Yes! We have a public API that you can use to integrate DocsBot into your own applications. You can find the documentation here: https://docsbot.ai/documentation/developer. We also have our admin API for managing your DocsBots and sources.

Dec. 3, 2023

Unlike traditional search, DocsBot inherits GPT's understanding of any language found on the Internet. So even if you index your documentation in English, it can respond in the language of the question. Asking questions in a different language than what you trained it on may not be as effective right now, as it will be less likely to be able to find the best context from our embeddings index. We are working on improving this!

Oct. 28, 2023

It's a bit technical, but here is a brief overview. We use OpenAI's embedding and ChatGPT APIs, as well as vector databases to store our index. All ingested documentation is cleaned up and divided into smaller chunks and labeled by source. We then use the GPT embedding API to generate a vector representation of each chunk and store it in our vector db index. When a user asks a question, we convert it to an embedding, and perform an advanced semantic search for closest matches to the user's query. Then we take the most relevant chunks, included them as context along with the original question, and use the ChatGPT API to generate a response in markdown format that we then convert to HTML and display to the user.

Oct. 28, 2023

We generally don't store PII unless you specifically upload it, or a user provides it in a question to your bots. We store queries and responses in our database to be able to privide and improve on the service. Queries and responses also pass through OpenAI and are subject to their privacy policy as well. We use Bento (https://bentonow.com/) for usage tracking, email, and marketing. Please see our privacy policy for more details: https://docsbot.ai/legal/privacy-policy.

Oct. 28, 2023