I would have loved some elaboration on how "the data" came to be. It appears in the sample app that each document is some subset of technical docs? That can be helpful, but when each document is very large you run into token limitations and increased probability of hallucinations. That's what I ran into when I tried to build a similar application that offers "GPT over docs". Figuring out your strategy for splitting documents isn't trivial.
Build a chatbot with custom data sources, powered by LlamaIndex
11–13 of 13 posts
Re: Build a chatbot with custom data sources, powered by LlamaIndex
#12I'd love to set up one of those fancy chatbots for my almost dead IRC channel. Does anyone know something out there?
Check out LLMStack ( https://github.com/trypromptly/LLMStack ). It allows you to build LLM apps and chatbots and provides you with an API for integration. It should be possible to write a simple script to link LLMStack's app with your IRC channel. API documentation for running the apps is at https://llmstack.ai/docs/apis/introduction#apps . Let me know if you need help with this.
Thank you. I'll check it out.
Re: Build a chatbot with custom data sources, powered by LlamaIndex
#13I would have loved some elaboration on how "the data" came to be. It appears in the sample app that each document is some subset of technical docs? That can be helpful, but when each document is very large you run into token limitations and increased probability of hallucinations. That's what I ran into when I tried to build a similar application that offers "GPT over docs". Figuring out your strategy for splitting d…
It's not and that's why most of these solutions utilize an indexing/search service to provide more targeted data to feed into "context" instead of just burning tokens with whole/chunked docs.