You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
I wanted to start by
talking about how important it is to democratize AI
. Unfortunately, most new applications or discoveries in this field end up enriching some big companies, leaving behind small businesses or simple projects. One striking example of this is Autogpt, an autonomous AI agent capable of performing tasks.
Autogpt and similar projects like BabyAGI
only work with paid APIs, which is not fair
. That's why I tried to recreate a simpler but very interesting and, above all, open-source version of Autogpt that
does not require any API and does not need any particular hardware.
I believe that by providing free and open-source AI tools, we can give small businesses and individuals the opportunity to create new and innovative projects without the need for significant financial investment.
This will allow for more equitable and diverse access to AI technology, which is essential for advancing society as a whole.
To create an open-source version of Autogpt that does not require paid APIs or specific hardware,
we performed a reverse engineering process on ChatGPT
, a language model developed by OpenAI. By doing so, we were able to use the agents and new technologies of langchain for free.
We then created a custom LLM wrapper with langchain,
which can be used as a plug-and-play solution with any langchain function or tool 💡
.
fromChatGPTAPIimportChatGPT# Instantiate a ChatGPT object with your tokenllm=ChatGPT(token="YOURTOKEN")
# Generate a response based on the given promptresponse=llm("Hello, how are you?")
# Print the responseprint(response)
The code snippet provided above shows how to use our custom ChatGPT LLM class to interact with the language model. It requires a token from the ChatGPT API, which can be obtained from
https://chat.openai.com/api/auth/session
.
Please note that there is a limit of 50 requests per hour for each account on the ChatGPT API 💣. Therefore, we implemented a call counter in our ChatGPT class to prevent exceeding this limit.
We believe that our open-source version of Autogpt will promote equitable and diverse access to AI technology and empower individuals and small businesses to create innovative AI projects without significant financial investment.