Giter VIP home page Giter VIP logo

autogpt-telegram-chatbot's Introduction

Tutorial: Deploy your own AutoGPT Telegram bot

๐Ÿ’› Credits to yoheinakajima for bringing babyagi to life.

This project contains the necessary scaffolding to deploy your own AutoGPT/BabyAGI via LangChain agents with memory.

These 3 steps should get you online. If not, shoot me a message on Discord. Happy to help you out.

Let's go:


The no-coder way ๐Ÿ˜Ž
  1. Step 1: Go to https://www.steamship.com/build/auto-gpt

  2. Step 2: Click launch

  3. Step 3: Copy-paste your bot token and click create ๐Ÿš€

The coder way ๐Ÿ’ป
  1. Step 1: Edit the AutoGPT agent in src/babyagi.py. You can also use the vanilla babyagi in the file.

  2. Step 2: Pip install the latest steamship_langchain: pip install --upgrade steamship_langchain

  3. Step 3: Run python deploy.py. The script will ask you to copy-paste your bot token. Learn how to get a Telegram bot token here.

autogpt-telegram-chatbot's People

Contributors

douglas-reid 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  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  avatar  avatar  avatar  avatar  avatar  avatar

autogpt-telegram-chatbot's Issues

Unable to get package manifest

I'm doing it like a few days ago and now I get this error. I can't see the package on the web either.

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 274, 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 "<frozen importlib._bootstrap>", line 1014, in _gcd_import
  File "<frozen importlib._bootstrap>", line 991, in _find_and_load
  File "<frozen importlib._bootstrap>", line 975, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 671, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 843, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/var/task/api.py", line 9, in <module>
    from babyagi import solve_agi_problem
  File "/var/task/babyagi.py", line 4, in <module>
    from langchain import LLMChain
  File "/var/task/langchain/__init__.py", line 6, in <module>
    from langchain.agents import MRKLChain, ReActChain, SelfAskWithSearchChain
  File "/var/task/langchain/agents/__init__.py", line 2, in <module>
    from langchain.agents.agent import (
  File "/var/task/langchain/agents/agent.py", line 17, in <module>
    from langchain.chains.base import Chain
  File "/var/task/langchain/chains/__init__.py", line 2, in <module>
    from langchain.chains.api.base import APIChain
  File "/var/task/langchain/chains/api/base.py", line 8, in <module>
    from langchain.chains.api.prompt import API_RESPONSE_PROMPT, API_URL_PROMPT
  File "/var/task/langchain/chains/api/prompt.py", line 2, in <module>
    from langchain.prompts.prompt import PromptTemplate
  File "/var/task/langchain/prompts/__init__.py", line 3, in <module>
    from langchain.prompts.chat import (
  File "/var/task/langchain/prompts/chat.py", line 10, in <module>
    from langchain.memory.buffer import get_buffer_string
  File "/var/task/langchain/memory/__init__.py", line 23, in <module>
    from langchain.memory.vectorstore import VectorStoreRetrieverMemory
  File "/var/task/langchain/memory/vectorstore.py", line 10, in <module>
    from langchain.vectorstores.base import VectorStoreRetriever
  File "/var/task/langchain/vectorstores/__init__.py", line 2, in <module>
    from langchain.vectorstores.analyticdb import AnalyticDB
  File "/var/task/langchain/vectorstores/analyticdb.py", line 15, in <module>
    from langchain.embeddings.base import Embeddings
  File "/var/task/langchain/embeddings/__init__.py", line 18, in <module>
    from langchain.embeddings.openai import OpenAIEmbeddings
  File "/var/task/langchain/embeddings/openai.py", line 66, in <module>
    class OpenAIEmbeddings(BaseModel, Embeddings):
  File "pydantic/main.py", line 198, in pydantic.main.ModelMetaclass.__new__
    fields[ann_name] = ModelField.infer(
  File "pydantic/fields.py", line 506, in pydantic.fields.ModelField.infer
    return cls(
  File "pydantic/fields.py", line 436, in pydantic.fields.ModelField.__init__
    self.prepare()
  File "pydantic/fields.py", line 552, in pydantic.fields.ModelField.prepare
    self._type_analysis()
  File "pydantic/fields.py", line 663, in pydantic.fields.ModelField._type_analysis
    self.sub_fields = [self._create_sub_type(t, f'{self.name}_{display_as_type(t)}') for t in types_]
  File "pydantic/fields.py", line 808, in pydantic.fields.ModelField._create_sub_type
    return self.__class__(
  File "pydantic/fields.py", line 436, in pydantic.fields.ModelField.__init__
    self.prepare()
  File "pydantic/fields.py", line 552, in pydantic.fields.ModelField.prepare
    self._type_analysis()
  File "pydantic/fields.py", line 668, in pydantic.fields.ModelField._type_analysis
    elif issubclass(origin, Tuple):  # type: ignore
  File "/var/lang/lib/python3.8/typing.py", line 774, in __subclasscheck__
    return issubclass(cls, self.__origin__)
TypeError: issubclass() arg 1 must be a class
Aborted!

The answers of bot are incomplete

I have to prompt like "go on" to continue, I wonder whether it will cost too many extra tokens when the dialog is long.

Can it just automatically complete its answers?

How to increase the number of characters replied by the telegram bot

I have successfully set up a telegram bot, and it can answer my questions normally.
However, when replying to some long text, such as more than 500 words, it will automatically truncate and can not display the complete reply content.
I want to ask how to adjust the maximum number of characters it can display. Thank you.
Screenshot_2023-04-29-10-19-54-995_org telegram plus-edit

My bot won't stop

I asked for a few copywriting sentences and it just started to randomly select other tasks to do and now won't stop, just keeps on going. It started to give me a to do list on how to deep clean my bathroom ๐Ÿ˜‚ and much more random stuff.

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.