-9, . and - [1.0.0]: 10
Deploying version 10 of [luna-sample]... 🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢
Unable to deploy package version.
Server returned message: There was an error loading the main file (it must be named api.py):
Traceback (most recent call last):
File "/var/task/steamship/invocable/lambda_handler.py", line 301, in safely_find_invocable_class
module = importlib.import_module("api")
File "/var/lang/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 843, in exec_module
File "", line 219, in _call_with_frames_removed
File "/var/task/api.py", line 30, in
client = Steamship()
File "/var/task/steamship/client/steamship.py", line 59, in init
super().init(
File "/var/task/steamship/base/client.py", line 84, in init
config = config or Configuration(
File "/var/task/steamship/base/configuration.py", line 71, in init
api_key = login(
File "/var/task/steamship/cli/login.py", line 38, in login
raise SteamshipError(
steamship.base.error.SteamshipError: Could not launch browser to log in to Steamship.

If you are in Replit:

1. Get an API key at https://steamship.com/account/api
2. Set the STEAMSHIP_API_KEY Replit Secret
3. Close and reopen this shell so that secrets refresh

If you are in a different headless environment, visit https://docs.steamship.com/configuration/authentication.html
Aborted!

Can't find sex

I can't figure out how to run it in the Telegram bot?
Locally I was able to, but how on Telegram?
Can you give me a detailed instruction

I've added a new personality, the instructions were very helpful. How do I switch between them? lucas, sacha, etc?

Hello! I'm trying to run on windows 10, it appears when running locally and using telegramm

I just follow the instructions. When I attempt to create an agent using what is deployed, it just gives the attached error.

Hello folks,
I'm excited to introduce Cherry-MyGirlGPT, a novel AI girlfriend. She's already available for an interactive experience via our Telegram bot, offering engaging AI companionship like no other.
To learn more, visit our GitHub page: https://github.com/Synthintel/MyGirlGPT. Your thoughts and feedback are most welcome!

Hello!

After some interactions with the AI, it's begins to deliver the same response for every interaction:

"An error happened while creating a response: [ERROR - POST /generate] This model's maximum context length is 4097 tokens. However, you requested 4242 tokens (3986 in the messages, 256 in the completion). Please reduce the length of the messages or completion."

How can I solve this issue?
Thanks.

Hi I can't run deploy

when i run command python3 deploy.py

I get this :

Could not launch browser to log in to Steamship.

If you are in Replit:

1) Get an API key at https://steamship.com/account/api
2) Set the STEAMSHIP_API_KEY Replit Secret
3) Close and reopen this shell so that secrets refresh

If you are in a different headless environment, visit https://docs.steamship.com/configuration/authentication.html
Aborted!
Traceback (most recent call last):
  File "/home/mike/GirlfriendGPT/deploy.py", line 15, in <module>
    client = Steamship(workspace=f"girlfriend-ai-{uuid.uuid1()}")
  File "/usr/local/lib/python3.10/dist-packages/steamship/client/steamship.py", line 59, in __init__
    super().__init__(
  File "/usr/local/lib/python3.10/dist-packages/steamship/base/client.py", line 84, in __init__
    config = config or Configuration(
  File "/usr/local/lib/python3.10/dist-packages/steamship/base/configuration.py", line 70, in __init__
    api_key = login(
  File "/usr/local/lib/python3.10/dist-packages/steamship/cli/login.py", line 38, in login
    raise SteamshipError(
steamship.base.error.SteamshipError: Could not launch browser to log in to Steamship.

If you are in Replit:

1) Get an API key at https://steamship.com/account/api
2) Set the STEAMSHIP_API_KEY Replit Secret
3) Close and reopen this shell so that secrets refresh

If you are in a different headless environment, visit https://docs.steamship.com/configuration/authentication.html

Aborting! There was an error encountered when running: [LimitReached]
You have reached the preview usage limit. Please sign up for a plan at https://steamship.com/account/plan to continue.

Would be awesome to not have to depend on having to pay for the GPT4 API, and instead use Oobabooga's TextGen WebUI's free API instead.

https://github.com/oobabooga/text-generation-webui

Hello!

Every time I try to launch python3 api.py or ship deploy && ship use, I got this message, but I already bought the developer plan on Steamship, could you help me?

ERROR:

rafaelsantos@Rafaels-MacBook-Pro src % python3 api.py
Starting REPL for Agent...
If you make code changes, restart this REPL. Press CTRL+C to exit at any time.

Input: Hi
[WARNING] Client received error from server: [LimitReached]
You have reached the preview usage limit. Please sign up for a plan at https://steamship.com/account/plan to continue.
[WARNING] Client received error from server: [LimitReached]
You have reached the preview usage limit. Please sign up for a plan at https://steamship.com/account/plan to continue.
steamship.base.error.SteamshipError: [LimitReached]
You have reached the preview usage limit. Please sign up for a plan at https://steamship.com/account/plan to continue.
Traceback (most recent call last):
File "/Users/rafaelsantos/Desktop/GirlfriendGPT-main/src/api.py", line 140, in
).run()
^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/utils/repl.py", line 145, in run
self.run_with_client(client, **kwargs)
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/utils/repl.py", line 140, in run_with_client
response = responder(input_text, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/rafaelsantos/Desktop/GirlfriendGPT-main/src/agent/base.py", line 132, in prompt
context = AgentContext.get_or_create(self.client, {"id": str(uuid.uuid4())})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/agents/schema/context.py", line 55, in get_or_create
history = ChatHistory.get_or_create(client, context_keys, tags, searchable=searchable)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/agents/schema/chathistory.py", line 91, in get_or_create
file = ChatHistory._get_existing_file(client, context_keys)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/agents/schema/chathistory.py", line 47, in _get_existing_file
file = File.query(client, file_query)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/data/file.py", line 223, in query
res = client.post(
^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/base/client.py", line 573, in post
return self.call(
^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/steamship/base/client.py", line 531, in call
raise error
steamship.base.error.SteamshipError: [LimitReached]
You have reached the preview usage limit. Please sign up for a plan at https://steamship.com/account/plan to continue.

