naveedjanmo

Ayo this looks sick

This is an interesting idea. I'll have a think about a way to start measuring it. In Unriddle, any responses given that aren't drawn from the document are prefaced with a message to that effect. The bot usually says something like "I appreciate your curiosity about [query], but as an AI assistant, my primary focus is to provide advice on [document description]."

Yeah I think you're right - the 32k context window for GPT-4 (not available for everyone yet) is already enough for research papers. I'm using a library called Langchain, there's also LlamaIndex.

*API calls to GPT-4

It's just the GPT-4 API - the chunks are sent as part of a prompt. In that case it won't use data from all chunks but it will try to find any chunks that provide descriptions of the document. I've found with research papers, for example, it fetches parts of the introduction and abstract.

Right now it's just one pdf per bot but yeah you could hack it by merging the pdfs and then generating a new bot. Interesting suggestion - did you notice a particular hallucination? What kind of docs would be high vs. low temperature?

I'm just exploring whether or not it's useful. If people continue using it and/or it evolves into something more useful, I'll likely charge a monthly fee for access to certain features (e.g. longer pdfs, merging multiple pdfs into one bot, having multiple bots). The plan is to keep it partially free though

There's an OpenAI API for vectorizing which I'm accessing through the Langchain library :)

Vectorisation is done via OpenAI's embedding API. And the chunking/querying is happens through the Langchain library. But there are a few different ways of doing it - another good library is LLamaIndex.

Hey! I'm the developer of Unriddle - it works using text embeddings. The document is split into small chunks and each chunk is assigned a numerical representation, or "vector", of its semantic meaning and relation to the other chunks. When a user prompts this too is assigned a vector and then compared to the rest of the chunks. The similar chunks are then fed into GPT-4 along with the query, ensuring the total number of words doesn't exceed the context window limit.

Thanks for the feedback. I get your point but with Unriddle users curate information for the index that sits on top of GPT-4. It's just one doc for now but in the future it will be multiple - this curation of info sources is where the "own" part comes in.