Enhancing GPT's External Data Lookup Capacity: A Walkthrough
Accessing external information and blending it with AI-generated text is a capability that would significantly enhance AI applications. For instance, the combination of OpenAI's GPT and external data lookup, when executed efficiently, can lead to more comprehensive and contextually accurate output.
One promising approach is to leverage the LangChain API to extract and split text, embed it, and create a vectorstore which can be queried for relevant context to add to a prompt template. A helpful demonstration of how LangChain works can be found on YouTube.
The unique aspect lies in how you query and write your prompt to the API. An innovative idea is to prompt for an outline using a research question or topic statement as the query, have GPT format the outline in a specific way for easy split and query, and then feed individual statements while keeping the overall context intact. If you don't have access to the API, the prompt generation can be done manually in ChatGPT.
Another workaround to enhance data lookup can be executed using Adobe Acrobat to combine PDFs into a single file and then uploading it to chatpdf. While this might not provide a citation to the specific PDF page, it's still an efficient way to pool resources.
There are other tools available for this purpose too. Vault.pash.city and ChatGPT Splitter are worth exploring. Bing Assistant also has an interesting feature where it can answer questions about documents opened in Edge.
It's important to remember that these methods are experimental and under development. They offer interesting possibilities and are worth exploring if you're interested in enhancing AI's interaction with external data.
Tags: GPT, External Data Lookup, LangChain, API, Vectorstore, ChatGPT, PDF, Bing Assistant, Vault.pash.city, ChatGPT Splitter