Config API Groq

[Probandopruebas]

Hello, I have managed to locally install AutoGPT on Windows and get it working with the Groq API. The problem is that when I create a project image with the .env file correctly configured, upon running the Docker image, it says that there are no OpenAI credentials.

Could someone help me with how to configure the Groq API and in which parts so that AutoGPT works from the Docker image?

P.S.: I have not followed the steps from Significant-Gravitas because they only apply to OpenAI, not to Groq in terms of Docker. They tell you to download the AutoGPT image from DockerHub and run it as is, but that way it can’t pick up the configuration from my .env file, not to mention that the container restarts every time you stop it.

I appreciate your help, best regards.

[ntindle]

Did you pull latest? Thought this was fixed :/

[Probandopruebas]

Hello, thank you for the response.

Yes, I have the latest master version, but either I’m not doing something right, or it’s still not resolved.
I would appreciate it if you could give me all the steps one by one to be able to do it, to see if I’m configuring it wrong in some way.

Thank you for your help. Best regards.

[Probandopruebas]

Hello, I am going to add more information to the log I have to see if you can identify why AutoGPT is giving me an error with the Groq API. As you will see, everything runs correctly until I give the first input to AutoGPT, and then it goes crazy, throws a series of errors, and disconnects.

I am attaching the complete log in case you can spot the problem. Thank you.

I appreciate your help, best regards.