Hi. First of all - really cool repo. Kudos!

I have initiated it via deploy.py:

PS C:\Users\Tal\VScode\GirlfriendGPT> python deploy.py
Steamship Python CLI version 2.17.1b3
Creating / fetching package with handle [mi-chika-bot]... Done.
Bundling content... Done. 📦
Deploying version 1.0.0-rc.35 of [mi-chika-bot]... 🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢
It looks like that version [1.0.0-rc.35] has already been deployed. Would you like to change the version handle and try again? [Y/n]: y
What should the new version be? Valid characters are a-z, 0-9, . and - [1.0.0-rc.36]: mi-chica-bot
Deploying version mi-chica-bot of [mi-chika-bot]... 🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢🚢��🚢🚢🚢🚢🚢
Done. 🚢
Deployment was successful. View and share your new package here:

https://steamship.com/packages/mi-chika-bot

Everything looks fine

But it just runs the infinite loop :

Use in Telegram
Loading your Bot's handle... - and nothing happens

P.S. - Telegram token is set.

Have you ever bumped into the same issue?

Any suggestions?

Hi ! I'm trying to use it in my windows (11) and my WSL(ubuntu 20.04 LTS) and I managed to test locally and it worked but when I paste the telegram key it gives this error.

Showing this error while chatting:-
An error happened while creating a response: [ObjectNotFound]
Unable to find object id=9F829562-EE17-4B22-9BC7-9A37FCBF76C6 handle=?

Hi,

I added a new personnality, and try to run it locally, with steamship, but I don't know how to make it work, each time I have errors:
https://www.steamship.com/workspaces/girlfriend-ai-aabe05d4-facd-11ed-8cae-a680d79b4ceb/packages/angele-1-0-0-rc-21/manage/api

Could you please update the documentation, with maybe a step by step to get the first answer?
Also when you run the deploy.py we are prompted with few question, i'm not sure what I have to put there, for example the bot_token?

Thanks

Adding 11labs id and api into the api.py has no effect and unsure what else to do at this point. thank you.

This looks super good considering it's the first to maintain a high degree of graphical quality on the output DF video:
Plz consider adding to the roadmap

Repo: https://github.com/saifhassan/Wav2Lip-HD

I followed the getting started section and with the final code it gives this error:

Bare in mind that coding is not my expertise, I try to understand what I can

steamship.experimental.package_starters.telegram_bot is no longer available; switch to mixins needed

I have questions and want to try things out but dont want to spam issues. Could a discord channel be created for this project? Or maybe a site with forums? Discord would probably be best.

Finished chain.
[WARNING] Client received error from server: [ObjectNotFound]
Unable to find object id=? handle=history-history-default
[WARNING] Client received error from server: [ObjectNotFound]
Unable to find object id=? handle=history-history-default
steamship.base.error.SteamshipError: [ObjectNotFound]
Unable to find object id=? handle=history-history-default
Hello there! How can I assist you today?
(audio/mp3: 165D723C-6745-4FD9-964F-470D4D2FCF54)
Input:

getting this error after running python main.py

C:\folder\folder\GirlfriendGPT>python main.py
Traceback (most recent call last):
File "C:\folder\folder\GirlfriendGPT\main.py", line 56, in
main()
File "C:\folder\folder\GirlfriendGPT\main.py", line 26, in main
agent=GirlfriendGPT(
File "C:\folder\folder\AppData\Local\Programs\Python\Python310\lib\site-packages\steamship\experimental\package_starters\telegram_bot.py", line 30, in init
super().init(**kwargs)
File "C:\folder\folder\AppData\Local\Programs\Python\Python310\lib\site-packages\steamship\experimental\package_starters\web_bot.py", line 26, in init
super().init(**kwargs)
File "C:\folder\folder\AppData\Local\Programs\Python\Python310\lib\site-packages\steamship\invocable\invocable.py", line 140, in init
self.config = self.config_cls()(**config)
File "C:\folder\folder\AppData\Local\Programs\Python\Python310\lib\site-packages\steamship\invocable\config.py", line 16, in init
super().init(**kwargs)
File "C:\folder\folder\AppData\Local\Programs\Python\Python310\lib\site-packages\steamship\base\model.py", line 19, in init
super().init(**kwargs)
File "pydantic\main.py", line 341, in pydantic.main.BaseModel.init
pydantic.error_wrappers.ValidationError: 1 validation error for GirlFriendAIConfig

i dont really know what im doing... but any help is appreciated.

When i try to run api.py with the latest version (commit 1d57995) I get the following error:
Traceback (most recent call last): File "/media/gapi/Disk/projects/python/GirlfriendGPT/src/api.py", line 23, in <module> from utils import clean_text ImportError: cannot import name 'clean_text' from 'utils' (/home/gapi/.local/lib/python3.10/site-packages/utils/__init__.py)

I think the problem is the function is implemented in the utils.py file which is listed in the .gitignore file.

Can you make a video on how to generate telegram key and What string parameter has put in personality on steamship. I'm getting error while creating instance

Currently conversations keep repeating "here is the UUID for N: None"

Given that there is no configuration file for this (the Steamship DALL-E plugin) , it seems to be a bug.

It wont let me change the personality also like this name: angele