This is a nifty tool. It’s existence alongside the emerging LLMs reminds me of the two diametrically opposed approaches to harnessing it all:
1. Store the knowledge in a highly structured way and interrogate it with a precise and rigorous query language to extract the exact answer you want based on a well defined set of rules
2. Store the knowledge in whatever ad hoc way it’s produced, and then rely on a higher form of intelligence to take an equally ad hoc query, feed it through the entire universe of knowledge with some attention mechanism, and magically return a (statistically significant) response
Both approaches are so satisfying when they work. Of course you also have everything in between and then you have tools like LangChain that start to bring it all together.
But, there is another option. The tool (presumably AI/ML based) that takes the ad-hoc query and turns it into a precise query to the structured-data tool in order to return precise results.
I hope that this will be Googles answer to ChatGPT... i.e. a chat interface to their existing search tool. This should then be able to "explain" the query its actually generated to the tool as a side-effect.
For sure, I just edited my comment to mention LangChain, which starts to get at that capability. Would be nice to see LangChain integrate with Trustfall similar to how it can integrate with Wolfram Alpha.
1. Store the knowledge in a highly structured way and interrogate it with a precise and rigorous query language to extract the exact answer you want based on a well defined set of rules
2. Store the knowledge in whatever ad hoc way it’s produced, and then rely on a higher form of intelligence to take an equally ad hoc query, feed it through the entire universe of knowledge with some attention mechanism, and magically return a (statistically significant) response
Both approaches are so satisfying when they work. Of course you also have everything in between and then you have tools like LangChain that start to bring it all together.