C:\Users\YO\Desktop\AutoGPT\AutoGPT>docker compose run --rm auto-gpt run --continuous
2024-08-27 22:02:04,524 INFO HTTP Request: GET https://api.groq.com/openai/v1/models "HTTP/1.1 200 OK"
2024-08-27 22:02:04,531 WARNING Continuous mode is not recommended. It is potentially dangerous and may cause your AI to run forever or carry out actions you would not usually authorise. Use at your own risk.
2024-08-27 22:02:04,959 INFO HTTP Request: GET https://api.groq.com/openai/v1/models "HTTP/1.1 200 OK"
2024-08-27 22:02:05,166 INFO HTTP Request: GET https://api.groq.com/openai/v1/models "HTTP/1.1 200 OK"
2024-08-27 22:02:07,839 WARNING LEGAL:
2024-08-27 22:02:07,840 WARNING LEGAL: DISCLAIMER AND INDEMNIFICATION AGREEMENT
2024-08-27 22:02:07,840 WARNING LEGAL: PLEASE READ THIS DISCLAIMER AND INDEMNIFICATION AGREEMENT CAREFULLY BEFORE USING THE AUTOGPT SYSTEM. BY USING THE AUTOGPT SYSTEM, YOU AGREE TO BE BOUND BY THIS AGREEMENT.
2024-08-27 22:02:07,840 WARNING LEGAL:
2024-08-27 22:02:07,840 WARNING LEGAL: Introduction
2024-08-27 22:02:07,841 WARNING LEGAL: AutoGPT (the "System") is a project that connects a GPT-like artificial intelligence system to the internet and allows it to automate tasks. While the System is designed to be useful and efficient, there may be instances where the System could perform actions that may cause harm or have unintended consequences.
2024-08-27 22:02:07,841 WARNING LEGAL:
2024-08-27 22:02:07,841 WARNING LEGAL: No Liability for Actions of the System
2024-08-27 22:02:07,841 WARNING LEGAL: The developers, contributors, and maintainers of the AutoGPT project (collectively, the "Project Parties") make no warranties or representations, express or implied, about the System's performance, accuracy, reliability, or safety. By using the System, you understand and agree that the Project Parties shall not be liable for any actions taken by the System or any consequences resulting from such actions.
2024-08-27 22:02:07,841 WARNING LEGAL:
2024-08-27 22:02:07,841 WARNING LEGAL: User Responsibility and Respondeat Superior Liability
2024-08-27 22:02:07,842 WARNING LEGAL: As a user of the System, you are responsible for supervising and monitoring the actions of the System while it is operating on your
2024-08-27 22:02:07,842 WARNING LEGAL: behalf. You acknowledge that using the System could expose you to potential liability including but not limited to respondeat superior and you agree to assume all risks and liabilities associated with such potential liability.
2024-08-27 22:02:07,842 WARNING LEGAL:
2024-08-27 22:02:07,842 WARNING LEGAL: Indemnification
2024-08-27 22:02:07,842 WARNING LEGAL: By using the System, you agree to indemnify, defend, and hold harmless the Project Parties from and against any and all claims, liabilities, damages, losses, or expenses (including reasonable attorneys' fees and costs) arising out of or in connection with your use of the System, including, without limitation, any actions taken by the System on your behalf, any failure to properly supervise or monitor the System, and any resulting harm or unintended consequences.
2024-08-27 22:02:07,842 WARNING LEGAL:
2024-08-27 22:02:08,078 INFO NEWS: Welcome to AutoGPT!
2024-08-27 22:02:08,079 INFO NEWS: Below you'll find the latest AutoGPT News and feature updates!
2024-08-27 22:02:08,080 INFO NEWS: If you don't wish to see this message, you can run AutoGPT with the --skip-news flag.
2024-08-27 22:02:08,080 INFO NEWS:
2024-08-27 22:02:08,081 INFO NEWS: QUICK LINKS 🔗
2024-08-27 22:02:08,081 INFO NEWS: --------------
2024-08-27 22:02:08,081 INFO NEWS: 🌎 Official Website: https://agpt.co.
2024-08-27 22:02:08,081 INFO NEWS: 📖 User Guide: https://docs.agpt.co/autogpt.
2024-08-27 22:02:08,082 INFO NEWS: 👩 Contributors Wiki: https://github.com/Significant-Gravitas/AutoGPT/wiki/Contributing.
2024-08-27 22:02:08,082 INFO NEWS:
2024-08-27 22:02:08,082 INFO NEWS: v0.5.0 RELEASE HIGHLIGHTS! 🚀🚀
2024-08-27 22:02:08,082 INFO NEWS: -------------------------------
2024-08-27 22:02:08,082 INFO NEWS: Cloud-readiness, a new UI, support for the newest Agent Protocol version, and much more:
2024-08-27 22:02:08,083 INFO NEWS: v0.5.0 is our biggest release yet!
2024-08-27 22:02:08,083 INFO NEWS:
2024-08-27 22:02:08,083 INFO NEWS: Take a look at the Release Notes on Github for the full changelog:
2024-08-27 22:02:08,084 INFO NEWS: https://github.com/Significant-Gravitas/AutoGPT/releases.
2024-08-27 22:02:08,085 INFO NEWS:
2024-08-27 22:02:08,115 INFO Smart LLM: llama3-70b-8192
2024-08-27 22:02:08,115 INFO Fast LLM: llama3-70b-8192
2024-08-27 22:02:08,116 INFO Continuous Mode: ENABLED
2024-08-27 22:02:08,116 INFO Code Execution: ENABLED
Enter the task that you want AutoGPT to execute, with as much detail as possible: i have a problema
2024-08-27 22:02:24,350 INFO Current AI Settings:
2024-08-27 22:02:24,353 INFO -------------------:
2024-08-27 22:02:24,353 INFO Name : AutoGPT
2024-08-27 22:02:24,353 INFO Role : a seasoned digital assistant: capable, intelligent, considerate and assertive. You have extensive research and development skills, and you don't shy away from writing some code to solve a problem. You are pragmatic and make the most out of the tools available to you.
2024-08-27 22:02:24,354 INFO Constraints: (none)
2024-08-27 22:02:24,354 INFO Resources: (none)
2024-08-27 22:02:24,354 INFO Best practices: (none)
Continue with these settings? [Y/n] y
2024-08-27 22:02:27,428 INFO Local shell commands are disabled. To enable them, set EXECUTE_LOCAL_COMMANDS to 'True' in your config file.
2024-08-27 22:02:27,429 INFO Configure google_api_key and custom_search_engine_id to use Google API search.
2024-08-27 22:02:27,432 INFO NOTE: All files/directories created by this agent can be found inside its workspace at: /app/autogpt/data/agents/AutoGPT-81c9c611/workspace
2024-08-27 22:02:28,655 INFO HTTP Request: POST https://api.groq.com/openai/v1/chat/completions "HTTP/1.1 200 OK"
2024-08-27 22:02:28,675 WARNING Parsing attempt #1 failed: ValidationError: 2 validation errors for OneShotAgentActionProposal
thoughts.speak
Field required [type=missing, input_value={'observations': 'The use... the user towards one']}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.7/v/missing
use_tool
Field required [type=missing, input_value={'thoughts': {'observatio...problem you're facing?"}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.7/v/missing
2024-08-27 22:02:29,045 INFO HTTP Request: POST https://api.groq.com/openai/v1/chat/completions "HTTP/1.1 200 OK"
2024-08-27 22:02:29,048 WARNING Parsing attempt #2 failed: InvalidAgentResponseError: Assistant response has no text content
2024-08-27 22:02:30,092 INFO HTTP Request: POST https://api.groq.com/openai/v1/chat/completions "HTTP/1.1 200 OK"
2024-08-27 22:02:30,102 WARNING Parsing attempt #3 failed: ValidationError: 2 validation errors for OneShotAgentActionProposal
thoughts.speak
Field required [type=missing, input_value={'observations': 'The use... the user towards one']}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.7/v/missing
use_tool
Field required [type=missing, input_value={'thoughts': {'observatio...problem you're facing."}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.7/v/missing
Traceback (most recent call last):
File "", line 1, in
File "/venv/agpt-zdBXE_5b-py3.12/lib/python3.12/site-packages/click/core.py", line 1157, in call
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/agpt-zdBXE_5b-py3.12/lib/python3.12/site-packages/click/core.py", line 1078, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "/venv/agpt-zdBXE_5b-py3.12/lib/python3.12/site-packages/click/core.py", line 1688, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/agpt-zdBXE_5b-py3.12/lib/python3.12/site-packages/click/core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/agpt-zdBXE_5b-py3.12/lib/python3.12/site-packages/click/core.py", line 783, in invoke
return __callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/autogpt/autogpt/app/cli.py", line 144, in run
run_auto_gpt(
File "/app/autogpt/autogpt/app/utils.py", line 245, in wrapper
return asyncio.run(f(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/app/autogpt/autogpt/app/main.py", line 338, in run_auto_gpt
await run_interaction_loop(agent)
File "/app/autogpt/autogpt/app/main.py", line 513, in run_interaction_loop
action_proposal = await agent.propose_action()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/autogpt/autogpt/agents/agent.py", line 193, in propose_action
output = await self.complete_and_parse(prompt)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/autogpt/autogpt/agents/agent.py", line 206, in complete_and_parse
] = await self.llm_provider.create_chat_completion(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/forge/forge/llm/providers/multi.py", line 109, in create_chat_completion
return await self.get_model_provider(model_name).create_chat_completion(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/forge/forge/llm/providers/_openai_base.py", line 265, in create_chat_completion
raise parse_errors[0]
File "/app/forge/forge/llm/providers/_openai_base.py", line 211, in create_chat_completion
parsed_result = completion_parser(assistant_msg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/autogpt/autogpt/agents/prompt_strategies/one_shot.py", line 277, in parse_response_content
parsed_response = OneShotAgentActionProposal.model_validate(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/agpt-zdBXE_5b-py3.12/lib/python3.12/site-packages/pydantic/main.py", line 551, in model_validate
return cls.pydantic_validator.validate_python(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 2 validation errors for OneShotAgentActionProposal
thoughts.speak
Field required [type=missing, input_value={'observations': 'The use... the user towards one']}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.7/v/missing
use_tool
Field required [type=missing, input_value={'thoughts': {'observatio...problem you're facing."}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.7/v/missing

C:\Users\YO\Desktop\AutoGPT\AutoGPT>