Build Intelligent Chatbots like never before with just a few lines of Python code.
Customize chatbots that can answer questions and converse with users just like humans.
(A thread) ๐งต๐
Customize chatbots that can answer questions and converse with users just like humans.
(A thread) ๐งต๐
Presenting conversant by Cohere AI
conversant is a modular, flexible and extensible Python library that lets you create any kind of chatbot you want!
It is the part of the sandbox project by Cohere that aims to make building and deploying LLM-powered apps a piece of cake.
conversant is a modular, flexible and extensible Python library that lets you create any kind of chatbot you want!
It is the part of the sandbox project by Cohere that aims to make building and deploying LLM-powered apps a piece of cake.
conversant comes up with the following out-of-the-box features:
- In-built integration with Cohere API
- chat history support
- customize personas
- Install with pip
- In-built integration with Cohere API
- chat history support
- customize personas
- Install with pip
It comes loaded with some prebuilt chatbot personas including:
- client support agent
- watch sales agent
- math teacher
- fantasy wizard
And the best thing of all - you can create your own persona with just a description and a few example conversations!
- client support agent
- watch sales agent
- math teacher
- fantasy wizard
And the best thing of all - you can create your own persona with just a description and a few example conversations!
How conversant works?
conversant uses prompt completion to define a chatbot persona with a description and a few examples.
The prompt is sent as input to Cohere's co.generate() endpoint to generate text in a few-shot manner from the examples and the current dialogue context.
conversant uses prompt completion to define a chatbot persona with a description and a few examples.
The prompt is sent as input to Cohere's co.generate() endpoint to generate text in a few-shot manner from the examples and the current dialogue context.
Cohere's chatbot application is built and deployed using @streamlit. Try it out yourself ๐ cohere-ai-sandbox-conversant-lib-appstreamlit-example-hgyk4x.streamlit.app
You can even edit the existing personas in the streamlit application itself and customize them for your usecase.
You can even edit the existing personas in the streamlit application itself and customize them for your usecase.
@streamlit All you need to build this interesting application is cohere's API key and a few lines of Python code.
Get the API key here ๐ cohere.ai
Source code ๐ github.com
Get the API key here ๐ cohere.ai
Source code ๐ github.com
@streamlit That's a wrap ๐
Follow me @Saboo_Shubham_ to stay updated with the latest advancements in AI, ML and NLP.
If you liked this tweet, jump to the first tweet and RT it!
Follow me @Saboo_Shubham_ to stay updated with the latest advancements in AI, ML and NLP.
If you liked this tweet, jump to the first tweet and RT it!
Loading suggestions...