Giter Site home page Giter Site logo

auto-gpt-text-gen-plugin's People

Contributors

danikhan632 avatar sidewaysthought avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

auto-gpt-text-gen-plugin's Issues

autogpt used local llm instead of gpt4 &gpt3.5

hello, thanks your solution for the local llm deploy in autogpt, when i installed it , follow the Readme, some steps not clear, and i can not test it sucess , is there needs to provides the openai keys in .env file if i used the text-generation-webui api ?
image
v
image

What AutoGPT release does this work on?

Hi,
To solve some of the problems I am having it would be helpful to know which AutoGPT release this plugin has worked on. Can you post a list (or just one) of the versions of AutoGPT that work with this plugin?

Thanks,
Chris

AttributeError: 'str' object has no attribute 'content'

Hi,
I am getting the error:

Traceback (most recent call last):
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/mnt/2TB_SSD/Auto-GPT/autogpt/__main__.py", line 5, in <module>
    autogpt.app.cli.main()
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/site-packages/click/core.py", line 1078, in main
    rv = self.invoke(ctx)
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/site-packages/click/core.py", line 1666, in invoke
    rv = super().invoke(ctx)
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/site-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
  File "/home/rowbot/anaconda3/envs/ooga/lib/python3.10/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context(), *args, **kwargs)
  File "/mnt/2TB_SSD/Auto-GPT/autogpt/app/cli.py", line 121, in main
    run_auto_gpt(
  File "/mnt/2TB_SSD/Auto-GPT/autogpt/app/main.py", line 174, in run_auto_gpt
    run_interaction_loop(agent)
  File "/mnt/2TB_SSD/Auto-GPT/autogpt/app/main.py", line 255, in run_interaction_loop
    command_name, command_args, assistant_reply_dict = agent.think()
  File "/mnt/2TB_SSD/Auto-GPT/autogpt/agents/base.py", line 121, in think
    return self.on_response(raw_response, thought_process_id, prompt, instruction)
  File "/mnt/2TB_SSD/Auto-GPT/autogpt/agents/base.py", line 345, in on_response
    "assistant", llm_response.content, "ai_response"
AttributeError: 'str' object has no attribute 'content'

I printed llm_response:
print("type:", type(llm_response), "content:", llm_response)

type: <class 'str'> content: 
{
  type: "object",
  properties: {
    thoughts: {
      text: {
        type: "string",
        required: true
      },
      reasoning: {
        type: "string",
        required: true
      },
      plan: {
        type: "string",
        required: true
      },
      criticism: {
        type: "string",
        required: true
      }
    },
    command: {
      name: {
        type: "string",
        required: true
      },
      args: {
        type: "array",
        items: {
          type: "string",
          required: true
        }
      }
    }
  }
}

If I takeout the .content it just says Thinking \ (loading sign spinning) forever, and one the text-generation-webui side in the terminal it shows that it outputted a message:
Output generated in 54.56 seconds (3.15 tokens/s, 172 tokens, context 761, seed 1172004049)
but nothing happens

here are the flags I'm using for the server.py
--listen --model-menu --api --gpu-memory 12 --verbose --auto-devices --trust-remote-code (got some of these options from step 2 in the readme, I've tried with the setting.yaml template too)

Could I get help understanding what is going wrong? I know there are frequent text-generation-webui updates so some changes might have broken this plugin. Let me know if I need to provide additional information to help fix this.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.