-
Notifications
You must be signed in to change notification settings - Fork 48
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Test GPT Integration ("ask the docs") #48
Comments
ChatGPT (OpenAI) demo on cocalc.com (SageMath): |
"Could you train a ChatGPT-beating model for $85,000 and run it in a browser?" (cf. Hackernews discussion) Related tools: |
...no resources in the foreseeable future. Still, interesting to see what the Rocket Chat developers set up for their docs #48 (comment). |
...recent movement in this area: Kagi Sidekick |
Hi @michaelweinold , Something that you can look at also is Flowise You can easily build a chatbot that reads the docs and uses that as a knowledge base. It works with openai and locally hosted models. You can have it in a docker container and it has an API endpoint to interact with the model, it even gives you a piece of html code you can add to the website, which will show a chat bubble. I tested it with openai, it works ok, it would work better as the docs get better. Here are some of the responses: Creating a Life Cycle Assessment (LCA) in Brightway typically involves creating an instance of the LCA class, which coordinates the assessment. The basic steps, as outlined in the documents provided, are as follows:
In Python code, a basic example might look something like this: from brightway2 import LCA
my_functional_unit = {my_activity: 1} # replace 'my_activity' with your specific activity
my_method = my_impact_method # replace 'my_impact_method' with your chosen impact assessment method
lca = LCA(my_functional_unit, my_method)
lca.lci() # Perform the life cycle inventory analysis
lca.lcia() # If you have an LCIA method, perform the life cycle impact assessment
lca.score # Gets the value The example provided is a basic outline and might not work verbatim. Please refer to the official Brightway2 documentation or relevant support channels for the exact process and commands. I also tested it with localai, but my computer doesn't have much resources to run a locally hosted model. To do that i just replaced the openai block in flowise with a localai block. here is some of the tests. Here is what the chat interface looks like Overall, its not perfect, but i will run some more tests to see if i can improve the results |
...more recent developments at Kagi: Kagi Assistant |
Potential Tools
mpaepper/content-chatbot
arc53/docsgpt
danswer-ai/danswer
The text was updated successfully, but these errors were encountered: